title_s
stringlengths 2
79
| title_dl
stringlengths 0
200
| source_url
stringlengths 13
64
| authors
listlengths 0
10
| snippet_s
stringlengths 0
291
| text
stringlengths 21
100k
| date
timestamp[ns]date 1926-02-14 00:00:00
2030-07-14 00:00:00
| publish_date_dl
stringlengths 0
10
| url
stringlengths 15
590
| matches
listlengths 1
278
|
|---|---|---|---|---|---|---|---|---|---|
The Case for AI and Machine Learning in Talent Management - ADP
|
The Case for AI and Machine Learning in Talent Management
|
https://www.adp.com
|
[] |
Artificial Intelligence in the workplace is more than a catch phrase in organizations today. With the pace of technology advancements and usage rapidly...
|
Trends The Case for AI and Machine Learning in Talent Management Trish McFarlane
The future is already here; artificial intelligence and machine learning can help create HR process effencies and improve candidate experience. Read on.
Artificial Intelligence in the workplace is more than a catch phrase in organizations today. With the pace of technology advancements and usage rapidly accelerating, the acceptance and reliance on such tools is also growing. The first thing HR leaders need to understand is what artificial intelligence (AI) is and what it includes. According to Ben Eubanks, an industry expert from Lighthouse Research, "AI is a term that encompasses multiple types of computerized programs. In fact, someone talking about AI can be discussing anything from facial recognition tools powered by neural networks to machine learning that predicts the best word to use in a subject line to improve email open rates."
There are two specific aspects of artificial intelligence that impact HR technologies: machine learning and natural language processing. Machine learning looks for patterns in large amounts of data and then makes predictions based on those patterns. The other is natural language processing. This is when a computer "understands" and responds to the written or spoken word.
HR professionals are empowered to purchase technologies that incorporate AI into the way the organization handles people through the entire employee life cycle. Right now, it is most common to have systems enhanced by AI to answer simple questions using data the system has stored. As more and more interactions with the data accumulate, the system learns and operates seamlessly within the employee's work day.
Some examples to consider are:
Talent Acquisition
A chatbot with natural language processing that can assist as you interview a candidate. Imagine you are interviewing a candidate and are asked a question about employee benefits, tuition reimbursement, or sabbaticals. You may not know those answers. Instead of looking them up or referring to HR, the chatbot could seamlessly interject with the needed information to keep the interview going.
In speaking with Jen Phillips-Kirkwood, Vice President-Future of Work at ADP, she said, "According to the ADP Research Institute® and the Workforce Vitality Report, 27 percent of workers would jump to a new job at the same or less rate of pay. Why? How? Technology has enabled workers to switch more easily than ever. AI-driven strategies are helping lure workers away by courting them with opportunities that are attractive to their values, sometimes even with a pay decrease."
Learning
The learning platform will have data about training employees have completed, their career path, and which roles are next in line for them. Using that information, the system will recommend not only traditional training courses, but micro learning, video learning and on-the-job opportunities that match the desired skill development.
Payroll
A platform that will allow you to access payroll data using voice commands. Additionally, one that will allow you to predict future payroll information by modeling out various payroll scenarios.
Workforce Management
The platform will allow you to record time, ask for time off, schedule extended leaves, or approve time all with voice prompts.
More from Phillips-Kirkwood: "Serving up the AI within existing worker and leader experiences is key. Those I consult with often say, 'My leaders aren't ready to use this…' or 'My turnover is too high to invest time to teach my leaders to leverage this.' The whole point of AI is to simplify, notify, and guide the leaders within an experience they are already comfortable in – such as mobile – without the expectation that they have to be the 'experts' of AI or data.
"By placing AI and data insights at the perfect intersection of where life meets work (i.e. via mobile), it empowers the leaders to leverage it with meaningful impact. In fact we have a client in the convenience store industry who didn't let the term 'AI' intimidate him. And it lead to more than a $3 million savings in the first year," Phillips-Kirkwood concluded.
Offboarding
A platform that will not only offer up exit information and forms, but that will engage the employee in ongoing connection so that as their career progresses elsewhere and they build additional skills, the now "former" employee can be considered for any future opportunities as they become available.
Artificial intelligence is not meant to be a replacement for people. It is a tool that can boost the productivity and enable the support HR has longed for. HR teams looking for a way to predict and handle many of the process-driven tasks now use AI. And as we rapidly develop more use cases, we're moving toward a workplace assisted by virtual teammates. Right now, that may take the form of a simple chat bot. But as workers and HR practitioners gain comfort interacting with devices like Amazon Echo, Google Home, Bixby, or Siri, they will begin to see the value of having similar technologies in place at work.
Right now, the priority is two-fold. First, understand process points in your organization that will benefit from either handling repetitive tasks, or from prediction of future behaviors. Second, work with your vendors to understand how they are currently using artificial intelligence in their solution. Then, ask how it fits into the product roadmap. Armed with this knowledge, you will be able to be the partner and guide for your organizational leaders so that you have the best opportunity for success.
Ready to dive in?
These are just of a few of the areas explored during an honest and interactive virtual discussion you can replay on-demand anytime: Deconstructing Talent Best Practices to Find What Really Works. A panel of ADP industry experts, including Jen Phillips-Kirkwood, share real life stories of working with organizations and their platforms as they navigate how to create their right-fit talent strategy.
See how you can unite technology and talent to transform the employee experience and improve performance.
| 2019-07-17T00:00:00 |
2019/07/17
|
https://www.adp.com/spark/articles/2019/07/the-case-for-ai-and-machine-learning-in-talent-management.aspx
|
[
{
"date": "2023/01/01",
"position": 75,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 73,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 71,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 79,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 79,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 79,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 75,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 74,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 75,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 71,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 80,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 78,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 79,
"query": "machine learning workforce"
}
] |
How Can AI change the Face of Workforce Management? - Workstatus
|
How AI Impact the Future of Workforce Management
|
https://www.workstatus.io
|
[
"Ash Grover"
] |
With the help of machine learning, one can analyze historical data related to employees' performance. This helps managers identify areas where high-performing ...
|
Artificial Intelligence (AI) is moving up the business value chain, with businesses recognizing its potential to assist in workforce management and planning.
Organizations are turning to automation to remain competitive in the new economy to eliminate manual effort and replace it with more efficient processes driven by artificial intelligence. They’re also looking for methods to utilize AI better to improve how they use employee data.
As per Gartner’s research, it is anticipated that by 2023, 60% of large businesses will have implemented digital transformation projects to automate HCM administration (HCM) activities.
By 2025, 60% of large businesses and mid-size firms will be using cloud-deployed HCM suites for administrative and talent management.
However, even if you remove these gaps entirely using HR software, most organizations will still need to get 20-30% of their HCM needs from other solutions.
Most of the invested money will be used for the company’s fundamental HR administration, HR service management (HRSM), talent management, and workforce management functions.
However, business executives are actively engaged in determining how to properly analyze and exploit the data that is accessible through their HCM platforms, particularly in terms of operational planning from a financial modeling standpoint.
Many company executives could not have foreseen the global coronavirus pandemic’s wide-scale challenges. However, the significant changes in how employees must operate have shed light on the necessity of optimizing efficiency in everything from staff to data and forecasting processes within corporate workforce planning.
The rapid growth of AI in the public sector recognizes that more efficiency can be gained from services by deploying this technology. As digital transformation projects begin to supercharge the shift towards a ‘predictive’ capability in forecasting and planning, many organizations are confronted with the twin challenges of finding the appropriate data science and analytics talent to drive these initiatives forward and incorporating AI-assisted processes into their existing workflows.
Read the full blog to know how AI can change the face of WFM in 2021-
How Is AI Leading Workforce Management?
AI is the new buzzword in almost every industry, and workforce management (WFM) is no exception. Its ability to analyze massive amounts of data and automate simple tasks can potentially change the way many WFM processes work.
AI will manage workforce planning, scheduling, timekeeping, and performance management.
1. AI can help with workforce planning
In the past, workforce planning was primarily a manual process that involved looking at data such as hiring plans, employee attrition rates, and business forecasts to predict future staffing needs.
However, this process can be improved with the help of AI.
AI can analyze historical data to identify patterns and trends. It can also use predictive analytics to predict future needs based on current data. This helps organizations plan their workforce more effectively and ensure that they have the correct number of employees at the right time.
Also read: 7 Leadership Tips for Digital Workforce Management
2. AI can help with scheduling
Employee scheduling is one of the most time-consuming and challenging tasks in WFM. With the help of AI, it can be automated and simplified.
Many organizations are already using machine learning to optimize schedules by analyzing historical data related to employees’ task preferences, availability, skill sets, workflows, and time required for completing tasks.
3. AI can help with timekeeping
Timekeeping is another crucial aspect of WFM. It has previously been accomplished manually by keeping track of employee hours worked.
However, AI can easily automate timekeeping tasks for better productivity and management.
AI can track employee hours worked automatically by reading time logs or attendance records. This helps organizations to save time and money on administrative tasks.
If you are looking for any AI-powered employee monitoring software, consider Workstatus with geofencing capabilities.
4. AI can help with performance management
Performance management is another area that can benefit from the use of AI. With the help of machine learning, one can analyze historical data related to employees’ performance. This helps managers identify areas where high-performing employees excel and low-performing employees need improvement, with minimal bias or subjectivity.
Thus, these are some ways through which AI is leading workforce management.
Machine learning algorithms enable an organization to take all the data about employee performance and develop models that predict future outcomes. This helps organizations identify at-risk employees before they become a problem and make necessary changes to improve their performance.
AI will be used extensively in workforce management to automate simple tasks, analyze data, and predict future needs. This will help organizations run their businesses more effectively and improve the performance of their employees.
Read more: How AI can Detect Employee Violations Quicker Than Ever
What To Expect From An AI-Enabled Workforce Management System?
As Artificial Intelligence (AI) continues to evolve, businesses are looking for ways to incorporate the technology into their operations. One area that is seeing a lot of interest is workforce management.
AI-enabled systems can help organizations optimize their workforce planning and scheduling, improve communication and collaboration, and identify potential issues before they become problems.
AI-enabled workforce management systems will be able to do the following:
Automatically match workers with the right tasks based on their skills and preferences.
Recommend task assignments and changes to workers in real-time based on their individual skill sets, work preferences, and job performance.
Generate reports on worker productivity and task performance.
Identify areas that need improvement and recommend changes to improve worker efficiency.
Assist managers in making informed decisions about staffing levels and department restructuring.
Automate timekeeping and payroll processes.
Facilitate communication between workers and management.
Assist in the training and development of workers.
Help to create a more engaged, productive workforce.
The impact of AI on the workforce management process is clear: it will automate many routine tasks, making the process more efficient and effective.
With the help of AI, managers will be able to make better decisions about their workforce, leading to increased productivity and improved business results.
Which AI-Enabled Tool Is The Best For Workforce Management?
There are many AI-enabled tools available in the market that can make workforce management easier. The best tool for your organization is the one that helps you manage your organization in 360 degrees.
Workstatus, the best workforce management software, includes more than 15 features for employee management and productivity enhancement, giving your organization the power to function like the big 4s of the world.
Here’s how Workstatus can help you. You can also take a live demo to walk through the product more efficiently.
Workstatus is a cloud-based workforce management software that helps firms monitor their employees’ work hours to improve business activities.
It also has features for payroll, tax benefits compliance with labor rules, employment contracts, and HR data security, including password encryption, an audit log, and built-in job costing reports.
Key Features:
GPS tracking system
Online timesheets
Summary reports
Productivity tracking
Team scheduling
Simple Payroll
Geofencing
Online invoicing
Project estimation
Attendance management
Task management
Pricing:
Free Forever Package: ₹0
Starter Package: ₹366.07/user/month
Scale Package: ₹732.87/user/month
Enterprise Package: ₹1320.49/user/month
Overall, Workstatus offers a comprehensive solution for workforce management with various features that cater to businesses of different sizes.
With the help of AI, it can help organizations automate routine tasks, monitor employee productivity, and manage their workforce efficiently.
Final Thoughts
As AI technology continues to evolve, it is becoming increasingly capable of performing tasks that were once exclusively performed by humans.
One area where AI is proving particularly useful is workforce management. AI-powered workforce management software tools can help businesses optimize scheduling, enhance communication and collaboration, and identify potential problems before they become critical issues.
While some may worry that this increased automation may lead to job losses, it’s important to remember that there are also opportunities for those who have the skills to work alongside these new technologies.
If you’re struggling to manage remote employees, AI-powered GPS tracking software could be the solution you need.
Request a free demo to learn more about how this technology can help streamline your workforce management processes.
FAQs
How can AI improve workforce planning and scheduling?
AI can use predictive analytics to forecast future workforce requirements based on historical data, such as sales or customer traffic. This can help managers schedule the right number of employees with the necessary skills, reducing the need for overtime or understaffing.
Additionally, AI-powered scheduling software like Workstatus can automatically adjust schedules in real-time based on unexpected changes, such as sick leave or last-minute staff requests.
Can AI be used for performance management?
Yes, AI can help automate performance management tasks such as performance tracking, goal setting, and feedback delivery.
AI-powered tools like Workstatus can analyze employee data to identify areas where improvement is needed, suggest personalized development plans, and provide managers with insights to help them make informed decisions. AI can also help ensure performance evaluations are objective and fair by minimizing human biases.
An AI form generator can also help you create feedback forms while you are monitoring performance.
Revolutionize Your Team's Productivity Today! Unlock Your Team's Full Potential. Book a Demo Start Free Trial
| 2021-12-13T00:00:00 |
2021/12/13
|
https://www.workstatus.io/blog/workforce-management/how-can-ai-change-the-face-of-workforce-management/
|
[
{
"date": "2023/01/01",
"position": 79,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 79,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 82,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 84,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 84,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 84,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 78,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 77,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 83,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 78,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 82,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 96,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 90,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 96,
"query": "machine learning workforce"
}
] |
Applying Artificial Intelligence for Workforce/HR Optimization
|
Applying Artificial Intelligence for Workforce/HR Optimization
|
https://decisionbrain.com
|
[
"Alexa Salles"
] |
How to work around a number of workforce challenges and optimize workforce planning and scheduling with Artificial Intelligence ... Machine Learning experts. This ...
|
Labor markets are now trying to settle into the post-pandemic world. Two enduring features of this new environment are worker shortages and work-from-home (WFH) or at least hybrid work models.
The WFH and hybrid work models are advantageous for employee productivity and morale, yet despite having had 2 years of warm-up to this new normal, few organizations have baked in the necessary changes to their systems and processes to get back to pre-pandemic performance levels.
In this paper, we discuss how to work around a number of workforce challenges companies face today and optimize workforce planning and scheduling at a strategic, tactical, and operational level.
| 2022-06-03T00:00:00 |
2022/06/03
|
https://decisionbrain.com/applying-ai-for-workforce-hr-optimization/
|
[
{
"date": "2023/01/01",
"position": 84,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 83,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 87,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 88,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 88,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 88,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 84,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 83,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 87,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 84,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 87,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 90,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 87,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 91,
"query": "machine learning workforce"
}
] |
Why utilizing artificial intelligence (ai) and machine learning ... - Redsis
|
Why utilizing artificial intelligence (ai) and machine learning is essential to solving your retail labor and execution challenges
|
https://redsisusa.com
|
[] |
You need to optimize labor spend and ensure proper staffing to be successful during disruptive times. Here are six ways intelligent workforce management ...
|
The holiday season is fast approaching, and I know you are facing more challenges than ever before.
Current shortages of retail team candidates will make it difficult to keep your store operations functioning properly. With store managers stretched thin, they may not have time to train employees on new skills, work with them to improve their current skillsets, or figure out how to utilize their skills optimally in the store. Store managers may also struggle to efficiently utilize the staff they have, period. With both customer and employee expectations higher than ever before, it can be hard to keep track of each team member’s scheduling preferences and availability.
However, it is important they have a way to do these things to keep morale up. Employees could experience burnout, frustration over their current roles, or a desire for a better work environment if they don’t feel like they’re adding value to the store. And if a store or team is understaffed, leaving associates feeling overworked, they may take advantage of the competitive labor market and find employment elsewhere.
So, this might be a good time to look at how intelligent workforce management technology could help ensure managers are balancing employee and store needs while remaining compliant with labor laws and regulations. You don’t want to add fines and penalties to your (now, very long) list of challenges.
| 2021-11-22T00:00:00 |
2021/11/22
|
https://redsisusa.com/blogs/why-utilizing-artificial-intelligence-ai-and-machine-learning-is-essential-to-solving-your-retail-labor-and-execution-challenges/
|
[
{
"date": "2023/01/01",
"position": 86,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 86,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 90,
"query": "machine learning workforce"
},
{
"date": "2023/09/01",
"position": 90,
"query": "machine learning workforce"
},
{
"date": "2023/10/01",
"position": 90,
"query": "machine learning workforce"
},
{
"date": "2024/03/01",
"position": 90,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 86,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 86,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 93,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 86,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 90,
"query": "machine learning workforce"
},
{
"date": "2025/02/01",
"position": 89,
"query": "machine learning workforce"
},
{
"date": "2025/03/01",
"position": 86,
"query": "machine learning workforce"
},
{
"date": "2025/04/01",
"position": 90,
"query": "machine learning workforce"
}
] |
Program - Machine Learning - AdventHealth University
|
AdventHealth University
|
https://workforce.ahu.edu
|
[] |
Ready to begin your career journey or have more questions? Connect with a Workforce Training Specialist today! First Name *.
|
Machine learning is a branch of artificial intelligence (AI) that empowers computers to learn from data without being explicitly programmed. This involves developing algorithms that can analyze data, identify patterns, and make predictions or decisions based on that analysis.
This program focuses on the practical application of machine learning using the Python programming language. You’ll learn to:
Build and train machine learning models: Develop and implement various machine learning algorithms, including classification and regression models.
Analyze and interpret data: Explore and understand the characteristics of different datasets and prepare them for analysis.
Evaluate model performance: Assess the accuracy and effectiveness of machine learning models using appropriate evaluation metrics.
| 2023-01-01T00:00:00 |
https://workforce.ahu.edu/program-machine-learning/
|
[
{
"date": "2023/01/01",
"position": 95,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 96,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 96,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 95,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 97,
"query": "machine learning workforce"
}
] |
|
Manager, Machine Learning - Workforce Development @ One ...
|
Manager, Machine Learning - Workforce Development @ One Model
|
https://jobs.techstars.com
|
[] |
See open jobs similar to "Manager, Machine Learning - Workforce Development" Techstars. Software Engineering. Atlanta, GA, USA. USD 176k-264k / year + Equity.
|
Your work days are brighter here.
At Workday, it all began with a conversation over breakfast. When our founders met at a sunny California diner, they came up with an idea to revolutionize the enterprise software market. And when we began to rise, one thing that really set us apart was our culture. A culture which was driven by our value of putting our people first. And ever since, the happiness, development, and contribution of every Workmate is central to who we are. Our Workmates believe a healthy employee-centric, collaborative culture is the essential mix of ingredients for success in business. That’s why we look after our people, communities and the planet while still being profitable. Feel encouraged to shine, however that manifests: you don’t need to hide who you are. You can feel the energy and the passion, it's what makes us unique. Inspired to make a brighter work day for all and transform with us to the next stage of our growth journey? Bring your brightest version of you and have a brighter work day here.
At Workday, we value our candidates’ privacy and data security. Workday will never ask candidates to apply to jobs through websites that are not Workday Careers.
Please be aware of sites that may ask for you to input your data in connection with a job posting that appears to be from Workday but is not.
In addition, Workday will never ask candidates to pay a recruiting fee, or pay for consulting or coaching services, in order to apply for a job at Workday.
About the Team
It's fun to work in a company where people truly believe in what they're doing. At Workday, we're committed to bringing passion and customer focus to the business of enterprise applications. We work hard, and we're serious about what we do. But we like to have a good time, too. In fact, we run our company with that principle in mind every day: One of our core values is fun.Join the Workforce ML team whose mission is to 'Enable the Future of Work with AI and ML.' We believe in loving what you do, and you'll direct a team of exceptional Data Scientists and ML Engineers to prove it. You'll drive the creation of next-generation smart applications impacting over 60 million users and supporting around 450 billion transactions each year. Your team tackles intricate business and user interaction problems through pioneering ML and agentic technologies, all within a highly autonomous and ownership-driven environment reminiscent of a startup
About the Role
We're looking for a technical, hands-on leader to drive software design, ML and AI methodology, and production code contributions. A successful candidate will lead multiple priorities with bold deadlines, be passionate about building high-quality enterprise applications, and be innovative in their approaches to technical delivery, process and operations, and relationship-building.
You are a leader, a coach, and a mentor - you will lead with heart and empathy, inspire your teams, galvanize in times of pressure, and equip teams and team members for success. You are a business leader with a growth mindset - you will use your technical expertise to challenge the status quo, find opportunities for positive change, and work with your partners to ensure sustainable business success for Workday. You will promote a diverse and inclusive environment where employees are happy, energized and engaged, and who are excited to come to work every day.
Responsibilities:
Lead the day-to-day agile activities of the team..
Attract, hire and maintain a team of skilled engineers..
Deliver Excellence: Ensure timely project delivery of high-quality AI solutions that exceed customer expectations.
Pioneer AI Technologies: Evaluate and integrate cutting-edge AI technologies, including LLMs, RAG, and orchestration frameworks like LangGraph.
Partner and collaborate with multi-functional stakeholders to prioritize, plan and deliver first-rate experiences for Workday customers
Understand and promote industry-standard methodologies
Coach and mentor team members to help them to be at their best, assisting with career growth and personal development
Personify and promote the Workday values of Employees, Customer Service, Innovation, Integrity, Fun, and Profitability
About You
Basic Qualifications:
3 or more years of proven Engineering Leadership
3 or more years of experience facilitating and leading Machine Learning development lifecycle from conception to delivery
Bachelor’s Degree Computer Science or equivalent work experience
3 or more years of experience with Machine Learning frameworks and algorithms
5+ years of experience developing applications using Cloud-based technologies
Other Qualifications:
You see software development as a team sport and thrive in a highly collaborative and agile culture where you’re always guiding and learning
You have a strong focus on delivering high-quality software products, continuous innovation, and you value test automation and performance engineering
You are proactive and able to deliver on initiatives that you start
You demonstrate the interpersonal skills needed to positively influence important issues or decisions in a multi-functional environment
You have the ability to communicate technical complexity in simple terms to both technical and nontechnical audiences
Experience supporting team members career growth and development
You put people first and ensure a psychologically safe environment for team members
Workday Pay Transparency Statement
The annualized base salary ranges for the primary location and any additional locations are listed below. Workday pay ranges vary based on work location. As a part of the total compensation package, this role may be eligible for the Workday Bonus Plan or a role-specific commission/bonus, as well as annual refresh stock grants. Recruiters can share more detail during the hiring process. Each candidate’s compensation offer will be based on multiple factors including, but not limited to, geography, experience, skills, job duties, and business need, among other things. For more information regarding Workday’s comprehensive benefits, please click here.
Primary Location: USA.GA.Atlanta
Primary Location Base Pay Range: $176,000 USD - $264,000 USD
Additional US Location(s) Base Pay Range: $167,200 USD - $297,600 USD
Our Approach to Flexible Work
With Flex Work, we’re combining the best of both worlds: in-person time and remote. Our approach enables our teams to deepen connections, maintain a strong community, and do their best work. We know that flexibility can take shape in many ways, so rather than a number of required days in-office each week, we simply spend at least half (50%) of our time each quarter in the office or in the field with our customers, prospects, and partners (depending on role). This means you'll have the freedom to create a flexible schedule that caters to your business, team, and personal needs, while being intentional to make the most of time spent together. Those in our remote "home office" roles also have the opportunity to come together in our offices for important moments that matter.
Pursuant to applicable Fair Chance law, Workday will consider for employment qualified applicants with arrest and conviction records.
Workday is an Equal Opportunity Employer including individuals with disabilities and protected veterans.
Are you being referred to one of our roles? If so, ask your connection at Workday about our Employee Referral process!
| 2023-01-01T00:00:00 |
https://jobs.techstars.com/companies/one-model/jobs/48764516-manager-machine-learning-workforce-development
|
[
{
"date": "2023/01/01",
"position": 97,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 95,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 100,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 95,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 96,
"query": "machine learning workforce"
},
{
"date": "2025/04/11",
"position": 96,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 100,
"query": "machine learning workforce"
}
] |
|
What Can Machine Learning Do? Workforce Implications - getAbstract
|
What Can Machine Learning Do? Workforce Implications Resumen gratuito
|
https://www.getabstract.com
|
[
"Erik Brynjolfsson",
"Tom Mitchell",
"Martin Neil Baily Et Al.",
"Andrew Mcafee",
"Peter Stone Et Al.",
"Clive Thompson",
"Emily Anthes",
"Philipp Gerbert",
"Thomas H. Davenport",
"Mark Walport"
] |
Access a free summary of What Can Machine Learning Do? Workforce Implications, by Erik Brynjolfsson and Tom Mitchell and 27000 other business, ...
|
El rating: su significado
En getAbstract resumimos libros* que le ayuden a la gente a entender el mundo y hacerlo un mejor lugar. Lo que escogemos para nuestra biblioteca tiene que sobresalir en una o ambas de las siguientes características:
Revelador – Usted aprenderá cosas que lo informarán para tomar mejores decisiones.
Útil – Usted obtendrá consejos prácticos que lo ayudarán a ser mejor en lo que hace.
Clasificamos todo el contenido en una escala del 1 al 10 en cuanto a estas cualidades principales. Nuestra clasificación le ayuda a organizar su lista de lecturas en sólidas (5) hasta brillantes (10). Los libros con una clasificación menor a 5 no son resumidos. A continuación, explicamos nuestro sistema de clasificación:
10 – Brillante. Un libro útil o revelador que, además de cumplir con los más altos estándares en todos los aspectos pertinentes, se destaca incluso de los mejores. A menudo se trata de un clásico instantáneo y lectura obligada para todo el mundo.
9 – Magnífico. Un libro útil o revelador bien construido, con muchas fortalezas y sin defectos dignos de mención.
8 – Muy bueno. Un libro útil o revelador que incluye una cantidad importante de cualidades destacables aunque no sea excelente en su totalidad, por ejemplo, un libro que presenta los hallazgos más recientes en un área específica, de la autoría de un experto de renombre, pero que falla un poco en estilo.
7 – Bueno. Un libro útil o revelador que combina dos o más fortalezas destacables, por ejemplo, un libro que contiene ideas novedosas poco comunes y las presenta de manera interesante.
6 – Destacable. Un libro útil o revelador que se destaca en por lo menos un aspecto, como puede ser que esté particularmente bien estructurado.
5 – Sólido. Un libro útil o revelador a pesar de sus flaquezas obvias. Por ejemplo, puede ofrecer consejos aceptables en algunas áreas pero que sea repetitivo o poco relevante en otras.
| 2023-01-01T00:00:00 |
https://www.getabstract.com/es/resumen/what-can-machine-learning-do-workforce-implications/32735
|
[
{
"date": "2023/01/01",
"position": 98,
"query": "machine learning workforce"
},
{
"date": "2023/02/01",
"position": 97,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 98,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 97,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 98,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 98,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 98,
"query": "machine learning workforce"
}
] |
|
What are AI-Powered Workforce Management Tools? - NiCE
|
What are AI-Powered Workforce Management Tools?
|
https://www.nice.com
|
[] |
AI-powered WFM tools use AI, machine learning, and predictive analytics to optimize contact center staffing with precision and agility.
|
Make the smartest buying decision with the latest Gartner analysis
NiCE has been named a Gartner® Magic Quadrant™ Leader for Contact Center as a Service for the 10th consecutive year and is positioned furthest on Completeness of Vision.
Get report
| 2023-01-01T00:00:00 |
https://www.nice.com/info/what-are-ai-powered-workforce-management-tools
|
[
{
"date": "2023/01/01",
"position": 100,
"query": "machine learning workforce"
},
{
"date": "2023/08/01",
"position": 94,
"query": "machine learning workforce"
},
{
"date": "2024/04/01",
"position": 100,
"query": "machine learning workforce"
},
{
"date": "2024/06/01",
"position": 92,
"query": "machine learning workforce"
},
{
"date": "2024/10/01",
"position": 97,
"query": "machine learning workforce"
},
{
"date": "2024/12/01",
"position": 100,
"query": "machine learning workforce"
},
{
"date": "2025/01/01",
"position": 94,
"query": "machine learning workforce"
}
] |
|
If AI replaces nearly all labour-based jobs, won't the people ...
|
The heart of the internet
|
https://www.reddit.com
|
[] |
Once AI replaces nearly all labour-based jobs (which according to many people is inevitable), these billionaires will have no use for their human workers.
|
Western society is ruled by big corporations and billionaires, there's no doubt about that right? Once AI replaces nearly all labour-based jobs (which according to many people is inevitable), these billionaires will have no "use" for their human workers. What is this movement's solution to this? In the eyes of these big corporations who hold nearly all the power, the common man will become obselete, and most of humanity will then have no possible way to exist in modern day society. I am not neccasarily against this movement, I just want to know if there's a solution as it seems to be a fundamental flaw
| 2023-01-01T00:00:00 |
https://www.reddit.com/r/singularity/comments/105ouj6/if_ai_replaces_nearly_all_labourbased_jobs_wont/
|
[
{
"date": "2023/01/01",
"position": 4,
"query": "AI labor union"
}
] |
|
Investigating accountability for Artificial Intelligence through ...
|
Investigating accountability for Artificial Intelligence through risk governance: A workshop-based exploratory study
|
https://pmc.ncbi.nlm.nih.gov
|
[
"Ellen Hohma",
"School Of Social Sciences",
"Technology",
"Institute For Ethics In Ai",
"Technical University Of Munich",
"Munich",
"Auxane Boch",
"Rainer Trauth",
"School Of Engineering",
"Design"
] |
by E Hohma · 2023 · Cited by 44 — The European Union's proposed AI Act (Regulation, 2021/0106) provides guidance for obligations regarding the assessment and management of risks prior ...
|
Abstract Introduction With the growing prevalence of AI-based systems and the development of specific regulations and standardizations in response, accountability for consequences resulting from the development or use of these technologies becomes increasingly important. However, concrete strategies and approaches of solving related challenges seem to not have been suitably developed for or communicated with AI practitioners. Methods Studying how risk governance methods can be (re)used to administer AI accountability, we aim at contributing to closing this gap. We chose an exploratory workshop-based methodology to investigate current challenges for accountability and risk management approaches raised by AI practitioners from academia and industry. Results and Discussion Our interactive study design revealed various insights on which aspects do or do not work for handling risks of AI in practice. From the gathered perspectives, we derived 5 required characteristics for AI risk management methodologies (balance, extendability, representation, transparency and long-term orientation) and determined demands for clarification and action (e.g., for the definition of risk and accountabilities or standardization of risk governance and management) in the effort to move AI accountability from a conceptual stage to industry practice. Keywords: accountability, Artificial Intelligence, organizational framework, risk governance, workshop
1. Introduction The influence of Artificial Intelligence (AI) in our society is growing. Businesses are increasingly considering the use of AI models, as they offer new application possibilities. Therefore, simple approaches are being replaced by complex systems that can complement, or even surpass, human capabilities. This leads to a shift of company processes through AI systems that act independently and autonomously. However, these increases in both capability and complexity raise new questions as to how the predictions, decisions or actions of AI-based applications must be administered. Questions on who is to be held responsible for an AI system’s outcomes, thus, who is accountable for it, are frequently discussed. Particularly, as there are specific ambiguities and difficulties when attempting to hold someone accountable for an AI-based system’s results. Several responsibility gaps have been articulated for AI (Santoni de Sio and Mecacci, 2021). A culpability gap arises from the human desire to know the cause of an occurred harm and, especially if the cause is due to fault, to justify or punish it (Santoni de Sio and Mecacci, 2021). But there are limits to justification and punishment if the decision-maker is an automated system instead of a human-being. Further, the inability of ‘asking why’ that arises with certain AI systems creates a moral accountability gap, meaning that a system provider or operator can no longer be held morally responsible if they are unable to predict the behavior of a machine (Matthias, 2004; Santoni de Sio and Mecacci, 2021). This leads to the topic of accountability in AI still being highly contested and its way into practice unresolved. Attempts are being made to deal with the problems of accountability through AI governance strategies (Raji et al., 2020). Particularly, since asking who to hold accountable primarily requires asking who to hold accountable for the harms caused by a system that works correctly or incorrectly (Wieringa, 2020), strategies regarding governing AI-related risks are broadly targeted. One example of risk-based governance is the recently proposed EU AI Act (Regulation, 2021/0106). It suggests a categorization of AI systems into risk levels based on their application field and foundation and imposes additional precautions to limit or adequately manage related risks. Similar concepts have been taken up and efforts made to further transfer them into practice. A large part of this contribution can be found among Standard Developing Organizations. The US National Institute of Standards and Technology (NIST) (2022, p. 1), for example, works on an AI Risk Management Framework, aiming at providing “a flexible, structured, and measurable process to address AI risks throughout the AI lifecycle”. In their Road Map Report on Artificial Intelligence, the CEN-CENELEC sets accountability among their priority standardization activities that are deemed “important to conduct soon” (CEN-CENELEC, 2020, p. 8). Risk management strategies are particularly emphasized as an important component thereof (CEN-CENELEC, 2020). However, it is also pointed out that risk governance for AI is not a concept that has to be rebuilt from scratch (e.g., National Institute of Standards and Technology (NIST), 2022). Approaches exist for other industries or branches and can be reconsidered or reused for AI (ISO 31000, 2020). For example, ISO 31000 generically introduces risk management processes as management tasks. IEEE/ISO/IEC 16085-2021 (2021) sets an international standard on risk management for system and software engineering along its life cycle processes. The essential elements thus seem to be understood and agreed and now need to be adapted to AI. But precisely because fundamental concepts for risk management and accountability already exist, the question arises as to why there seem to be difficulties when transferring them to AI-based technologies. The above-mentioned responsibility gaps probably play a part in this, but what exactly are the hurdles to accountability and risk management of AI in practice and why do currently proposed risk management methods seem to not be suitable for practical application? Our guiding research question in this endeavor is “How can (standard) risk management concepts be used to administer accountability in the context of AI?.” As we targeted practice-oriented research, we organized two exploratory and participatory workshops with experts and practitioners from the targeted fields, each workshop focusing on certain sub-aspects of our research aim. The purpose of Workshop 1 on “Accountability Requirements for AI Applications” was to further investigate risks and accountabilities arising from and with AI-based systems. We thus explored current challenges for AI accountability from a practitioner’s perspective and the ways in which risks are perceived in everyday work. Workshop 2 on “Risk Management and Responsibility Assessment for AI Systems” focused on AI risk governance, where we studied how existing AI risk management methods are applied in practice, what works well or not as well as which requirements for good AI risk management participants see from a practical perspective. In summary, this work has three main contributions: It gives an overview of the most pressing questions regarding accountability and risk governance issues as perceived in industry. It provides insights into practitioners’ opinions regarding risk governance and brings their opinions at the center of the risk governance for accountability considerations. It derives required characteristics for AI risk management methodologies as well as determines demands for clarification and actions to help move AI accountability from a conceptual stage to industry practice.
3. Methodology The aim of this research was to explore the use of risk governance to administer accountability for AI-based systems in practice, retrieving particularly which benefits and challenges currently arise with the application of AI risk governance. From the review of existing efforts, we see that the need for establishing accountabilities for AI-based systems has been clearly acknowledged, not only in theory. Concepts to operationalize it through risk governance, building off traditional techniques from software engineering, have been proposed. However, as we, at the same time, see difficulties of transferring and applying such approaches in practice, we argue that more evaluation of practitioners’ perspectives is required to ensure practicability of proposed concepts. We therefore address this demand with our findings of two workshops with AI practitioners on their views on accountabilities for AI-related risks as well as the currently proposed concepts to define and govern them. More precisely, the purpose of Workshop 1 was to define and investigate the risks and accountabilities that arise with them. We looked at current challenges of risk responsibility attribution from practitioners’ perspective. In the second workshop, we studied current risk management methodologies, to what extent they are employed by practitioners, where they can help and what they lack from a practical perspective. Thus, discussions were turned toward risk governance investigating their use, strengths and limitations of risk management methodologies. Figure 1 outlines the research approach and key focuses of each workshop. Figure 1. Open in a new tab Overview of key considerations within and structure of this research. Our methodology was intended to be exploratory and participatory to reveal various sets of drawbacks for accountability and risk governance for AI. The choice of the workshop methodology is based on the participatory principle outlined by Vaughn and Jacquez (2020), allowing for meaningful engagement with target stakeholders and supporting the creation of relevant, meaningful research findings translatable into action. 3.1. Workshop 1: Accountability requirements for AI applications In the first workshop, we aimed at understanding the perspectives of practitioners from industry and academia on risks and accountabilities brought upon by AI systems with the aim to understand clearly the practitioners’ perspective when facing them, i.e., how do risks arise and which, their considerations of how risks can be appropriately addressed and, finally, who should be held accountable for such. The anticipated outcome was to build a clear, sector-blind map to then be able to identify appropriate risk management methodologies and responsible parties within or outside of an organization. This was targeted in two ways, first, directly exploring the challenges for accountability through workshop discussions with the participants from different backgrounds on their views on risks and, second, more practically, by studying concrete case studies to observe more clearly the different areas of concern in their opinions. Figure 2 shows the agenda of the workshop as presented to the participants. Figure 2. Open in a new tab Agenda for the ‘Accountability Requirements for AI Applications’ workshop. 3.1.1. Participants The group for the first workshop was composed of 18 participants, including three organizers. The participants came from different backgrounds: engineering, ethics, data science, policy, law and sustainability. Eight of them worked in academia, ten came from the private sector. Participants were recruited through advertisement on professional social media platforms and personal network. 3.1.2. Procedure During Part 1, after a short introduction of the organizers and a brief presentation of the workshop’s background, fundamental definitions and motivation, the interactive workshop part started with an open, moderated discussion regarding the question ‘In your opinion, what are the most pressing challenges in the industry regarding risks of AI and accountability?’. Participants were invited to speak up or use the ‘raise your hand’-function of the online-meeting tool to join the discussion. In Part 2 of the workshop, participants were presented three case studies (see Appendix A for details) on mobility, healthcare or finance topics. The mobility case study focused on the question of adjusting driving styles for autonomous cars, the healthcare case study questioned the use of robots to support elderly populations and the finance case study debated the algorithmic assessment of individuals’ creditworthiness. The use case analysis exercise was worked on in smaller teams in breakout rooms for which participants were asked to decide themselves which room, and thus use case, to join. The exercise consisted of two sub-tasks: (1) the identification of risks related to AI and ethics within the investigated use case, and (2) the determination of potential risk management strategies and their responsible entities. A “Miro-board”1 was used to record and structure the conversations and main outcomes of the exercises with the participants, illustrated in Figure 3. The “sticky notes” represent ideas and comments that were made during the exercise and were added by the participants or the organizers’ team member who attended and moderated the respective session. Figure 3. Open in a new tab Screenshot of online collaborative “Miro-board” used for the use case analysis. 3.2. Workshop 2: Risk management and responsibility assessment for AI systems For the second workshop, our aim was to understand in more detail the practitioners’ challenges regarding risk management tools for AI systems to clarify their pain points and gaps. Understanding with the first workshop their approach to accountability for risks, we now aimed at investigating the reason why the risks did not seem to be easy to mitigate with the available frameworks. Additionally, a major point of interest flagged early on in our research was the lack of clarity on who is accountable for what, which is why a second aspect of our workshop was to focus on responsibility attribution within and outside of the organization for each step of the risk management strategy implementation. Participants were thus first asked direct questions regarding current tools and their appreciation of those. Second, a prototype risk management process was developed in smaller groups to step by step investigate, for a chosen holistic AI-related risk, the required countermeasures as well as accountable stakeholders. Figure 4 shows the agenda of the workshop as presented to the participants. Figure 4. Open in a new tab Agenda for the ‘Risk Management and Responsibility Assessment for AI Systems’ workshop. 3.2.1. Participants For this workshop, 19 participants were present, including three organizers. Except for the organizers, all participants worked in the industry. Their background covered the fields of law, AI ethics, sustainability and technical sciences. Some participants took part in both workshops, while others participated in only this one. The participation in both workshops was not required. Participants were recruited through advertisement on specific social media platforms, contact of first workshop participants and personal network. 3.2.2. Procedure Participants were first introduced to the risk-based AI accountability approach. They were presented important regulations and policy papers published by the European Union, indicating which objectives and core values should be maintained and reached in AI applications, namely the High-Level Expert Group on Artificial Intelligence (AI HLEG) (2019) documentation on trustworthy AI and the AI Act (Regulation, 2021/0106). During Part 1, participants were asked through ‘mentimeter’2, an interactive polls and word clouds tool, about their perception of AI-related risks in their daily practice as well as whether they use risk management tools or methodology to cope with those. Afterwards, participants were asked to give feedback in the form of multiple word clouds on their perceived limitations and benefits of existing risk management methodologies as well as challenges they face in managing risks today and what they would require in a good risk management tool, which were discussed afterwards. Part 2 of the workshop dealt with the active prototyping of a risk management tool and took place in groups. Participants were introduced a risk management canvas as presented in Figure 5. The canvas was built off a common prototyping scheme as used in design practices3 and adapted to the workshop exercise. In break-out rooms, participants were asked to choose a risk that would be holistic to multiple AI-using sectors and to map the steps needed to manage the chosen risk within an institution. For each step, required activities as well as responsibility distribution they envisioned within and outside of the fictive organization were determined. Two scenarios were discussed by each group, a first one for proposing a proactive risk management methodology, in other words, the planned risk management activities to avoid or prevent harm from a risk in the first place (Clarke, 2019) and a second one building a reactive risk management methodology for the same risk, in other words, risk management activities to respond to or mitigate damages when a risk has created harm (Clarke, 2019). Figure 5. Open in a new tab Outline for the AI risk management prototyping canvas. 3.3. Analysis The findings were synthesized by going through the materials collected and notes from the discussions for both workshops. Additionally, for the first workshop, the Miro-Board content and, for the second workshop, the canvases content were integrated in the analysis. The authors discussed and structured the relevant outcomes. The main outcomes were identified through a ‘frequency of topics’ analysis and the review of arguments and details given by participants on their opinions during the discussions and exercises. The more the topics were mentioned by the participants, thus the more it was discussed, the more they were considered urgent and relevant. All topics mentioned, even if just once, were considered in the final outcomes. The proposed approach is similar to other articles building on workshop methodology in the area of ethics and technology (e.g., Danaher et al., 2017; Fosch-Villaronga et al., 2020).
4. Results and analysis This section presents the results for the two workshop studies carried out. Filled material as well as discussion summaries will be presented and analyzed for each workshop to conclude findings resulting from the considerations. Their implications for theory and practice are compiled in the subsequent discussion section. 4.1. Workshop 1 In Workshop 1, risks perceived by participants in different scenarios and responsible entities for their mitigation were investigated. The main aim was to identify which risks are seen by practitioners in certain use cases as well as which patterns can be derived from this in order to retrieve further risks. Additionally, strategies for managing these risks were examined regarding options for specification and standardization as well as potential accountability determination mechanisms observed. 4.1.1. Part 1: Workshop discussion A summary of terms mentioned during the workshop discussion on pressing challenges regarding AI and accountability can be found in Table 1. Be reminded that the workshop was not technically recorded but notes were taken during the discussions to capture the participants’ opinions. Therefore, explanations presented in the second column of Table 1 are not direct quotes from the discussion but were paraphrased by the authors to explain the key points mentioned during the workshop. Table 1. Summary of points mentioned by participants during the discussion on pressing challenges regarding AI and accountability. Acceptance and Trust Deployment and technology acceptance are two different things. Trust is key in acceptance; thus, we need to demonstrate trust. Data Bias AI systems must not be biased against certain groups in society. Non-discrimination and data quality needs to be ensured during development and deployment. Education Education is key. People need to be educated on the risks and safety of AI, data scientists and developers need to be educated on the ethical challenges of AI, and regulators need to be educated on current technological developments. Explainability There is a gap between what can be explained and what needs to be explained. Additionally, it needs to be ensured that people can understand what the system explains. Implications Accountability needs to be understood in terms of how but also which systems to design. Only because we can do something does not mean we should do it. Privacy How can high data privacy standards be fulfilled in AI systems? Regulation Detailed legal acts and legal cases are required. Safety and risk Technology can never be 100% safe. The question is, how much risk is bearable, what is safe enough and how can we determine suitable thresholds. Open in a new tab Evaluating and structuring the key arguments mentioned during the workshop discussion reveals that pressing challenges for AI accountability were mostly seen among two categories: (1) challenges w.r.t. the system design (data bias, explainability, privacy, safety, and risk) and (2) challenges w.r.t. the use of the system (acceptance and trust, education, implications, and regulation). Both dimensions thus seem to be important in determining accountability and should be considered independently (e.g., examine how biased data can affect responsibilities for the system’s outputs) as well as in relation to each other (e.g., how decisions regarding the system design influence accountabilities for the system’s use). 4.1.2. Part 2: Use case exercise In sub-task 1, the determination of risks related to AI and ethics, participants identified multiple, diverse risks within the different use cases. Appendix B shows the full results, presenting the identified risks as well as a short description w.r.t. the specific use case. During the exercise we observed that participants predominantly focused on societal or end-user-related risks as well risks for organizations. Risks linked to the AI system itself, such as design-related decisions or the system’s accuracy, robustness and security, were less mentioned in the discussions. One reason for this could be a bias in the participants’ answers. Although great care was taken in the selection of participants to ensure a diversity of backgrounds (see Section 3.1.1), their previous experiences or the workshop context, which had an AI-ethics connection, may have led participants to adopt a more user-centered perspective in their risk considerations. Thus, our results do not imply that risks linked to the technology are less important but rather reconfirm the prevalence of perceived societal risks of AI systems. Based on the participants’ findings and our analysis, we propose to map AI-related risks along the two actors that are mainly impacted: the society (incl. End-users, other individuals and the general public) and organizations (incl. The AI provider, component producers and third-party organizations). Figure 6 demonstrates the resulting scheme for the risks identified by our participants during the workshop. Figure 6. Open in a new tab Risks identified by the participants during the workshop structured according to the actor they impact. Appendix C gives an overview of results from the second sub-task of the use case analysis exercise, the definition of potential risk management approaches and the assignment of responsible actors for them. Due to time constraints, not all risks determined in sub-task 1 were discussed. Instead, certain risks were selected by the participants as examples. Analyzing the participants’ suggestions revealed a great variety of potential risk management measures. Figure 7 displays the investigated risks along with their respective potential risk management approaches that certain actors can take which have been discussed during the workshop. It demonstrates the great variety of risk management methodologies that participants have found during the exercise, ranging from technical methods, such as extensive testing or fairness-enhancing techniques, to non-technical measures, like inclusive debates with affected parties, detailed and understandable explanations or use manuals and promotion of team diversity. While most responsibilities were seen with the AI-system provider and regulators or general public, other stakeholders, like the user or data subjects, were found to be able to take action and aim at preventing or mitigating risks. In particular regarding data, participants proposed and wished for more regulative approaches to promote clarity and standardization. While the concrete design of certain methodologies was found to depend on the specific use case and context, an overall tendency, or at least the fact that certain measures are required, can be determined from a broader perspective, which is further reflected in Figure 7. Figure 7. Open in a new tab Summary of risk management approaches discussed during the use case analysis exercise for selected identified risks. The second point of interest in our analysis was how participants distributed responsibilities among the different actors involved. The participants’ answers revealed that they saw responsibilities for both, internal actors (i.e., the AI-system providing organization and its employees) as well as external stakeholders (e.g., regulators, the broader society or other third parties). Figure 8 provides an overview of which parties were pointed out by the participants during the use case analysis exercise. Figure 8. Open in a new tab Responsibilities determined by the participants in the use case analysis exercise structured along the responsible actor. As indicated before, AI-system providers were seen responsible for nearly all the investigated risks. Even though nearly all workshop participants had a practice-oriented background, it was not discussed further who within the company should be held responsible. Therefore, a precise responsibility-sharing scheme still needs to be detailed, which was one of our endeavors for Workshop 2. Regulators were mentioned second most often. While this reemphasizes the demand for more clarity regarding risk response approaches, it likewise indicates that there is still a gap of standardized, unified and at the same time sufficiently acknowledged frameworks for AI accountability. Finally, other actors were pointed out to bear some responsibility, among them third-party contributors and the broader society. Especially responsibilities for the user, data subjects or general public were frequently discussed during the exercise. In summary these results thus indicate that the large network of stakeholders involved in AI development and use requires sharing responsibilities for risks fairly across various actors. Currently, this division is still unclear, and a uniform and standardized set of rules is desirable to offer more acknowledged guidance. 4.2. Workshop 2 The aim of Workshop 2 was to reveal insights on the daily practice of dealing with AI risks and risk management methodologies. The main interest was to investigate if and how participants perceived the risks of AI in their everyday work as well as how they cope with them. Ultimately this should lead to deriving requirements for good, useful and practical risk management approaches and the clarification of which challenges exist in their implementation. 4.2.1. Part 1: Survey and discussion The survey results obtained through online polls with the participants in the beginning of the workshop unveiled quantitative and qualitative insights on the participants’ perception of AI risks as well as practical application of risk management methodologies. They were followed by a mid-way and final discussion to receive more explanatory inputs from participants regarding their answers of the online poll. A summary report of the discussions regarding the participants’ opinions on AI risks and their perception during daily practice as well as requirements for good AI risk management can be found in Appendix D. The two quantitative questions revealed that 13 out of 16 participants indicated to perceive the risks of AI in their everyday work (1 participant indicated ‘No’, 2 did not vote). To cope with these risks, 2 out of 16 participants reported using methodologies or technical tools (11 participants indicated ‘No’, 3 did not vote). Further information on how to practically cope with risks linked to AI applications was found through qualitative questions. The word clouds to the four qualitative questions asked during the survey-part are displayed in Figure 9. Figure 9. Open in a new tab Word clouds of answers from participants to the four qualitative questions. (A) What do you think is working with current risk management tools and methodologies? (B) What do you think is not working with current risk management tools and methodologies? (C) Which problems/challenges do you come across (in your everyday work) in coping with these risks? (D) What do you require for a good AI risk management tool? The participants’ quantitative responses show that there seems to be a need to manage risks linked to AI, however, current approaches are not considered suitable or satisfying enough to be applied in practice. More concretely, certain aspects about risk management tools and methodologies have been pointed out as positive or ‘working well’ (Question A). GDPR explicitly has been highlighted as an effective tool (Regulation, 2016). Along with other mentioned terms, such as ‘detailed’, ‘oversight’ or ‘AI Act’, this emphasizes the participants’ demand for more standardized and recognized guidelines which seem to be considered powerful tools. Further, ‘awareness’ on the topic was mentioned as an important factor in the success of risk management. Presumably this accounts for both, awareness on risk management techniques, in addition to risks themselves, as sectors that are commonly considered riskier, like AI in autonomous driving or medicine, were particularly pointed out as being more effective w.r.t. risk management. Additionally, some available technical methods, such as tools for ‘fairness’ or ‘bias recognition’, were regarded useful. Despite these positive aspects, several downsides have been mentioned regarding current risk management tools and methodologies (Question B). The most important issue seems to be a clear lack of accountability definition and distribution. Furthermore, the evaluation regarding the risks’ impact on humans does not seem sufficient in the current approaches, as they were considered to lack ‘multi-stakeholders’ feedback’, ‘public opinions’, ‘inclusiveness’, and ‘human factors’. Additionally, the lack of clarity (‘unclear’, ‘transparency’, and ‘explainability’) and the handling of unforeseen events (‘unknown unknowns’, ‘predictability’, and ‘uncontrollable events’) were criticized. Regarding coping with risks in practice, participants were asked for challenges they perceive in their everyday work (Question C) as well as how these challenges could be resolved with risk management tools, thus, what they would require for a good AI risk management tool (Question D). Three main challenges were mentioned by participants regarding practical handling of AI risks. Most importantly, they reported uncertainties regarding how to cope with perceived risks and responsibilities for it (‘uncertainty’, ‘no remediation plan’, ‘effective mitigation’, ‘task distribution’, ‘no process to follow’, ‘risk identification’, and ‘accountability’). During the discussion, this view was detailed, stating that risks are multidimensional and interrelated. Bias regarding how to approach risks, for example, due to a lack of team diversity, can further negatively affect the response processes. Second, a lack of awareness for risk coping approaches was mentioned as challenge (‘awareness’, ‘no expertise’, ‘limited understanding’, and ‘misunderstood’) and supplemented in the discussion with a misjudgment regarding urgency of many companies as well as a lack of sufficient resources to develop their own strategies and concepts, especially for smaller companies. Finally, a third key challenge mentioned relates to the black box nature of many AI systems. Intransparency of systems can particularly cause difficulties in managing risks, as sometimes risks are not identified correctly due to unintended consequences, and even if risks are properly determined, lack of understanding can lead to an inability to address risks appropriately (‘black box nature’, ‘black box of AI’, and ‘lack of XAI’). Evaluating such challenges have led participants to specify certain requirements needed for good AI risk management. Specifically, a need for being understandable by all, experts and non-expert users, was determined (‘explainability’, ‘non-expert and expert’, ‘transparency’, ‘easy for all to use’, and ‘clarity’). Human involvement was further considered one key characteristic of such methods (‘human involvement’, ‘accountability’). A clear definition of risks with, for example, support from scenarios and use cases presenting mitigation ideas and failsafes in case of issues seems required to enable determining risk management processes as well evaluating trade-offs. Finally, tools should be adaptable and extendable, allowing for good coverage, stakeholder preferences and a long-term perspective. Particularly these characteristics were further detailed in the subsequent discussion. A call for clarity in coverage, i.e., which risks are employed by certain tools and how to treat the ‘unknown unknowns’ and standardization, i.e., resolve the currently scattered and incomplete nature of risk management tools, was expressed. Further the challenge of specification vs. generalization was discussed intensively and the unfavourability of a ‘one size fits all’ solution. Resolutions were proposed regarding balancing usefulness and detail with an extendable method, offering a generic model to avoid common mistakes and context-aware add-ons to be enacted for addressing specific issues being determined as most promising. 4.2.2. Part 2: Prototyping exercise During the interactive prototyping exercise, participants were divided into two subgroups and invited to brainstorm on the development of two risk management processes (reactive and proactive) for two different AI-related risks (fairness and unanticipated human impact). As an example, Figure 10 illustrates one resulting prototyping canvas which participants used during the exercise for structuring and noting down their ideas. Figure 10. Open in a new tab One of the prototyping canvases created during the workshop to exemplify the ideation process toward a reactive risk management technique. More specifically, Group 1 focused on fairness of AI-systems in different sector scenarios (health, education and emerging technologies) with the intention to mitigate discrimination caused by a lack of fairness for specific groups. For this, the target of the risk management process was determined as improved equity, inclusion and an increased consideration of the exact demographic of the target population in the system development. Group 2 aimed at managing unanticipated human impacts referring to unintended or undeliberate system use having negative effects on, e.g., human rights or economical aspects for individuals or other organizations. Consequences of unexpected impacts on humans were determined as discrimination, physical/mental harm or security and safety issues. Therefore, the targeted risk management aim was broadly defined as prevention of harm. Developing the risk management processes, parallels can be found for both investigated scenarios as well as both examined management strategies. Essentially all sketched risk management processes followed four steps. First, a problem analysis is required involving a general problem definition, identification and assessment as well as conceptualization of processes and targets. Second, a reaction is planned, including strategies regarding problem improvement, harm reduction or implementation preparation, followed by the reaction execution referring to the actual evaluation and analysis of data or anticipated response implementation. The process ends with outcome testing, involving user tests and feedback loops. Application of these four steps slightly varied with the application to the use cases, however, a clear pattern was discernible. A final aim of the prototyping exercise was the definition of responsible stakeholders for each step of the sketched risk management process. Actors were asked to be determined within (internal) as well as outside (external) of the process implementing organization. Figure 11 provides an overview of all responsible parties mentioned among both subgroups in the exercise. Figure 11. Open in a new tab Summary of responsible actors determined for each step of the prototyped risk management process. Internal responsibilities were mainly determined among the management, business operation and development. Responsible external actors were found in the public as well as private sector. Interestingly, in the two proactive approaches responsibilities for management were more found in the first and second step of the risk management process, dealing with the definition of goals and strategies, while the third and fourth step were predominantly seen as responsibility of development teams, implementation and testing of planned responses. This was perceived different with reactive approaches where responsibilities were shared across all teams throughout the whole risk management process, although the fundamental structure of steps was chosen similarly. Such peculiarities were not found for external actors, instead a need for action or monitoring was found at each step. In summary, discussions during the prototyping exercise and shared participant opinions revealed valuable insights into practice-oriented risk management approaches. Established risk management ideas seem to be transferable to AI-related issues as well as suited for determining key risk management steps and responsibilities. A structured 4-step process was derived with responsibilities for internal and external stakeholders determined at each step.
5. Discussion The two conducted workshops revealed various insightful conclusions from practitioners regarding how to connect standard risk management concepts to AI accountability. First, defining AI accountability comes with major challenges due to the way systems are designed and how they are used. When using risks as a heuristic to determine ‘what to be accountable for’, risks linked to AI systems can create implications along multiple dimensions mainly structured along implications for society and implications for organizations. Considering the use of risk management methodologies for administering AI accountability, there is a great variety in approaches and all affected actors can take action to prevent, manage and mitigate risks. Generally, established risk management ideas seem to be transferable to AI-related issues as well as suited for determining key risk management steps and responsibilities. However, although some techniques already work well, overall, recent AI risk management methodologies and tools are not suited for practical application due to their many downsides presented and therefore are hardly used in practitioners’ everyday work. Further, the concrete design of certain measures needs to be determined w.r.t. the use case and context, however, their general need, as well as broader implementation decisions can be determined generically. Finally, the large network of stakeholders involved in AI development and use requires sharing responsibilities for risks fairly across many actors. Currently, this division is still unclear, and a uniform and standardized set of rules is desirable to offer a more acknowledged guidance that is useful in practice. 5.1. Implications for theory Our results reveal opinions from practitioners on how a connection between accountability and risk governance should be established and their evaluation regarding usability of currently proposed AI risk governance methods. These insights can be helpful for the development of new accountability frameworks, particularly those based on risk governance. Further, our findings can help overcome deficiencies of existing frameworks and guide their practical adaptation. In the following we therefore want to summarize how links between accountability and risk governance are currently seen in practice and which challenges arise with the practical use of current AI risk management tools. Finally, characteristics, content and methods for good AI risk governance are concluded to help adapt approaches to practitioners’ needs. In the workshop discussions, the link between accountability and risk governance for AI has been identified within system design and system use of AI applications. Especially for challenges w.r.t. accountability for a system’s design, risk governance approaches seem to be a good response. In the prototyping exercise of Workshop 2, for example, accounting for data bias, or more generally fairness issues, has been investigated and a mock-up risk governance methodology to prevent related problems has been proposed (see also results for ‘unanticipated human impact’ in Figure 10). Proactive risk management strategies, like prevention, were found to be a suitable measure, a conclusion that seems further supported by the many efforts that have already been put up in this field by research or practice to advance their application, like XAI methods or data bias detection tools (Gunning and Aha, 2019). Based on such disaggregated, step-by-step considerations of risk management measures, responsibilities can be clarified. Implementation of prevention-measures for system design, however, benefits from the fact that system development, despite influenced by external factors, mainly lies in the area of competence of the AI-system provider. This might be more challenging when it comes to system use, as AI-system providers not necessarily have full power over how a user operates the system and its outputs. Nevertheless, risk governance approaches still seem promising. For example, considering the issue of missing education regarding AI use and its risks mentioned during the workshop discussion, use manuals or impact assessment summaries might be a reasonable solution. The link between accountability and risk governance becomes evident when revisiting our results from the use case exercise in Workshop 1, particularly those outlined in Figure 7, as accountabilities need to be considered not only for AI-related risks, but also for the management of those. When aiming to clarify accountabilities for AI, good risk governance approaches are thus inevitable. The question is therefore which disadvantages hinder their comprehensive application and how can they be overcome. Summarizing the results from both workshops reveals challenges and drawbacks that our participants saw with current AI risk governance. First and foremost, the issue of defining accountabilities also impacts the creation and adoption of risk management measures, as unclarity regarding responsibility for a risk naturally leads to unclarity about responsibility for its mitigation. Second, the issue of transparency was mentioned in the context of two challenges. The black-box nature of AI systems was seen problematic to determine response mechanisms and the lack of understandability of risk governance measures in return hinders their effectiveness. Awareness for AI risks and management measures as well as the potential non-expertise of their operators can create issues. In addition, vagueness and unclear processes of risk governance approaches exacerbate such drawbacks. Finally, unanticipated consequences and unforeseen events have been mentioned as particularly hard to manage. Especially, if they entail negative impacts for humans, such risks should particularly be targeted. Based on these identified drawbacks mentioned by practitioners during the workshops, we derive five key requirements that AI risk governance approaches should meet to be practically useful. Balance. One major issue mentioned was the lack of clearly defined processes that are highly adapted to the organization’s specific context and needs and thus would be easily implementable. However, at the same time the inability of many currently proposed AI risk management frameworks to be applicable in various scenarios and therefore the resulting unclarity about standardized and uniform procedures was pointed out as a particular downside. This argument is in line with findings from literature, as currently available frameworks in the EU context do not cover AI from a holistic perspective and cannot provide a sector blind understanding of arising risks [see, e.g., U.S. Government Accountability Office (GAO), 2021; Europol Innovation Lab and CENTRIC, 2022]. A key duty when designing risk management measures is thus finding a good balance between specialization and generalization. One suggestion for solving this quest is to develop a holistic fundament following standardized rules and, in addition, allowing for add-ons or extension to ensure adaptability per sector.
Extendability. The second key requirement links to the dynamic nature of risks and the environment they need to be operated in. Risks or approaches to solve them can evolve over time, new risks can be revealed or arise in combination with newly developed technologies or regulations that need to be adhered to can emerge. Therefore, risk management recommendations should not be rigid, instead, they should be easily extendable and adaptable to new, perhaps even unforeseen aspects to stay practically useful also over time. This would also allow for a better identification and interpretation of the unknown knowns and unknown unknowns as presented by Bralver and Borge (2010).
Representation. Risk management approaches should be holistic and comprehensive. Often a lack of completeness has been mentioned regarding risk identification and management. Many existing tools are highly specialized and can thus not guarantee an inclusive risk governance concept (e.g., Tekathen and Dechow, 2013; Pollmann et al., 2014). Especially, when it comes to negative impacts on humans, many risk management approaches do not seem to consider them appropriately. Input and feedback from different stakeholders, e.g., field experts or the global population, could promote the representativeness of risk governance approaches regarding various risks.
Transparency. Transparency has been identified as a major condition to enable practical application of risk management approaches. The tools need to be understandable and usable by all, including expert and non-expert users. Further, transparency can help reveal responsibilities within the process and thus promote overall clarity regarding needed interventions. Therefore, developed methods should be as easily understandable as possible to foster their integration into existing structure and procedures.
Long-term orientation. Finally, missing long-term orientation has been pointed out as deficiency of many existing methodologies. Continuous monitoring and updating, however, can benefit the overall countering of risks. Thereby it should allow for identification and prevention of unexpected or unintended risks, as risks can alter over time. Besides the more generic characteristics that risk management methodologies should fulfill, certain concrete content and methods needed for effective risk management, and thus accountability definition, were demanded during the workshop. In line with the identified unclarity about accountabilities, recommendations on clear responsibility definition and distribution have been requested (see limitations in: Regulation, 2021/0106; U.S. Government Accountability Office (GAO), 2021; Europol Innovation Lab and CENTRIC, 2022; National Institute of Standards and Technology (NIST), 2022). This further emphasizes the need for precise standards that has been previously stated in literature or policy efforts (e.g., Algorithm Watch, 2021a; Circiumaru and Kind, 2022). Impact on humans (i.e., individuals, groups and society) has been mentioned to not be targeted enough, therefore a clear call for possibilities to examine and prevent human impacts has been raised. Further, communication tools for internal and external use were demanded. This could help raise awareness but also prove compliance with imposed obligations. Finally, more training opportunities, especially for unintended consequences and AI ethics in general were requested to allow for intervention regarding AI risks already early on. Our findings re-emphasize that risk management concepts are generally a good measure for administering and fostering AI accountability as well as its current challenges for practice. Nevertheless, the identified drawbacks show that many of the already developed AI risk management approaches fail to meet all required features or clarification demands to be practically useful. Therefore, there is clearly a need to adapt risk management concepts to practical demands in order to strengthen their ability and usefulness for defining AI accountability and administering it in practice. In addition, risk-based accountability frameworks should account for these requirements and demands to be practically useful. 5.2. Implications for practice Besides concrete requirements for risk management techniques, several ‘Calls for Action’ for regulators and organizations can be derived from the shortcomings of current risk governance that participants perceive in their everyday practice. Table 2 summarizes the 6 defined ‘Call for Action’-items. Table 2. Summary of “Call for Action”-items for regulators and organization derived from the workshop discussions. Provide clear definition of risks Risks arising from and with the application of AI are manifold and multidimensional. A clear and standardized definition of ‘risks’ is inevitable to allow for effective risk governance. Provide standardization regarding risk governance Currently a large variety of risk governance approaches exists. Unification and standardization are important to give guidance on which risks to address and how. Provide clear accountability frameworks A lack of clear definition of responsibilities and accountabilities for risks and their management was expressed. Generate transparent, widely understandable and practical methodologies Several downsides were seen across currently proposed risk management methods. Particularly their transparent and practical application along the full process chain was regarded challenging. Include human impact evaluations in risk management processes Evaluation regarding impacts of risks for humans was expressed to be only partially included or insufficient. Increasing the importance of human impact analyzes throughout risk assessment and management techniques has been demanded. Provide clarity about how to handle unforeseen events Due to their unpredictability unforeseen events and risks arising with them are still challenging to solve in practice. Clarity regarding responsibility and how to deal with them is required. Open in a new tab Several of these items can or should be addressed through regulations, and therefore our findings are relevant for regulators and policy makers. Particularly, demands for standardization can most effectively be solved through policy efforts. Indeed, a reaction to some of the raised needs can already be found in the AI Act proposal (Regulation, 2021/0106). For example, clarity regarding risk definition has been proposed through the categorization of AI technologies into minimal, limited, high risk and prohibited practices. The concrete list of prohibited or high-risk systems along with the AI Act’s objectives specifying protectable principles and values gives insights on which risks must be addressed. In addition, the necessity of several of the identified calls for actions can also be seen in the AI Act. For example, Art. 17(1)(m) of the AI Act specifically obliges an accountability framework “setting out the responsibilities of the management and other staff with regard to all aspects listed in this paragraph” for high-risk AI systems. However, other than that, no specific standardized requirements for such accountability frameworks are stated. Further, the need for assessing impacts on humans is a core fundamental of the AI Act. A high-level of protection of fundamental rights and Union values is clearly stated within the draft’s objectives. This is reflected in the categorization of high-risk AI systems, which may be extended, among other preconditions, with systems posing risk of adverse impact on fundamental rights [Art. 7(1)(b), Regulation, 2021/0106]. In addition, Art. 29(6), for example, redraws attention to the obligation of high-risk AI system users to carry out a data protection impact assessment that the GDPR obliges (Regulation, 2016). In summary, the AI Act clearly articulates many of the above defined Calls for Actions and can therefore cover certain facets of standardization. However, some aspects are only vaguely addressed or left open for concrete adoption. While this promotes generalizability, it raises challenges regarding specific and standardized application. The aforementioned problem of a good balance of generalization and specification is thus not completely addressed, even with the proposed AI Act. Finally, it needs to be restated that the AI Act is still under development and not put into force. Therefore, concrete verifications regarding its practicability are yet to come. Similar to challenges for regulators, a major take-away for the practical application of risk management methods in the industry seems to be a lack of transparency and clarity regarding risk governance. The need for clarification regarding the nature of risks seems to already have been heard and addressed by some organizations. Companies like BMW4 or Novartis5 have adopted principles or codes of conducts for the generation of trustworthy and responsible AI. While this can help to give a better and easier overview of relevant fundamental values, translating abstract principles to practical activities might still be challenging. Further, clarification regarding coping with identified risks has been particularly demanded (Chui et al., 2021). Standardized procedures can be imposed through, but also by the AI-developing organization itself, e.g., through establishment of clearly communicated accountability frameworks and development of reaction processes. Further, opportunities for education and training of responsible persons can help create awareness about risks and how to deal with them. Nonetheless, while some companies are already establishing or practicing such approaches, it seems that such processes are not yet fully developed and therefore practitioners still see a need for further action. 5.3. Limitations and future research With this paper, our aim was to explore how risk governance methodologies can be used to administer accountability for AI systems. While the chosen workshop-based methodology allowed for exploratory conversations and unveiled also unexpected areas of discussions, certain limitations regarding methodology and overall research approach need to be noted. A first limitation to be pointed out is the potential lack of depth on specific topics allowed through the workshop settings. Due to the exploratory angle of the research, this was not a problem for studying our research questions, however, to obtain detailed solutions for the identified issues, more in-depth investigations would be needed. A second argument for limitation could be the non-systematic procedure in the transcription and analysis of the conversations throughout both workshops. We thus do not qualify this work as deep-qualitative analysis but as an exploratory approach giving insights on the practical implementation. A final limitation of our study is the number of participants and their possible lack of representation of the practitioners’ population. With the aim to mitigate the impact of this last issue on the results, we made sure to have diversity in gender, sector and ethnicity of the participants. Regarding future research, we noted that our workshop participants demanded more precise information on which risk governance methodologies to use when and how. We thus encourage researchers to dig dipper into the questions of risk governance and accountability distribution within each specific sector with a strong focus on understandability and usability of the tools proposed, as a need for more structured and explainable practices has clearly been identified. A qualitative literature-based comparison of tools available in multiple sectors, building off existing work such as Morley et al. (2020), to develop a “new and improved” version could help. More research could also be done on the realistic consequences of AI applications on populations to support the clarification of AI systems’ impacts on humans and society, as participants pointed out the lack of understanding in this area and the lack of implementation of such concerns in current frameworks. Finally, unforeseen events and unknown unknown risks will always be present when it comes to innovation. Therefore, strategies and approaches to uncover and handle them will be needed.
6. Conclusion and outlook The aim of our research was to investigate how current risk governance approaches can contribute to solving the challenge of accountability in and for AI based systems. Risk-based frameworks seem to be common in addressing this issue and have been frequently suggested, the latest regulative effort being the proposed draft of the EU AI Act (Regulation, 2021/0106). However, given their currently rare adoption, existing risk governance frameworks seem to be unpractical in real industry scenarios. Therefore, the purpose of our work was to study current endeavors towards risk governance for AI accountability in practice. An exploratory workshop-based methodology was used to gather insights from practitioners on their organizations’ habits regarding handling risks of AI in practice. Both conducted workshops revealed a variety of perspectives and thus allowed deriving multiple findings regarding requirements of suited risk management methods as well as explanations or actions demanded by the practitioners to move forward. Particularly, we found that clarity and standardization were much desired. This is especially interesting because, despite some efforts from policy, research or industry have been proposed in this direction, such findings further highlight the need to complement rather high-level approaches with tangible methodologies. We suggest that more attention be paid to these aspects in future studies to finally move accountability for AI systems from a theoretical concept to actual practice.
Data availability statement The original contributions presented in the study are included in the article/Supplementary material, further inquiries can be directed to the corresponding author.
Ethics statement Ethical review and approval was not required for the study on human participants in accordance with the local legislation and institutional requirements. Written informed consent for participation was not required for this study in accordance with the national legislation and the institutional requirements.
Author contributions EH, AB, RT, and CL contributed to the conception and design of the overall research project and the conception and planning of the conducted workshops. EH, AB, and RT contributed to the preparation, realization, post-processing and analysis of the two workshops. Further, EH, AB, and RT contributed to writing, revising and approving the manuscript. All authors contributed to the article and approved the submitted version.
Funding This work was supported by Fujitsu Limited and the Technical University of Munich’s Institute for Ethics in Artificial Intelligence (IEAI). Fujitsu Limited had the following involvement with the study: determination of overall study goal and participation in the workshops. All authors declare no other competing interests.
Conflict of interest The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Publisher’s note All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
Footnotes 1Miro Board used for the workshop: https://miro.com/app/board/uXjVOGvHe4s=/?share_link_id=373952986511 2 https://www.mentimeter.com/ 3Building off: http://www.designabetterbusiness.tools/tools/prototype-canvas 4 https://www.bmwgroup.com/content/dam/grpw/websites/bmwgroup_com/downloads/ENG_PR_CodeOfEthicsForAI_Short.pdf 5 https://www.novartis.com/about/strategy/data-and-digital/artificial-intelligence/our-commitment-ethical-and-responsible-use-ai
Supplementary material The Supplementary material for this article can be found online at: https://www.frontiersin.org/articles/10.3389/fpsyg.2023.1073686/full#supplementary-material
| 2023-01-25T00:00:00 |
2023/01/25
|
https://pmc.ncbi.nlm.nih.gov/articles/PMC9905430/
|
[
{
"date": "2023/01/01",
"position": 61,
"query": "AI labor union"
}
] |
WSNA Northwest contract - Labor Relations
|
WSNA Northwest contract
|
https://hr.uw.edu
|
[] |
Labor union contracts · Professional Staff Program · Nonpermanent employment ... Entitlement to the holiday will not lapse when denied under a.i. above.
|
WSNA Northwest contract
Notes: Looking for a specific term or topic within a contract? Use “Control F” (PC) or “Command F” (Mac) to search within a web page.
The text below is the most recent version of the contract. Use the print button for a hard copy.
Visit WSNA UWMC-NW Mid-cycle MOUs to view agreements made within the life of this contract.
WSNA UWMC – Northwest (Effective 2023-2025 Biennium)
Preamble
This Agreement is made and entered into by and between the University of Washington (hereinafter referred to as the “Employer”) and the Washington State Nurses Association (hereinafter referred to as the “Association”). The purpose of this Agreement is to set forth the understanding reached between the parties with respect to wages, hours of work and conditions of employment.
Return to top
Article 1 – Recognition
1.1 Bargaining Unit. The Employer recognizes WSNA as the sole and exclusive bargaining representative for all full-time, part-time, intermittent, and nonpermanent nurses employed as registered nurses by the Employer; excluding supervisory and administrative/management positions and all other employees.
1.2 New Positions. New registered nurse job classifications established during the term of this Agreement shall be covered by this Agreement unless they are bona fide supervisory or administrative/management positions. WSNA shall be notified of any new classifications established by the Employer.
Return to top
Article 2 – Association Membership/Dues Deduction
2.1 Association Membership. The Employer agrees to remain neutral with respect to nurse’s decisions about union membership and payroll deduction. The Employer agrees to direct all communications from nurses regarding union membership or payroll deduction to WSNA or this agreement.
2.2 Dues Deduction. WSNA shall transmit to the Employer by the cut-off date, via a web based electronic reporting system, for each payroll period, the name and Employee ID number of nurses who have, since the previous payroll cut-off date, provided authorization for deduction of dues or have changed their authorization for deduction. The Employer will provide instructions and templates for the web based electronic reporting system and provide a calendar of required payroll cut-off dates.
During the term of this Agreement, the Employer shall deduct dues from the pay of each member of WSNA who voluntarily executes a wage assignment authorization form, and the authorization form will be honored in accordance with its terms. The amount deducted and a roster of all nurses using payroll deduction will be promptly transmitted to WSNA by check payable to its order. Upon issuance and transmission of a check to WSNA, the Employer’s responsibility shall cease with respect to such deductions. WSNA and each nurse authorizing the assignment of wages for the payment of WSNA dues hereby undertakes to indemnify and hold the Employer harmless from all claims, demands, suits or other forms of liability that may arise against the Employer for or on account of any deduction made from the wages of such nurse.
2.3 Revocation.The Employer will direct all questions about revocation to WSNA. A nurse may revoke their authorization for payroll deduction of payments to WSNA by written notice to the Employer and WSNA in accordance with the terms and conditions of their signed membership card. Every effort will be made to end the deduction effective on the first payroll, and not later than the second payroll, after receipt by the Employer of confirmation from WSNA that the terms of the nurse’s signed membership card regarding dues deduction revocation have been met.
2.4 Bargaining Unit Roster.
Each pay period the Employer will provide the following four (4) reports electronically.
Total Compensation and deductions
Name
Home Address
Home phone
Cell phone
Work phone
Work location (building)
Work location (address)
Work station or office (suite and/or number)
Employee ID number
Personal Email
UW email
UW mailbox
Employment status
Employment status effective date
Job classification
Department
Pay grade
Pay step
Pay rate salary
Hourly rate
Supervisor
Supervisor email
Race
Gender
DOB
Date of hire
Job title
Job class code
Shift
Deduction amount dues
Deduction amount fees
Deduction amount other
Deduction amount cope
Total wages for the pay period
Total base pay for pay period
Total overtime pay for pay period
Total overtime hours per pay period
Total hours worked in the pay period
Days in the pay period
Total hours for each class/type of differential and or/ premium pay for the pay period
Total wages for each class/type of differential and or/ premium pay for the pay period
Total wages year to date
Pension plan enrollment (which plan)
Position number
Medical plan enrollment (which plan)
Bargaining Unit
Total FTE
Anniversary date (step date)
Employment status (regular fulltime, regular part time, hourly, fixed duration part time, fixed duration full time) All appointment list
Appointment budget number(s)
Beginning date
End date
Department and/or hiring unit
College/Org name
Job Classification
Job Classification Code
Full time salary or hourly rate
Appointment/FTE Percentage
Appointment status
Appointment term
Distribution line information
Position number
Earnings in last pay cycle
Hours worked in last pay cycle
FTE in last pay cycle Change Report
Name
Job classification
Job classification code
Department
Employee id
Original hire date
Status change date
Termination/separation date if any
Reason for status change, nature of status change
Reason for termination/separation
LOA effective date
Nature of LOA
New hire date
New Hire Vacancy Report
Position Number
Job Classification
Date of vacancy
Elimination date of vacancy
Reason for elimination (filled, deleted, transferred to a different classification/status)
2.5 Contract.The Employer will make available to the designated Local Unit Chairperson a list of all newly hired nurses within five (5) working days. Before the completion of the orientation process, the Employer shall provide the Local Unit Chairperson or designee with an opportunity on release time, to introduce this Agreement to newly hired nurses.
2.6 Distribution of Agreement.Nurses newly hired during the life of this Agreement shall be given a copy of this Agreement by the Employer, as provided by WSNA. WSNA may attach a cover letter, membership application, and return envelope to the Agreement.
Return to top
Article 3 – Association Representatives
3.1 Access to Premises. Access Provision. After notifying Nursing Administration, WSNA’s authorized staff representatives shall have access to the Employer’s premises where nurses covered by this Agreement are working, excluding patient care areas, for the purpose of investigating grievances and contract compliance. Such visits shall not interfere with or disturb nurses in the performance of their work during working hours and shall not interfere with patient care.
3.2 Local Unit Chairperson. WSNA shall have the right to select a local unit chairperson(s) from among nurses in the unit. The local unit chairperson(s) shall not be recognized by the Employer until WSNA has given the Employer written notice of the selection. Unless otherwise agreed to by the Employer, the investigation of grievances and other Association business shall be conducted only during nonworking times, and shall not interfere with the work of other nurses.
3.3 Bulletin Boards. The Employer shall furnish bulletin boards in a prominent place for the use of the local unit. Materials posted may only include meeting notices, local unit newsletters, training and education information, and general matters relating to professional nursing and health care.
3.3.1 E-mail. Authorized representatives of WSNA may transmit messages for distribution to nurses to the System Administrator for posting on the WSNA electronic bulletin board.
3.4 Negotiations Compensation. The Employer will provide paid time or paid release time for up to eight (8) total WSNA designated bargaining team members for up to eight (8) hours per session (including caucus time) for up to eight (8) sessions during negotiations for a new collective bargaining agreement. Neither paid time nor paid release time shall be considered as hours worked for the purposes of calculating overtime.
Return to top
Article 4 – Definitions
4.1 New Graduate/Returning Nurse. New Graduate/Returning Nurse. A registered nurse whose clinical experience after graduation is less than six (6) months, or a registered nurse who is returning to practice with no current clinical training or experience shall be assigned as a team member under the close and direct supervision of a qualified nurse and shall be responsible for the direct care of patients with increasing complexity as individual RN competency level increases. This status generally shall not exceed six (6) continuous months
4.2 Registered Nurse 2. A registered nurse who is responsible for the direct and indirect nursing care of the patient.
4.3 Charge Nurse/Lead Nurse. A nurse who on assignment by the Unit Manager is accountable on a shift basis to maintain organization on a unit such that nursing staff are able to provide patient care. All assigned hours in charge will be paid at the charge nurse/lead nurse premium rate. All nurses assigned as charge/lead or relief charge/lead nurse will receive orientation. In charge nurse/lead nurse assignments the Employer will consider the level of direct patient care along with other duties.
4.4 Preceptor. A preceptor is an experienced RN2 proficient in clinical teaching who is specifically responsible for planning, organizing and evaluating the new skill development of a senior practicum nurse, traveler, or an employed nurse enrolled in a defined program, the parameters of which have been set forth in writing by the Employer. Inherent in the preceptor role is the responsibility for specific, criteria-based and goal directed education and training for a specific training period. Nursing management will determine the need for preceptor assignments. Each newly hired nurse, nurse transferring to a new unit, and a senior practicum nurse shall be assigned a preceptor. It is understood that RN2s in the ordinary course of their responsibilities will be expected to participate in the general orientation process of new nurses. This would include the providing of informational assistance, support and guidance to new nurses.
4.5 Full-Time Nurse. A nurse who works on a regularly scheduled basis at least forty (40) hours per week or eighty (80) hours in a fourteen (14) day period.
4.6 Part-Time Nurse. A nurse who has committed to regularly working and who is assigned a scheduled FTE of less than forty (40) hours per week (less than 1.0 FTE). Unless otherwise provided for herein, a part-time nurse shall be compensated in the same manner as a full-time nurse except that wages and benefits shall be reduced in proportion to the nurse’s actual hours of work.
4.7 Probationary Period. A nurse who has been hired by the Employer on a full-time or part-time basis will attain permanent status in a job classification upon successful completion of a probationary or trial service period. Every part-time and full-time nurse who has been continuously employed by the Employer will serve a probationary period of six (6) consecutive months. Any paid or unpaid leave taken during the probationary period will extend the period for an amount of time equal to the leave on a day per day basis. After successfully completing the probationary period, the nurse shall attain regular status.
During the probationary period, a nurse may be terminated without notice and without recourse to the grievance procedure. Probationary nurses shall not be required to give fourteen (14) days’ notice of intention to terminate.
4.8 Regular Rate of Pay. Unless otherwise required by the Fair Labor Standards Act, the regular rate of pay shall be defined to include the nurse’s hourly wage rate, all premiums, and differentials.
4.9 Certification Pay. Registered nurses will be eligible to receive a nursing certification premium as follows:
All bargaining unit RNs who obtain and maintain a current, nationally recognized renewable certification in a specialty that is representative of the patient population to which they are primarily assigned, based upon management approved Nursing Specialty Certification List, will be eligible. A list of approved certification programs will be kept in Human Resources. Annually, the Conference Committee will review the current list of certifications. The Conference Committee may consider adding new certification programs by reviewing the program description, including purpose, scope, term, pre-requisites, re-certification and any other pertinent information. All new certifications are subject to Employer budget review and approval for funding. The Conference Committee will determine the practice areas in which the certification will apply. The nurse must document certification achievement and re-certification to Human Resources. Only one (1) certification premium rate can be credited per nurse, regardless of other certifications a nurse may have.
Return to top
Article 5 – Employment Practices
5.1 Equal Opportunity. The Employer and WSNA agree that conditions of employment shall be consistent with applicable state, federal, and municipal laws regarding nondiscrimination.
5.2 Notice of Resignation. Nurses shall be required to give at least fourteen (14) calendar days’ written notice of resignation presented in person to the nurse’s manager or designee. The Employer will give consideration to situations that would make such notice by the nurse impossible. The notice period may not include vacation, unless approved. Sick time off usage during the notice period may require proof of illness pursuant to section 11.3.4 of this Agreement.
5.3 Discipline and Discharge. No full-time or part-time nurse who has completed the probationary period shall be disciplined or discharged except for just cause. “Just cause” shall be defined to include the concept of progressive discipline (such as verbal and written reprimands and the possibility of suspension without pay). A copy of all written disciplinary actions shall be given to the nurse. Nurses shall not be required to sign the written disciplinary action except for the purpose of acknowledging receipt thereof. Progressive discipline shall not be applied when the nature of the offense requires immediate suspension or discharge. A nurse may request the attendance of an Association representative during any investigatory meeting which may lead to disciplinary action.
Documentation of disciplinary action at the oral warning or written reprimand level of discipline will not be considered relevant to future discipline after two (2) years, provided there are no further similar occurrences in the intervening period.
5.3.1 Just Cause Intermittent: Except as provided below, Intermittent Nurses shall not be terminated except for just cause. Newly hired Intermittent nurses must work a cumulative one thousand eight hundred and seventy-two (1,872) non-overtime hours or more from their date of hire in continuous employment with the Employer in imtermittent positions. The parties agree to adhere to the grievance process as outlined in Article 17 of the WSNA UWMC-NW CBA. If a nurse is not meeting performance expectations, they will be given an action plan outlining the identified issues. The parties agree to start at Step Two for terminations.
5.3.2 Failure To Schedule: Notwithstanding the above, if an intermittent or nonpermanent nurse fails to provide dates to be scheduled as required by the applicable agreement, or to any lesser extent required by their unit, they shall be subject to a written warning If they thereafter fail to provide dates on a second occasion within a rolling year, their appointment may be ended. Appointments may also end due to a lack of work.
5.3.3 Meeting Request: An intermittent or nonpermanent nurse who is separated may, within twenty-one (21) days of the action, request a meeting with a representative of WSNA, human resources, and the manager of the department or designee to discuss the action. A meeting will be promptly scheduled.
5.4 Personnel File. Personnel records will be maintained for each nurse in Human Resources. Information contained in the personnel record will include: employment application and supporting materials, performance appraisals, records of payroll activity, licensure and training records, letters of commendation and recognition, and records of disciplinary action. By appointment, nurses may inspect their personnel records. Nurses will be given the opportunity to provide a written response to any written evaluations or disciplinary actions to be included in the personnel file. If no disciplinary action is required for a period of two (2) years, evidence of such discipline shall be inadmissible in a grievance arbitration and shall not be used for purposes of progressive discipline. Documentation regarding conditions at date of hire (rate of pay, unit, shift, hours of work), reason for termination, change in employment status, pay or shift and leaves of absence shall be in writing with a copy given to the nurse.
5.5 Parking. WSNA agrees that during the life of this Agreement, the Employer may apply changes in transportation policy, including adjusting parking fees and criteria for assigning parking spots, to the bargaining unit without the obligation to bargain with WSNA.
5.6 Floating. Nurses required to float within the hospital shall receive orientation appropriate to the assignment. In the event floating is necessary, a reasonable effort will be made to float a nurse within the specialty area; however, a nurse may be floated outside their specialty area as staff helper, unless the nurse agrees and is qualified to take a patient assignment. Orientation will be dependent upon the nurse’s previous experience and familiarity with the nursing unit to which such nurse is assigned. Nurses will be expected to perform all basic nursing functions but will not be required to perform tasks or procedures specifically applicable to the nursing unit for which they are not qualified or trained to perform. The Employer will not assign float nurses as charge nurse or lead nurse unless mutually agreeable. Probationary nurses will not be required to float except in emergency situations where skill and competence to perform the work required allow. The order of rotation will be on an equitable rotation to be determined on each unit.
5.7 Evaluations. All nurses will be formally evaluated in writing prior to completion of the probationary period and thereafter on a regular and periodic basis. Where the nurse requests an evaluation, an evaluation will be given, provided that no more than one evaluation will be given per year. Interim evaluations may be conducted as may be required. The evaluation is a tool for assessing the professional skills of the nurse and for improving and recognizing the nurse’s performance. The nurse’s participation, including a self-evaluation, is an integral part of the evaluation process. The nurse will be given a copy of the evaluation, if requested. Nurses will sign the evaluation to acknowledge receipt thereof. Nurses will be given the opportunity to provide a written response to the evaluation which will be retained with the evaluation in the nurse’s personnel file. A peer evaluation format may be developed in addition to supervisory evaluation on a unit-by-unit basis by mutual agreement between unit nurses and the manager.
5.8 Communication. Nurses who have concerns regarding their working conditions are encouraged to raise those concerns through the appropriate levels of supervision and the Conference Committee.
5.9 Nurse Staffing. Quality of care and the health and safety of patients and nurses are of paramount concern to the Hospital and the nursing staff who provide care for our patients. Accordingly, the Employer shall comply with applicable staffing laws and regulations. The hospital and staff RNs shall produce an annual staffing plan in accordance with law, RCW 70.41.420.
5.10 Staffing Concerns. The parties recognize that nurse staffing is an essential component of quality care delivery. It is also acknowledged that healthcare is a dynamic business. As needs change, both parties will comply with the law and work collaboratively through the Nurse Staffing Committee to jointly assess and evaluate nurse staffing.
Nurses, individually or as a group, believing there is an immediate workload/staffing problem should, as soon as possible, bring the problem to the attention of the nurses’ Supervisors or Nurse Managers. If the situation is not remedied, nurses may file an Assignment Despite Objection (ADO) when safely able to do so. No nurse shall be retaliated against for filing an ADO. The ADOs will be reviewed in Staffing Committee.
Nurses who raise staffing issues shall be free from restraint, interference, discrimination or reprisal.
The matters discussed pursuant to this section shall not be subject to Article 17, Grievance Procedure.
5.11 Health and Safety
5.11.1 Healthy and Safe Workplace. The Employer will maintain reasonable conditions of health, safety and sanitation including compliance with Federal, State and Local laws applicable to the safety and health of its employees. Nurses shall not perform tasks that endanger their health or safety if such work or tasks are not inherent to reasonably prudent nursing practice. All health and safety equipment that is deemed necessary for a particular job, as indicated in the job description or department protocols shall be furnished and, where feasible, utilized. The Employer will provide nurses with adequate training on the proper use of proper work methods and protective equipment required to perform hazardous duties. The Employer will continue its
5.11.2 Safety Committee. Employee Safety Committee in accordance with existing regulatory requirements including representation by bargaining unit RNs. The purpose of this Committee shall be to investigate safety and health issues and to advise the Employer on education and preventative health measures of the workplace and its employees. It is a nursing as well as a management responsibility to report unsafe conditions by using the QA Memo or other appropriate method. Where the nurse reports an unsafe condition, the Employer will inform the nurse and the Safety Committee of the planned remedy, if any, within a reasonable time.
5.11.3 Workplace Violence. The employer is committed to promoting a safe workplace that is free from violence or threats of violence. Prominent signs shall be posted in each unit and patient room of the Employer stating this policy.
5.11.4 Workplace Violence Prevention. To promote a safe workplace, the Employer has established a Workplace Violence Prevention Committee which is tasked with the development, implementation and monitoring of the WPVP plan. The WPVP Committee monitors WPV trends and makes necessary recommendations such as training needs, WPV awareness and reporting mechanism/s. The employer agrees to allow one (1) RN selected by WSNA to participate in the Workplace Violence Prevention Committee. Such participation shall be on paid time.
5.12 Travel Pay. Any nurse required by the Employer to travel to a place of work other than their regular official duty station shall be reimbursed for travel costs if eligible, in accordance with the Administrative Policy Statement 70.2, www.washington.edu/admin/adminpro..
Return to top
Article 6 – Seniority
6.1 Seniority. Seniority shall be defined as continuous length of service from date of hire as a registered nurse in the bargaining unit. Part-time and full-time nurses shall accrue seniority at the same rate. In the event two (2) nurses are hired on the same day, relative seniority will be determined by the date the nurse formally accepted the position. The Employer will maintain a record of the date and time each nurse accepts a bargaining unit position. Seniority shall not apply to a nurse until completion of the required probationary period. Upon satisfactory completion of the probationary period, the nurse shall be credited with seniority from most recent date of hire. This definition of seniority applies to the entire Collective Bargaining Agreement except as modified in Article 21 Posting, Transfer, Promotions, Reallocation, which temporarily limits use of a nurse’s full seniority when a nurse transfers into a new department.
6.2 Clinical Cluster. A clinical cluster is a grouping of units within a specialty area in which skills and abilities are similar in nature (see Appendix D).
6.3 Layoff Definition. Layoff shall be defined as a reduction in the number of non- probationary nurses and/or a reduction to the FTE of nurses covered by this agreement that is intended to be permanent or prolonged.
6.4 Definition of Qualified
6.4.1 For Displacing A Less Senior Nurse. A qualified nurse is defined as a nurse who possesses the minimum qualifications, based on established criteria, of the position held by the nurse to be displaced, and is capable of performing the work needed at the level of a satisfactory non-probationary nurse within three months of assuming the position.
6.4.2 For placement into a vacant position open to new graduate recruitment, a qualified nurse will be defined as a nurse who possesses the minimum qualifications and is capable of performing the work needed at the level of a satisfactory non-probationary nurse following an orientation period equal to the average orientation period provided to new graduates hired into that position. Nurses agreeing to accept a vacant position open to new graduate recruitment may have to work a schedule that would have been required of the new graduate for up to a period of one year.
6.5 Prior to Layoff. Prior to implementing a layoff, the Employer, within the context of its determination as to the number of FTEs, shifts, and skill mix needed on the unit, will make a good faith effort to:
Reduce overtime on the unit impacted; Reduce the use of agency and traveler nurses on the unit impacted; Reduce reliance on intermittent or nonpermanent nurses on the unit impacted; Utilize low census as appropriate due to a decrease in patient census or other business operations; Seek volunteers on the unit impacted who are willing to be reassigned or reduce their FTE but not go below .5 FTE; and Freeze external hiring into vacant positions within the clinical cluster until the process in section 6.7 is completed.
6.6 Layoff Notification. If there are insufficient volunteers the least senior nurse(s) on the unit impacted will be identified for layoff. The employer will notify the nurse in the position to be eliminated and WSNA at least thirty (30) calendar days in advance of the date of the projected layoff. During the notice period the Employer will do the following in the order below.
6.7 Vacant Positions Within the Clinical Cluster.
Before making vacant positions within a clinical cluster available to nurses identified for layoff, the Employer will post those positions in accordance with the Job Posting language of the contract. The Employer will identify and list all vacant positions within the clinical cluster that are .5FTE or higher that are available for nurses identified for layoff. In order of seniority, most senior nurse first, nurses identified for layoff who are qualified to perform the work needed in the vacant position(s) will be offered the choice of filling one of the positions listed provided the nurse is qualified (see section 6.3.1). If there is a vacant position available for a nurse identified for layoff that is on the same shift the nurse must either take the vacant position, resign or go on the rehire list. A nurse who accepts a funded vacant position will have the option to resign within six (6) weeks after accepting the position to be placed on the rehire list. This employment option will count as one (1) of the two (2) offers of placement under section 6.8.5. If there is no vacant position available that is on the same shift for a nurse identified for layoff the Employer will move to Displacing a Less Senior Nurse (section 6.8).
6.8 Displacing a Least Senior Nurse. RN3s will have the option of displacing RN2s in accordance with this section. RN2s may only displace RN2s.
Nurses identified for layoff who have an opportunity to displace a less senior nurse will be given up to one week to choose between displacing the less senior nurse or being laid off and placed on the rehire list.
The opportunity to replace the least senior nurse in the affected job class within the nurse’s unit; The opportunity to replace the least senior nurse in their clinical cluster (see Appendix D); When an RN 3 has more seniority according to section 6.1, the RN3 will have the opportunity to replace the least senior RN2, within the same unit.
Nurses may request to be laid off and have the right to be placed on the rehire list(s) instead of accepting an employment option above.
6.9 Rehire List. The rehire list is defined as the list on which a nurse who is laid off is placed after it is determined that:
There are no vacant positions available or there are no vacant positions available for which the nurse is qualified and option (c) below is not available; There is a vacant position(s) available and on the same shift as the position the nurse held for which the nurse is qualified but the nurse has chosen not to fill the position; Option (b) is not available and the nurse has chosen not to displace a less senior nurse in the clinical cluster.
6.9.1 Prior to Referral from Rehire List. Prior to offering reemployment to nurses on the rehire list, the Employer will post vacant positions according to the job posting provisions of this contract. Nurses on the rehire list may apply for posted vacant positions. Nurses laid off in accordance with this Article will be placed on a rehire list for twenty- four (24) months from the date of layoff.
6.9.2 Referral from the Rehire List. Nurses on the rehire list will be offered re- employment in reverse order of seniority when vacant positions remain unfilled after having been posted in accordance with the job posting provisions of this contract. A nurse on the rehire list will be offered reemployment to vacant positions prior to the Employer offering the positions to non-bargaining unit members when:
The FTE of the vacant position is equal to or less than the nurse’s FTE status at the time of layoff; The nurse, in accordance with 6.3 above, is qualified to perform the work needed in the position; RN 2s will be eligible for rehire into RN 2 positions; RN 3s will be eligible for rehire into RN 3 and RN 2 positions.
6.9.3 Responding to Referral from Rehire List. A nurse offered reemployment from the rehire list shall be given up to one (1) week to determine if they want the position and, if accepted, up to an additional week to report to work.
6.9.4 Re-employment Trial Service Period. Nurses reemployed from the rehire list will serve a three (3) month rehire trial service period. During this period either party, at its sole discretion and without resort to the grievance procedure, may initiate return to the rehire list. Time spent in a rehire trial period will not count toward the twenty-four (24) month rehire list period. The three (3) month rehire trial period will be adjusted to reflect any paid or unpaid leave taken during the period.
6.9.5 Removal from the Rehire List. A nurse will be removed from the rehire list when any one of the following occurs:
The nurse has been on the list for twenty-four (24) months and has not been reemployed; The nurse has been successfully reemployed either from the rehire list or as a result of the nurse independently applying for and being selected for a position; The nurse has refused two (2) opportunities for reemployment from the rehire list for a position equal to the nurse’s FTE status at the time of layoff; The nurse has been placed two (2) times from the rehire list and has failed to complete the rehire trial service period.
6.9.6 Re-employment from the Rehire List. A nurse who is reemployed either from the rehire list or as a result of independently applying for and being selected for a position while being on the rehire list, will regain the seniority earned at the time of layoff.
6.9.7 Rights While on Rehire List. A nurse on the rehire list shall be eligible to participate in the Employer’s in-service programs and other Employer training programs on a space available basis and on the nurse’s own time.
6.9.8 Rehire List Nurses and Reserve Work. A nurse on the rehire list shall be given preference for intermittent or nonpermanent nurse work. Acceptance of such work will not affect the nurse’s rehire rights. Preference shall be handled in accordance with the following:
The nurse must specifically request the work in advance and must follow all Employer policies and procedures regarding intermittent or nonpermanent nurse positions. Nurses on the rehire list who meet the requirements of (a) above and the requirements of the position will have preference for intermittent or nonpermanent positions when the schedules are developed.
6.10 Vacation – Laid off Nurses. Nurses who have been laid off will be entitled to be paid for all accrued and unused vacation time off at the time of layoff.
6.11 Vacant Positions Outside Clinical Cluster. Nurses identified for layoff will also be informed of vacant positions not in the clinical cluster in which the nurse identified for layoff worked. If a nurse expresses interest in one of these vacant positions and the nurse and nurse manager agree, the nurse may fill a vacant position not in the nurse’s clinical group. The Employer will not require a nurse identified for layoff to accept a vacant position out of the nurse’s clinical group and a decision by a nurse manager not to accept a nurse into a position out of the nurse’s clinical group shall not be grievable.
6.12 Re-employed Nurses. For purposes of accrual of benefits, re-employed nurses will be treated as newly hired except that a nurse who has been laid off because of lack of funds or curtailment of work and who is re-employed within twenty-four (24) months (plus a twelve (12) month extension if requested) shall be entitled to previously accrued benefits and placement on the salary schedule which they had at the time of layoff.
6.13 Retention of Benefits While on the Rehire List. RNs on the rehire list will receive employer paid benefit coverage so long as they meet the eligibility requirements as determined by the State of Washington.
6.14 Low Census. Low census is defined as a decline in patient care requirements resulting in a temporary staff decrease. During temporary periods of low census, the Employer will:
Cancel Agency nurses. Cancel Travelers Cancel Incentive shifts. Cancel Overtime shifts. Cancel intermittent or nonpermanent nurses Cancel part-time nurses working above their assigned FTE. Ask for volunteers. Rotate regular full-time and part-time nurses by seniority within the Low Census Grouping starting with the least senior nurse first, providing skills, competence and ability are not overriding factors.
If an individual volunteers to take a low census day off, that day off shall be counted for purposes of the rotation list. The rotation list will reflect all low census days taken whether or not the nurse chooses to use annual leave, and will be restarted each six (6) months, beginning with the least senior nurse. Nurses who are scheduled to work but are released from duty due to low census shall continue to receive medical and dental insurance coverage. Low census hours taken shall be considered hours paid for the accrual of all benefits and seniority. Low census is an appropriate subject for the Conference Committee.
6.14.1 Additional Hours. Nurses desiring additional hours should notify the Employer in writing, identifying their specific availability. The Employer will first offer additional scheduled hours in the assigned unit to those nurses who have made the request who have lost hours due to low census during their current or prior posted work schedule.
6.14.2 Low Census Groups. The seven (7) Low Census Groups are:
Medical, Surgical, Float Pool, Adult Psych Services, ICU/SCU; CBC; Endoscopy; Emergency Department; Surgical Services (including operating room, post-anesthesia care unit, pre-surgical admitting, pre-admit calling, Cardiac Procedure Unit and OSC); Electrophysiology lab, Interventional Radiology, Cardiac Cath Lab,. Primary Care Clinics – nurses low censused on a per clinic basis or temporarily reassigned to another area provided skills, competency, and ability are considered equal as determined by the employer. Ambulatory Specialty Clinics – nurses low censused on a per clinic basis or temporarily reassigned to another area provided skills, competency, and ability are considered equal as determined by the employer.
6.14.3 Low Census Notification. As a general guide, the Employer will seek to provide notice to nurses called off for low census not less than one and one-half (11/2) hour prior to day-shift starting time and not less than two (2) hours prior to evening and night-shift starting time.
6.14.4 Low Census Report Pay. Nurses who report for work as scheduled (unless otherwise notified in advance) and who are released from duty by the Employer because of low census shall receive a minimum of four (4) hours’ work or four (4) hours’ pay at the regular rate of pay. Nurses who are sent home after this four (4) hours and subsequently that day are called and agree to work shall receive time and one-half (1½x) the regular rate of pay for all hours worked on the callback.
6.15 Restructure/Rebid. A restructure/rebid is a redistribution of nursing positions when deemed necessary by the Hospital. When the Hospital proceeds with a restructure/rebid, the following procedures shall be followed:
6.15.1 Restructured Units. The Employer shall notify WSNA and nurses thirty (30) days prior to the effective date of any restructure/rebid process. WSNA may request a special meeting of the Conference Committee, preferably before the positions are posted, to discuss the proposed changes and evaluate any alternatives. Such meeting shall take place within two (2) weeks following notification.
The employer shall determine the number of full-time and part-time positions by FTE, shift and schedule line required for the new or restructured unit. A listing of these positions on the new/restructured unit shall be posted on the unit(s) for 10 days. The employer will also post a department seniority list.
6.15.2 Nurse Rebid Process. To be considered in the rebid process, a nurse within a restructured unit must submit a bid during the job posting period to their Director/Manager on a form developed by the Employer. The Employer may modify the form as it deems necessary to fit the rebid situation. Such form shall include the newly created positions with shift schedule lines, shift and FTE. The form shall also include a method for the nurse to rank the positions in order of preference.
6.15.3 Rebid & Absent Nurses. The Director/Manager shall attempt to inform any nurse in a restructured unit who during the entire time allocated for the bidding process is on vacation, absent for an extended illness, or is on a leave of absence about the rebid process by telephone and email. Notification shall occur at least ten (10) days prior to the posting period. At that time, the nurse shall receive the bid form and options via email or phone call, or by other mutually agreed to method. Rebids from these nurses must be submitted in writing via email or hand delivery prior to the conclusion of the ten (10)-day posting period. If a nurse fails to submit a bid sheet, management shall place the nurse into a position in order of seniority after all nurses who submitted a bid sheet are placed.
6.15.4 Restructure/Rebids & Seniority. Seniority within the department, per Article 21 Posting, Transfer, Promotion, Reallocation, shall be the determining factor in making reallocation assignments.
6.15.5 Restructure/Rebid & Schedule Changes. At the conclusion of the bidding period and within seven (7) calendar days, the hospital shall assign the FTE, shift and schedule line by seniority, consistent with this Article. The hospital shall notify the nurse in writing of the results. Once the nurses are notified, there shall be at least a sixteen (16) day waiting period prior to implementation of the new schedule. The hospital shall provide WSNA with copies of the rebid forms and results of the rebid within five (5) business days of notifying the nurses.
6.15.6 Restructure/Rebid & A Displaced Nurse. A displaced nurse who does not receive an acceptable position, chooses not to submit a bid or experiences a reduction in FTE, will have the option being laid off pursuant to Section 6, Layoff.
Return to top
Article 7 – Hours of Work and Overtime
7.1 Work Day. The normal work day shall consist of eight (8) hours work to be completed within eight and one-half (8-1/2) consecutive hours, ten (10) hours work to be completed within ten and one-half (10-1/2) consecutive hours, or twelve (12) hours work to be completed within twelve and one-half (12-1/2) consecutive hours. For ten (10) hour shifts, refer to Appendix B. For twelve (12) hour shifts, refer to Appendix C.
7.2 Work Period. The normal work period shall consist of forty (40) hours of work within a seven (7) day period or eighty (80) hours of work within a fourteen (14) day period.
7.3 Alternative Work Schedules. The Employer may post ten (10) hour positions and twelve (12) hour positions. The Employer may not require any nurse in an eight (8) hour position to work a ten (10) hour or twelve (12) hour position. When mutually agreeable to the supervisor, the nurse concerned and WSNA, the work schedule may consist of shifts other than eight (8), ten (10) or twelve (12) hours. Alternative work schedules may be established by agreement between an individual nurse or a group of nurses and their nurse manager within their unit. To the extent any of the terms and conditions of the alternative schedule would violate any of the provisions of this Agreement, the Employer will negotiate such schedules with WSNA prior to implementing the schedules. For ten (10) hour shifts, refer to Appendix B. For twelve (12) hour shifts, refer to Appendix C.
Alternative schedules shall be in writing, identifying in detail the schedule to be worked. A copy of the schedule will be sent to the Local Unit Chairperson within fifteen (15) days of its implementation. Once the schedule is implemented, the Employer will not discontinue it with less than six (6) weeks’ notice to the affected nurses, including one (1) complete schedule posting period.
In the event a majority of the nurses involved in the alternative schedule desire to discontinue the schedule they will give their nurse manager written notice of their desire signed by each of the nurses desiring the change. On presentation of this request the nurse manager will discontinue the schedule after one (1) complete monthly work schedule under the alternative schedule has been worked after the notice.
7.4 Work Schedules. It is recognized and understood that deviations from normal hours of work may occur from time to time, resulting from several causes, such as but not limited to vacations, leave of absence, weekend and holiday duty, absenteeism, employee requests, temporary shortage of personnel, low census and emergencies. The Employer retains the right to adjust work schedules to maintain an efficient and orderly operation. Monthly work schedules shall be posted sixteen (16) days prior to the beginning of the scheduled work period. Except for emergency conditions involving patient care, and low census conditions, individual scheduled hours of work set forth on the posted work schedules may be changed only by mutual consent.
7.4.1 Nurses are encouraged to work together to create a schedule. Professionalism, flexibility and team work are key to a successful scheduling program. The goal is for nurses to work together to create a mutually acceptable schedule that meets the scheduling parameters as defined by the Employer. Departments will maintain procedures that define responsibilities and timeframes for each step within the scheduling process, clarify procedures for scheduling requests (e.g. trades, use of benefit time, professional leave, weekend coverage) and how scheduling conflicts are resolved. The Employer retains ultimate responsibility for schedule approval.
7.5 Overtime. Overtime shall be compensated for at the rate of one and one-half (1½x) times the regular rate of pay for time worked beyond the nurse’s normal full-time work day or normal full-time work period. Double time (2x) the regular rate of pay shall be paid for all consecutive hours worked by the nurse beyond twelve (12) hours. For purposes of computing overtime, the nurse’s straight time hourly rate of pay shall include shift differential. Time paid for but not worked shall not count as time worked for purposes of computing overtime pay. Excluding emergency situations, the Employer as a matter of policy shall not reschedule a nurse for extra work because of time off with pay.
7.5.1 Overtime Definition. All time which is compensated for at the rate of time and one-half (1-½x) the rate of pay will be considered overtime whether or not such compensation is characterized as overtime or premium pay. Except for work on a holiday, only time worked at straight time will count toward calculation of daily or weekly overtime.
7.5.2 The Employer will not initiate requests for nurses to work their administrative time before or after their scheduled shift.
RN3s that are approved to schedule administrative time before or after a scheduled shift shall have that time considered time worked and shall be paid at the regular rate of pay. Time worked for administrative time is determined by the nurse and will not count towards work before or after the standard shift (Section 7.5) or double time premium in excess of twelve (12) hours per day (Section 7.5) This time will also not count towards toward Rest Between Shifts (Section 7.10).
7.6 Prohibition of Mandatory Overtime. The acceptance of overtime by any nurse is strictly voluntary, except that overtime may be assigned on a mandatory basis (a) because of an unforeseeable emergent circumstance, (b) because of prescheduled on-call time, (c) when the Employer documents that the employer has used reasonable efforts to obtain staffing for reasons other than chronic staff shortages, or (d) when a nurse is required to work overtime to complete a patient care procedure already in progress where the absence of the nurse could have an adverse effect on the patient.
7.7 Overtime Approval. All overtime must be pre-approved by a supervisor or designee. The Employer and WSNA agree that overtime should be minimized. Overtime shall be computed to the nearest quarter hour. There shall be no pyramiding or duplication of overtime pay or premium pay paid at the rate of time and one-half (1½x). When a nurse is eligible for two (2) or more forms of premium pay and/or overtime pay, the nurse will receive the highest pay rate. Every effort will be made to discuss changes made to time records with the affected nurse prior to submission to payroll.
7.8 Meal/Rest Periods. All nurses shall receive an unpaid meal period of one-half (1/2) hour. No nurse shall be required to work more than five (5) consecutive hours without a thirty (30) minute meal period unless there is an urgent patient care need. Nurses working a twelve (12) hour shift are entitled to a second thirty (30) minute meal period. If the Nurse voluntarily chooses to waive their right to a second meal period they must do so in writing on the waiver form provided by the Employer. Nurses required to remain on duty or in the Hospital during their meal period shall be compensated for such time at the appropriate rate of pay.
All nurses shall receive one paid (1) fifteen (15) minute break for every four (4) hours of work. If a nurse requests their manager (or alternate) for the time off to take a break and the manager is unable to provide adequate coverage for the nurse the Employer will pay the break time at the rate of time and one-half (1½x) times the nurse’s regular rate, if the manager does not reschedule the break. Nurses should report missed breaks to their unit leadership at the time of the missed break whenever possible and enter and record missed rest and meal breaks on the time clock.
7.9 Weekends. The weekend shall be defined for first (day) and second (evening) shift personnel as Saturday and Sunday. For third (night) shift personnel, the weekend shall be defined as Friday night and Saturday night. For staff who work alternative shifts and/or twelve (12) hour shifts, the shift will count as a weekend shift if the majority of the shift falls between 11pm Friday and 11pm Sunday.
The Employer will make a good faith effort to schedule all regular full and part-time nurses for every other weekend off. In the event a nurse works two successive weekends, all time worked on the second weekend shall be paid at the rate of time and one-half (1½x) the regular rate of pay. The third regularly scheduled weekend shall be paid at the nurse’s regular rate of pay. Every other weekend off cycles may be altered with at least ten (10) days’ notice prior to the start date of the next posted work schedule. Subject to advance approval, nurses may request the trading of weekends, providing the schedule change does not place the Employer into an overtime pay condition. This time and one-half (1½x) premium pay provision (and the double time (2x) premium referenced below) shall not apply to nurses who voluntarily agree to work more, frequent weekend duty, or to nurses who have agreed to trade weekend work. The availability of weekend work shall be determined by the Employer.
Unscheduled weekend is defined as a shift that is in addition to the nurse’s posted scheduled shifts after the schedule is posted and when the nurse is performing direct nursing care. Nurses that agree to work unscheduled weekend shifts shall be paid at double time (2x) the regular rate of pay. This double time (2x) the regular rate of pay cannot be stacked with the successive weekend premium above.
This section does not apply to scheduled standby shifts. Paid time off taken on a weekend does not count as a weekend shift worked for purposes of eligibility of the double time (2x) premium.
7.10 Rest Between Shifts. Nurses who qualify for rest between shifts premium (1.5x) will receive it for eight (8) hours.
Nurses will qualify to receive rest between shifts premium if they do not receive eleven (11) hours rest between regularly scheduled shifts. This includes time worked from call back or standby situations.
Nurses who are called back to work, whether or not the nurse was on standby, will qualify for rest between shifts premium if the work performed from standby or call back results in the nurse not receiving eleven (11) hours unbroken rest before the start of the nurse’s next regularly scheduled shift.
7.11 Shift Rotation. Should shift rotation be required on a temporary basis, volunteers will be sought first. If there are insufficient volunteers, the Employer will assign shift rotation on the basis of qualifications and reverse seniority on the affected unit. A nurse is entitled to take up to twenty-four (24) hours of rest both before and after a shift rotation occurs if the change in start time from the nurse’s regular shift to the adjusted shift is greater than or equal to ten (10) hours.
7.11.1 Limitations on Occurrence of Shift Rotation. The Employer will limit required shift start changes, of more than eight (8) hours, to two (2) per twenty-eight (28)-day work schedule. For example, if an RN is on day shift and rotates to evening shift, this constitutes one of the two allowable shift rotations. When the RN returns to day shift, this constitutes the second of two allowable shift rotations within the twenty-eight (28)-day work schedule.
7.11.2 Double Shifts. Any nurse who works a double shift of at least sixteen (16) hours in combination, may request to have their next scheduled shift off, if that shift is within twenty-four (24) hours of the end of their double shift. If the nurse requests, they shall be entitled to draw on any accrued and unused annual leave to cover the hours of the shift they have requested off. If the nurse has opted for taking their shift off and patient demand cannot be covered by another nurse and, therefore, the nurse is required to work their shift, the nurse will receive payment at the overtime rate of time and one-half (1½x) for all hours worked on that shift.
Return to top
Article 8 – Compensation
8.1 Progression Start Dates. Annually the salary of nurses covered by the UWMC-NW bargaining units will be increased by one step on the nurse’s progression start date until the nurse has reached the top step of the appropriate salary range. For purposes of step increases, the progression start date will be determined as follows:
The first of the current month for actions occurring between the first and the fifteenth of the month; or, The first of the following month for actions occurring between the sixteenth and the end of the month.
When unpaid time off exceeds ten (10) working days in any calendar month or eighty (80) hours prorated for part-time employment, the progression start date will be extended by one (1) month. Unpaid time off for Worker’s Compensation, military service, or for the purpose of formal collective bargaining sessions, will not alter the progression start date.
When a nurse returns from layoff status, the progression start date will be reestablished and extended by an amount of time equal to the period of layoff to give credit for time served in a salary step prior to layoff.
When a progression start date coincides with a promotional date, the appointment to a new salary range, and/or a market adjustment, the step increase will be applied first.
8.2 Date of Implementation. Wage increases, longevity increments, and increases in other forms of compensation set forth in this Agreement shall become effective at the beginning of the first full payroll period on or after the calendar dates designated.
8.3 Recognition for Past Experience. Full-time and part-time nurses hired during the term of this Agreement shall be compensated in accordance with the following plan:
All nurses hired during the term of this Agreement shall be given full credit for continuous recent experience when placed on the wage scale. For purposes of this section, continuous recent experience as a registered nurse shall be defined as clinical nursing experience in an accredited hospital or skilled nursing facility (including temporary employment with an employer) without a break in nursing experience which would reduce the level of nursing skills in the opinion of the Employer.
8.4 Wage Increases. Nurses covered by this Agreement shall be paid in accordance with the wage schedule as shown in Appendix E.
The wage schedule in Appendix E reflects the following:
Effective July 1, 2023, each classification represented by WSNA will continue to be assigned to the same Pay Table and Salary Range as it was assigned on June 30, 2023. Effective July 1, 2023, each nurse will continue to be assigned to the same Salary Range and Step that they were assigned on June 30, 2023 unless otherwise agreed. Nurses who are paid above the maximum for their range on June 30, 2023 will continue to be paid above the maximum range on July 1, 2023 unless otherwise agreed.
Effective July 1, 2023, all step values of Table BZ, Range 02 will be increased by an additional four percent (4%). This increase will be based upon the salary schedule in effect on June 30, 2023. Effective July 1, 2024, all step values of Table BZ, Range 02 will be increased by an additional three percent (3%). This increase will be based upon the salary schedule in effect on June 30, 2024. The RN 3 scale shall be amended to reflect eight percent (8%) above the RN2 scale at each step of the wage scale throughout the life of this Agreement. Charge Nurse will remain two dollars and fifty cents ($2.50) above each step on the RN2 scale and Float Nurse will remain five dollars ($5.00) above each step on the RN2 scale. Range increases on Table BZ will be calculated based off the full time monthly value and then converted to an hourly rate.
Return to top
Article 9 – Other Compensation
9.1 Shift Differential. Nurses assigned to work the second (3-11 p.m.) shift shall be paid a shift differential of two dollars and fifty cents ($2.50) over the hourly contract rate of pay. Nurses assigned to work the third (11 p. m. – 7 a. m.) shift shall be paid a shift differential of four dollars and fifty cents ($4.50) over the hourly rate of pay. Nurses shall be paid shift differential on second or third shift if the majority of hours are worked during the designated shift. RNs who are assigned to work first shift shall receive second shift differential when they work four (4) or more hours after 1500.
An RN permanently assigned to second (evening) or third (night) shift will receive the shift premium assigned to that shift. An RN who is temporarily assigned, within the RN’s FTE, to another shift with a lower shift rate will receive the higher shift rate if the temporary assignment is not greater than five (5) consecutive working days.
An RN who is using paid time off will receive the shift premium if the RN has a permanent work shift designation of evening or night.
9.2 Low Census Standby Premium and Callback Pay When Called Back from Low Census. Where there is a low census, under section 6.14, nurses may be put on standby during the hours they are scheduled to work and will be compensated at the rate of four dollars ($4.00) for each hour on standby. If the nurse is called in from standby, then the nurse will be guaranteed a minimum of three (3) hours’ pay at time and one-half (1 ½ X) the nurse’s regular rate of pay. The nurse will be paid at the nurse’s regular rate of pay for the remainder of the scheduled shift. In addition, the nurse shall receive standby pay for the entire shift. Nurses who agree to be on standby shall continue to be considered on low census and all such hours shall count toward seniority and benefit accrual. If in any unit, voluntary standby is not routinely accepted by nurses on that unit, the Employer may give WSNA thirty (30) days’ written notice to apply standby in that unit according to the low census order of Article 6.14.
9.3 On Call Premium and Callback Pay. Nurses assigned to be on call during the hours outside of the nurse’s regularly scheduled shift, shall be paid seven dollars ($7.00) per hour for all
standby hours. If the nurse is called to work, they shall be guaranteed a minimum of three (3) hours’ pay at the rate of time and one-half (1½x) the nurse’s regular rate of pay in addition to on call pay. Nurses on call shall be provided with signal devices. Travel to and from the Hospital shall not be considered time worked. On call duty shall not count toward seniority and benefit accrual. This section shall not apply to nurses subject to low census.
9.4 Charge Nurse/Lead Nurse Pay. Nurses who are assigned as charge nurse/lead nurse with a regular schedule of at least .8 FTE will receive two dollars and fifty cents ($2.50) per hour additional pay. Nurses who are assigned relief charge or relief lead will receive a differential of two dollars and fifty cents ($2.50) per hour for hours actually worked.
9.5 Preceptor Pay. Any nurse assigned as a preceptor shall receive a premium of one dollar fifty cents ($1.50) per hour.
9.6 Weekend Premium Pay. Any nurse who works on a weekend shall receive four dollars ($4.00) per hour premium pay for each hour worked on the weekend in addition to the nurse’s regular rate of pay. Weekend premium pay shall not be included in the nurse’s regular rate of pay for overtime pay calculations, unless required by the Fair Labor Standards Act.
9.7 Work in Advance of Shift. When a nurse is required to report for work in advance of the assigned shift and continues working during the scheduled shift, all hours worked prior to the scheduled shift shall be paid at time and one-half (1½x) the regular rate of pay. A nurse who reports to work in advance of the assigned shift will not be released from duty prior to the completion of that scheduled shift, except for low census, unless there is mutual consent.
9.8 Work on Day Off. Full-time nurses called in on their regularly scheduled day off shall be paid at the rate of one and one-half (1½x) times the regular rate of pay for the hours worked.
9.8.1 Incentive Shifts. To avoid using agency, the employer may post incentive shifts paying an additional ten dollars ($10.00) per hour. Incentive shifts will be posted in advance when possible. Regularly scheduled nurses will have priority over intermittent or nonpermanent nurses. Staff working at regular pay rate will have priority over overtime shifts. Nurse must work scheduled shifts during that pay period.
9.8.1.1 Scheduling. Unit manager will designate and post incentive shifts as far in advance as they deem necessary. Nurse will schedule incentive shifts with the unit manager or designee.
A nurse canceling an incentive shift will give twenty-four (24) hour notice (except in case of illness). Failure to do so may result in ineligibility for future incentive shifts. Management reserves the right to cancel incentive shifts. Nurses calling in sick on incentive shifts will not receive sick pay.
9.9 Certification Pay. Nurses certified in a specialty area recognized by the Employer, as defined in section 4.10, shall receive a premium of one dollar twenty-five cents ($1.25) per hour.
9.10 Float Pool Premium. Any full time or part time nurse with regularly scheduled shifts and hours designated to the Float Pool or as nursing house supervisors, shall receive a five dollar ($5.00) per hour premium for all hours worked as a Float Pool nurse as part of the nurse’s regular rate of pay.
9.11 Temporary Floating Premium. Effective upon ratification, all nurses who are assigned to float to a regular unit, other than their hired unit(s)/area(s), except for Designated Float Nurses, shall receive one dollar fifty cents ($1.50) per hour float premium for all hours worked as a float to the other unit/area.
9.12 BSN Premium. A RN who holds a BSN or higher degree in nursing shall receive one dollar ($1.00) per hour premium pay.
9.13 MSN/MN Premium. A RN who attains a Master of Science in Nursing (MSN) or a Master of Nursing (MN) degree shall receive a one (1)-step pay increase with proof of the degree.
Return to top
Article 10 – Holiday and Vacation Time Off
10.1 Holidays. Holidays for nurses in the bargaining unit shall be as designated by the Employer and approved by the State of Washington for classified nurses of the Employer including UWMC-NW. The designated holidays are observed as shown on the Employer’s staff holiday schedule:
New Year’s Day Martin Luther King Jr.’s Birthday (3rd Mon Jan) President’s Day (3rd Mon Feb) Memorial Day Juneteenth Independence Day Labor Day Veteran’s Day Thanksgiving Day Native American Heritage Day Christmas Day Personal Holiday
The Employer may designate other days to be observed in lieu of the above holidays.
Holidays are prorated for part-time nurses. The Employer may designate other days or shifts to be observed in lieu of the above holidays.
To be paid for a holiday not worked, nurses must be in pay status for at least four (4) hours on the last scheduled work shift preceding the holiday.
Holiday Pay Rules. The following applies to the holidays listed in this Article:
Full Time Nurse:
When the holiday falls on the full time nurse’s regularly scheduled work day and is worked, the nurse will be paid holiday premium pay (one and one half) for all hours worked. The nurse will also receive eight (8) hours of holiday credit. When the holiday falls on the full time nurse’s regularly scheduled work day and is not worked, the nurse will be paid eight (8) hours at the nurse’s regular rate of pay. If the nurses shift is more than eight (8) hours, the nurse will be allowed to use compensatory time, holiday credit, vacation time off, or unpaid time off to complete the regularly scheduled work hours for the day. When the holiday falls on the nurse’s regularly scheduled day off, the nurse will receive eight (8) hours of holiday credit.
Part Time Nurse:
When the holiday falls on the part time nurse’s regularly scheduled work day and is worked, the nurse will be paid holiday premium pay (one and one half) for all hours worked. The nurse will also receive the prorated to full time number of hours of holiday credit. When the holiday falls on the part time nurse’s regularly scheduled work day and is not worked, the nurse will be paid the prorated to full time number of hours at the nurse’s regular rate of pay. When the holiday falls on the part time nurse’s regularly scheduled day off, the nurse will be paid the prorated to full time number of hours at the nurse’s regular rate of pay.
Night Shift Nurses. The holiday for night shift nurses whose work schedule begins on one calendar day and ends on the next will be the shift in which half or more of the hours fall on the calendar holiday. That shift will be treated as the holiday and paid in accordance with the above holiday pay rules.
Holiday Credit.
Holiday credit will be used and scheduled by the nurse in the same manner as vacation time off. Holiday Credit Cash Out: All holiday credit must be used by June 30 of each year. The nurse’s holiday credit balance will be cashed out every June 30 or when the nurse leaves University employment for any reason. The nurse’s holiday credit balance may be cashed out when the nurse: Transfers to a position in their department with different funding sources or, Transfers to a position in another department.
Nurses must be in pay status for at least four (4) hours of their last scheduled work day preceding the holiday in order to be paid for the holiday.
10.1.1 Personal Holiday.
Each nurse may request one personal holiday each calendar year and the Manager must grant this day, provided: The nurse has been continuously employed by the Employer for more than four (4) months; The nurse has made the request in accordance with the department scheduling guidelines; however, the nurse and the supervisor may agree upon an earlier date; and The number of nurses selecting a particular day off does not prevent providing continued public service. Entitlement to the holiday will not lapse when denied under a.i. above. Full-time nurses shall receive eight (8) hours of regular holiday pay for the personal holiday. Any differences between the scheduled shift for the day and eight (8) hours may be adjusted by use of vacation time off, use or accumulation of compensatory time or holiday credit as appropriate, or unpaid time off. Part-time classified nurses shall be entitled to the number of paid hours on a personal holiday that are pro-rated to their FTE.
10.2 Vacation Time Off. The vacation accrual schedule for nurses in the bargaining unit shall be as follows:
1st year 12 days 2nd year 13 days 3rd year 14 days 4th year 15 days 5th year 16 days 6th year 17 days 7th year 18 days 8th year 19 days 9th year 20 days 10th year 21 days 11th year 22 days 12th – 19th year 23 days 20th – 24th year 24 days 25th year or more 25 days
10.3 Vacation Time Off—Use.
10.3.1 All requests for vacation time off must be approved by the Employer in advance of the effective date unless used for emergency childcare.
10.3.2 Vacation time off shall be scheduled by the Employer at a time most convenient to the work of the department, the determination of which shall rest with the employing official. As far as possible, time off will be scheduled in accordance with the wishes of the nurse in any amount up to the total of their accrued time off balance.
10.3.3 Paid vacation time off may not be used in advance of its accrual.
Scheduling of vacations shall be the responsibility of supervision. When a vacation request is submitted eight (8) weeks or more in advance of schedule posting, that request shall be responded to within two (2) weeks of that request. Nurses shall not be required to secure their own coverage for any properly requested time off. Scheduled weekends during approved vacation periods shall not be rescheduled. However, schedules may be adjusted to meet unit needs. The department shall receive input from the local unit before making changes to established department policies on vacation time off. A signup sheet will be maintained for volunteers to cover vacation weekends. Such volunteers will be scheduled prior to requiring schedule adjustments and will be paid the appropriate weekend premium.
10.3.4 Peak Vacation Periods: Peak vacation periods for the purposes of RN scheduling are June 16 through September 15 and Thanksgiving through January 1.
From June 16 through September 15, vacations will be a maximum of two (2) calendar weeks, unless the clinical area or unit has a limit that exceeds two (2) calendar weeks or can accommodate more than two (2) calendar weeks. The two (2) calendar weeks may be taken consecutively if the RN requests two (2) consecutive weeks. From Thanksgiving through January 1, vacations will be a maximum of one (1) calendar week and may be inclusive of one major holiday unless the clinical area or unit has a limit that exceeds one (1) calendar week or can accommodate more than one (1) calendar week. Peak Period Vacation Scheduling: Peak period vacation requests will follow the schedule below unless the clinical area or unit has an existing procedure for vacation requests and responses: June 16 through September 15 requests must be submitted in writing by February 1 and will be approved or denied in writing by February 28. Thanksgiving through January 1 vacation requests must be submitted in writing by July 1 and will be approved or denied in writing by July 31.
The time frames for submission of requests contained in (a) and (b) above do not preclude nurses from submitting requests after the deadline; however, late requests will be considered after those that are timely submitted in accordance with the unit’s scheduling guidelines.
In the event multiple requests for the same period cannot be granted and cannot be resolved among the nurses involved, unit needs or seniority as calculated for transfer will be used as the determining factor.
10.4 Vacation Time Off – Accumulation-Excess. A RN may accumulate a vacation balance that normally shall not exceed two hundred eighty (280) hours. A RN may elect to accrue in excess of two hundred eighty (280) hours provided:
10.4.1 The excess accrued vacation time is used prior to the RN’s anniversary date.
10.4.2 The nurse has requested and received written approval of a plan from their manager and Human Resources to use the excess accrued vacation. It is the RN’s responsibility to monitor and manage excess accrued vacation. If the approvals outlined above are not met, the RN will lose the accrued vacation in excess of two hundred eighty (280) hours on their anniversary date.
10.4.3 If a RN’s request for vacation time off is denied by the Employer, the maximum of two hundred eighty (280) hours accrual shall be extended for each month that the vacation time off is denied.
10.5 Vacation Time Off – Cash Payment. RNs who have completed six (6) continuous months of employment and who separate from service by resignation, layoff, dismissal, retirement or death are entitled to a lump sum cash payment for all unused vacation time off. Vacation time off payable under section 10.2, 10.3, and this section shall be computed at the RN’s regular rate of pay. No contributions are to be made to the Department of Retirement systems for lump sum payment of excess vacation leave accumulated, nor shall such payment be reported to the Department of Retirement Systems as compensation.
10.6 Vacation Time Off Donation. In accord with state law and Employer policy, RNs may donate vacation time off as shared leave to any nurse eligible to receive such donations.
Return to top
Article 11 – Sick Time Off
11.1 Sick Time Off — Accrual.
11.1.1 Full-time RNs shall accrue eight hours of sick time off for each month of completed classified service. Paid sick time off may not be used in advance of accrual.
11.1.2 RNs working less than a full-time schedule shall accrue sick time off on the same pro-rata basis that their employment schedule bears to a full-time schedule.
11.1.3 Employees with leave without pay exceeding 80 hours in a month (prorated for part-time) will earn a monthly accrual proportionate to the number of hours in pay status, in the month to that required for full-time employment. Sick leave accruals must not exceed eight hours in a month.
11.2 Family Members.The RN’s spouse or state registered domestic partner (any sex), child, child’s spouse, parent, grandparent, grandchild, sibling. Family member also includes individuals in the following relationships with the RN’s spouse or domestic partner: child, grandchild, parent and grandparent. “Child” also includes a child of a legal guardian or de facto parent, regardless of age or dependency status and those to whom the nurse is “in loco parentis” or “de facto” parent as well as a child of a legal guardian or de facto parent. Parent and Parent-in-law also includes de facto parent, foster parent, stepparent, or legal guardian. Family member also includes any individual who regularly resides in the employee’s home or where the relationship creates an expectation that the employee care for the person, and that individual depends on the employee for care. Family member does not include an individual who simply resides in the same home with no expectation that the employee care for the individual.
11.3 Sick Time Off—Use.
11.3.1 Sick time off shall be allowed a nurse under the following conditions:
Because of and during illness, disability or injury which has incapacitated the nurse from performing required duties. By reason of exposure of the nurse to a contagious disease during such period as attendance on duty would jeopardize the health of fellow employees or the public. When an employee’s child’s school or place of care has been closed for a health-related reason or after the declaration of an emergency by a local or state government or agency, or by the federal government. Because of emergencies caused by serious illness or injury of a family member fifteen years of age and over that require the presence of the nurse to provide immediate necessary care of the patient or to make arrangements for extended care. The Employer may authorize sick time off use as provided in this subsection for other than family members. To care for a child under the age of eighteen (18) with a health condition that requires treatment or supervision, or to make arrangements for extended care. Because of illness or injury of a family member who is a person of disability and requires the nurse’s presence to provide short-term care or to make arrangements for extended care. To provide emergency child care for the nurse’s child. Because of a family member’s death that requires the assistance of the nurse in making arrangements for interment of the deceased. For personal medical, dental, or optical appointments or for family members’ appointments when the presence of the nurse is required, if arranged in advance with the employing official or designee.
11.3.2 Sick time off may be granted for condolence or bereavement.
11.3.3 In accordance with the Washington Family Care Act, RCW 49.12, RNs shall be allowed to use any or all of their choice of sick time off or other paid time off to care for their
child with a health condition that requires treatment or supervision or spouse, parent, parent-in-law or grandparent who has a serious health condition or an emergency condition.
Nurses shall not be disciplined or otherwise discriminated against because of the exercise of these rights.
11.3.4 Sick Time Off Verification. The Employer may only request verification if you use or request to use paid sick time off after absences on (3) consecutive work days. Such verification or proof may be given to the supervisor/manager or Human Resources according to departmental policy.
11.3.5 Any discrimination or retaliation against a nurse for lawful exercise of paid sick time off rights is not allowed. Corrective action may not be taken for the lawful use of paid sick time off.
11.4 Bereavement Time Off.Three (3) days of bereavement time off shall be granted for each death of a family member, defined as the RN’s spouse or state registered domestic partner (any sex), child, parent, grandparent, grandchild, sibling. Family member also includes individuals in the following relationships with the RN’s spouse or domestic partner: child, parent and grandparent. “Child” also includes a child of a legal guardian or de facto parent, regardless of age or dependency status and those to whom the nurse is “in loco parentis” or “de facto” parent as well as a child of a legal guardian or de facto parent. Parent and Parent-in-law also includes de facto parent, foster parent, stepparent, or legal guardian.
Sick time off in addition to the three (3) days of bereavement time off may be used for the purpose of bereavement with the approval of the nurse manager.
11.5 Sick Time Off Cash Out.
Nurses shall be eligible to receive monetary compensation for accrued sick time off as follows: In January of each year, and at no other time a nurse whose year-end sick time off balance exceeds four hundred and eighty (480) hours may choose to convert sick time off hours earned in the previous calendar year minus those used during the year to monetary compensation. No sick time off hours may be converted which would reduce the calendar year-end balance below four hundred and eighty (480) hours. Monetary compensation for converted hours shall be paid at the rate of twenty-five percent (25%) and shall be based upon the nurse’s current salary. All converted hours will be deducted from the nurse’s sick time off balance. Nurses who separate from state service due to retirement or death shall be compensated for their unused sick time off balance at the rate of twenty-five percent (25%). Compensation shall be based upon the nurse’s salary at the time of separation. For the purpose of this subsection, retirement shall not include “vested out-of-service” nurses who leave funds on deposit with the retirement system. Compensation for unused sick time off shall not be used in computing the retirement allowance; therefore, no contributions are to be made to the retirement system for such payments, nor shall such payments be reported as compensation. A nurse who separates from the classified service for any reason other than retirement or death shall not be paid for accrued sick time off.
11.6 Sick Time Off Donation. In accord with state law and Employer policy, RN’s may donate sick time off as shared leave to any nurse eligible to receive such donations under the Employer’s Shared Leave Programs under APS 45.10 and 45.9.
11.7 Advance Notification. All nurses working any shift shall notify the Employer at least two (2) hours in advance of the nurse’s scheduled shift if unable to report for duty as scheduled.
11.8 Voluntary Employee Beneficiary Association (VEBA). RNs who retire from the University of Washington may participate in the Employer’s VEBA program in accord with the terms and conditions of the program at the time of the RN’s retirement. Such terms and conditions may be found on the HR website at: https://hr.uw.edu/benefits/retirement-plans/nearing-retirement/veba-sick-leave-cash-out-at-retirement/
11.9 Northwest Hospital Carryover. NWH Carryover cannot be cashed out at retirement, will not be considered in the Annual Attendance Incentive Program, does not transfer outside of any UWMC-NW/UWMC-Montlake WSNA covered positions and will not transfer if the nurse takes a job with another state agency. Nurses who have this leave will be encouraged to use it to cover absences when appropriate before using UW Sick Time Off.
11.10 UWMC-NW WSNA sick time off can be used for the illness, injury, and medical appointments of the individual nurse and their family member, and for other reasons as outlined in the current CBA. It can also be placed into a VEBA Health Reimbursement account at twenty-five percent (25%) of the cash value at retirement or paid at twenty-five percent (25%) of the cash value as part of the Annual Attendance Incentive Program (RCW 41.04.340) if certain conditions are met.
NWH Carryover can be used when the nurse is sick or under various other circumstances. However, it cannot be cashed out at retirement or as part of an annual incentive program.
Return to top
Article 12 – Medical and Insurance Benefits
12.1 State Benefits. Nurses in the UWMC-NW Bargaining Unit will be included in the same Public Employees Benefit Board authorized state-employee benefits and the same wellness plans as nurses at UWMC-Montlake in analogous employee types. Nurses will no longer receive a premium or credit for waiving any elements of coverage.
12.2 Health Care Premiums. For the 2021-2023 biennium, the Employer will contribute an amount equal to eighty-five percent (85%) of the total weighted average of the projected health care premium for each bargaining unit nurse eligible for insurance each month, as determined by the Public Employees Benefits Board. The projected health care premium is the weighted average across all plans, across all tiers.
12.3 Medical Plans. The point-of-service costs of the Classic Uniform Medical Plan (deductible, out-of-pocket maximums and co-insurance/co-payment) may not be changed for the purpose of shifting health care costs to plan participants, but may be changed from the 2014 plan under two (2) circumstances:
In ways to support value-based benefits designs; and To comply with or manage the impacts of federal mandates.
Value-based benefits designs will:
Be designed to achieve higher quality, lower aggregate health care services cost (as opposed to plan costs); Use clinical evidence; and Be the decision of the PEB Board.
12.4 Medical Plan Expiration. Article 12.3 will expire June 30, 2023.
12.5 Plan Information. The PEBB Program shall provide information on the Employer Sponsored Insurance Premium Payment Program on its website and in an open enrollment publication annually.
12.6 Life, Disability And Dental Plans. The Employer will pay the entire premium costs for each bargaining unit nurse for dental, basic life, and any offered basic long-term disability insurance coverage. If changes to the long-term disability benefit structure occur during the life of this agreement, the Employer recognizes its obligation to bargain with the Coalition over impacts of those changes within the scope of bargaining.
12.7 Wellness.
12.7.1 To support the statewide goal for a healthy and productive workforce, nurses are encouraged to participate in a Well-Being Assessment survey. Nurses will be granted work time and may use a state computer to complete the survey.
12.7.2 The Coalition of Unions agrees to partner with the Employer to educate their members on the wellness program and encourage participation. Eligible, enrolled shall have the option to earn an annual one hundred twenty-five dollars ($125.00) or more wellness incentive in the form of reduction in deductible or deposit into the Health Savings Account upon successful completion of required Smart Health Program activities. During the term of this Agreement, the Steering Committee created by Executive Order 13-06 shall make recommendations to the PEBB regarding changes to the wellness incentive or the elements of the Smart Health Program.
Return to top
Article 13 – Leaves of Absence
13.1 In General. All leaves of absence are to be requested from the Employer in writing as far in advance as possible, stating the reason for the leave and the amount of time requested. A written reply to grant or deny the request shall be given by the Employer within thirty (30) days.
13.2 Parental Leave. A parental leave of absence shall be granted upon request of the nurse for a period of up to six (6) months after the birth of a child to the nurse, spouse or domestic partner, or because of the placement of a child with the nurse or domestic partner through adoption or foster care, without loss of benefits accrued to the date such leave commences. Such leave shall be in addition to maternity leave granted for the temporary disability period resulting from pregnancy or childbirth. If the nurse’s absence from work for family reasons does not exceed twelve (12) weeks, the nurse shall return to work on the same unit, shift and former full-time or part-time status. Thereafter for the duration of the six (6) month leave, upon requesting return to work, the nurse shall be offered the first available opening for which the nurse is qualified. Leave may be taken in a single block or by mutual agreement on an intermittent or reduced schedule basis. During the period of disability, the nurse may use previously accrued sick time off, vacation time off, personal holiday, holiday credit, or compensatory time, the combination of which may be determined by the nurse. During the parental leave portion, the nurse may take previously accrued vacation time off, personal holiday, holiday credit, compensatory time and up to eight (18) weeks (720) hours of sick time off, a combination of which may be determined by the nurse. Nurses must use all applicable accrued time off prior to going on unpaid time off unless it runs concurrently with Washington Paid Family and Medical Leave (PFML). Prior to the nurse returning from a leave of absence, the Employer may require a statement from a licensed medical practitioner verifying the period of physical disability and attesting to the nurse’s capability to perform the work required of the position.
13.3 Family and Medical Leave Act. In the event the Family and Medical Leave Act (FMLA) provides a better benefit than those provided in sections 13.2 and 13.3, the appropriate provisions of the FMLA shall prevail.
13.4 Military Spouse Leave. Up to fifteen (15) days of unpaid time off will be granted to an eligible nurse (nurse who averages twenty (20) or more hours of work per week) whose spouse or state-registered domestic partner is on leave from deployment or before and up to deployment during a period of military conflict. The nurse must provide their supervisor with notice of the nurse’s intention to take leave within five (5) business days of receiving official notice that the nurse’s spouse will be on leave or of an impending call to active duty. This provision shall be administered in accordance with RCW 49.77.
13.5 Military Leave With Pay.
Nurses shall be entitled to military leave with pay not to exceed twenty-one (21) working days during each year, beginning October 1 and ending the following September 30, in order to report for active duty, when called, or to take part in active training duty in such manner and at such time as they may be ordered to active duty or active training duty in the Washington National Guard or of the Army, Navy, Air Force, Coast Guard, or Marine Corps reserve of the United States or of any organized reserve or armed forces of the United States. Such leave shall be in addition to any vacation and sick time off to which a nurse is entitled and shall not result in any reduction of benefits, performance ratings, privileges or pay. During military leave with pay, the RN shall receive the RN’s normal rate of pay. Nurses required to appear during working hours for a physical examination to determine physical fitness for military service shall receive full pay for the time required to complete the examination.
13.6 Military Leave Without Pay. A Registered Nurse shall be entitled to military leave of absence without pay for service in the uniformed services of the United States or the state, and to reinstatement as provided in chapter 73.16 RCW. No adjustments shall be made to the seniority date, months of service toward their vacation accrual rate, progression start date and time off service date (anniversary date) while a nurse is on military leave.
13.7 Leave with Pay. Leave with pay shall not affect a nurse’s compensation, accrued hours, benefits or status with the Employer.
13.8 Return from Leave. Nurses who return to work on a timely basis in accordance with an approved leave of absence agreement shall be entitled to the first available opening for which the nurse is qualified.
13.9 Civil Duty Time Off. All full-time and part-time nurses who are required to serve on jury duty or who are called to be a witness on behalf of the Employer in any judicial proceeding, shall be compensated by the Employer for the difference between their jury duty/witness fee pay and their regular rate of pay. Nurses subpoenaed for proceedings not involving the Employer will be given unpaid release time.
13.10 Leave Without Pay for Reason of Faith or Conscience. In accordance with RCW 1.16.050, nurses will have the option to take up to two unpaid holidays per calendar year for a reason of faith or conscience, or for an organized activity conducted under the auspices of a religious denomination, church, or religious organization.
To take unpaid time off under the statute, nurses must consult with their supervisor or administrator and use their unit’s procedure for making advance leave requests. The nurse will need to inform their unit that the requested unpaid day(s) is for a reason of faith or conscience or for an organized activity conducted under the auspices of a religious denomination, church, or religious organization.
The Employer can only deny a nurse’s requested day(s) off if the employer determines that the requested time off would impose an undue hardship on the employer, or the nurse’s presence is necessary to maintain public safety. Undue hardship is defined in Washington Administrative Code (WAC) 82-56-020. Nurses may be asked to provide verification for their unpaid leave request.
Requests to use unpaid personal holiday leave will follow normal departmental leave request processes.
13.11 Leave of Absence Without Pay.
Leave of absence without pay may be allowed for any of the following reasons: Conditions applicable for leave with pay; Disability leave; Educational leave; Leave for government service in the public interest; Parental leave; Child care emergencies; To accommodate annual work schedules of nurses occupying cyclic year positions; Serious health condition of an eligible nurse’s child, spouse, domestic partner (same sex or opposite sex) or parent. Requests for leave of absence without pay must be submitted in writing to the Employer and must receive the approval of both the employing official and the personnel officer. Leave of absence without pay extends from the time a nurse’s leave commences until he/she is scheduled to return to continuous service, unless at the nurse’s request the employing official and the personnel officer agree to an earlier date. Vacation time off and sick time credits will not accrue during a leave of absence without pay which exceeds ten (10) working days in any calendar month.
13.12 Bereavement Time Off. Three (3) days of bereavement leave shall be granted for each death of a family member as defined in section 11.4.
Sick leave in addition to the three (3) days of bereavement leave may be used for the purpose of bereavement with the approval of the nurse manager.
13.13 Domestic Violence Leave. Eligible nurses shall be entitled to take leave for domestic violence, sexual assault or stalking that the nurse has experienced, or to assist a qualifying family member who has experienced domestic violence, sexual assault or stalking. Leave under this provision shall be administered in accordance with RCW 49.76.
For purposes of this section, “family member” includes a nurse’s child, spouse, parent, parent-in-law, grandparent, domestic partner or a person who the nurse is dating. The RN must provide advance notice of the need for such leave, whenever possible and may be required to provide verification of need and familial relationship (e.g. a birth certificate, police report).
A RN may elect to use any combination of their accrued time off or unpaid time off. The Employer shall maintain health insurance coverage for the duration of the leave.
The Employer shall maintain the confidentiality of all information provided by the RN including the fact that the RN is a victim of domestic violence, sexual assault or stalking, and that the RN has requested leave.
13.14 Disability Leave.
13.14.1 Disability leave shall be granted for a reasonable period to a permanent nurse who is precluded from performing their job duties because of a disability (including those related to pregnancy or childbirth). Disability leave includes a serious health condition of the nurse as provided in the federal Family and Medical Leave Act of 1993. (FMLA) Leave for disability due to pregnancy or childbirth is in addition to twelve (12) weeks under the FMLA.
13.14.2 In any case in which the necessity for leave is foreseeable based on planned medical treatment, the nurse shall provide not less than thirty (30) days’ notice, except that if the treatment requires leave to begin in less than thirty (30) days, the nurse shall provide such notice as is practicable.
13.14.3 The disability and recovery period shall be as defined and certified by the nurse’s licensed health care provider. The nurse shall provide, in a timely manner, a copy of such certification to the employer.
13.14.4 Certification provided under this section shall be sufficient if it states:
The date on which the condition commenced; The probable duration of the condition; The appropriate medical facts within the knowledge of the health care provider regarding the condition; A statement that the nurse is unable to perform the essential functions of their position.
13.14.5 The employer may require, at its expense that the nurse obtain the opinion of a second health care provider designated or approved by the employer. The health care provider shall not be employed on a regular basis by the employer.
13.14.6 In any case in which the second opinion differs from the original certification, the employer may require, at its expense that the nurse obtain the opinion of a third health care provider designated or approved jointly by the employer and the nurse. The opinion of the third health care provider shall be final and binding.
13.14.7 The employer may require that the nurse obtain subsequent re-certifications on a reasonable basis.
13.14.8 Disability leave may be a combination of sick time off, vacation time off, personal holiday, holiday credit, compensatory time, and unpaid time off and shall be granted at the written request of the nurse. The combination and use of paid and unpaid time off during a disability leave shall be per the choice of the nurse.
13.14.9 The Employer shall maintain health care coverage during disability leave granted here, in accordance with the requirements of the Public Employee’s Benefits Board (PEBB), FMLA, and PFML. As specified in the FMLA and PFML, the Employer may recover the premium for maintaining coverage during the period of unpaid disability leave if the nurse does not return to work.
13.14.10 If necessary due to continued disability, the nurse shall be allowed to use eight (8) hours of accrued paid time off per month for the duration of the leave to provide for continuation of benefits as provided by the PEBB. The employer shall designate on which day of each month the eight (8) hours paid time off will be used.
13.15 Workers Compensation Leave: Nurses who suffer a work related injury or illness that is compensable under the state worker’s compensation law may select time loss compensation exclusively or a combination of time loss compensation and accrued paid time off.
The policy for the Employer’s “Return to Work Program” can be located at the following link: https://uwmc.uwmedicine.org/sites/PoliciesProcedures/apop/Pages/default.aspx
13.16 Leave Due to Family Care Emergencies.
Absence due to family care emergencies as defined shall be charged to one of the following: Compensatory time off; Vacation time off; Sick time off; Personal holiday; Unpaid time off. Use of any of the above time off type is dependent upon the nurse’s eligibility to use such time off. Accrued compensatory time shall be used before any other time off is used. Use of vacation time off, sick time off, and unpaid time off for emergency family care is limited to six (6) days total per calendar year. The nurse upon returning from such time off shall designate in writing to which time off type the absence will be charged. For the purpose of this section, advance approval or written advance notice of time off use shall not be required.
There are two (2) types of family care emergencies: Child care emergency is defined as a situation causing a nurse’s inability to report for or continue scheduled work because of emergency child care requirements (“child” as identified in section 15.2), such as unexpected absence of regular care provider, unexpected closure of child’s school, or unexpected need to pick up child at school earlier than normal. An elder care emergency occurs when you are unable to report for or continue scheduled work because of emergency elder care requirements such as the unexpected absence of a regular care provider or unexpected closure of an assisted living facility. Accrued sick time off in excess of six (6) days may be used when the nurse’s child’s school or day care has been closed by a public official for any health-related reason or after the declaration of an emergency by a local or state government or agency, or by the federal government.
Return to top
Article 14 – Family Medical Leave Act and Parental Leave
14.1 Leave Procedure. All leaves as delineated in sections 13.1 through 13.16 above are to be requested from the Employer in writing as far in advance as possible, stating all pertinent details and the amount of time requested. A written reply to grant or deny the request shall be given by Human Resources within thirty (30) days except as otherwise provided in this Article.
14.2 Federal Family and Medical Leave Act. Benefits provided through state laws and this contract shall not be diminished or withheld in complying with the Family and Medical Leave Act of 1993.
Consistent with the federal Family and Medical Leave Act of 1993, a nurse who has worked for the state for at least twelve (12) months and for at least one thousand two hundred and fifty (1250) hours during the twelve (12) months prior to the requested l
| 2023-01-01T00:00:00 |
https://hr.uw.edu/labor/staff-unions/wsna-northwest/wsna-northwest-contract
|
[
{
"date": "2023/01/01",
"position": 75,
"query": "AI labor union"
}
] |
|
Workers AI - Cloudflare
|
Workers AI
|
https://www.cloudflare.com
|
[] |
Workers AI facilitates the scalable development & deployment of AI applications at the edge. It enhances user experience and efficiency by running AI closer to ...
|
"ChainFuse transforms unstructured data chaos into actionable insights, ensuring every piece of customer feedback, issue, and opportunity is heard and valued. Using products such as Workers AI, AI Gateway, and Vectorize, we have successfully analyzed and categorized over 50,000 unique conversations from places like Discord, Discourse, Twitter, G2, and more. Having access to 32 AI models for any task—and swapping them on the fly—allows us to be accurate and efficient at scale."
| 2023-01-01T00:00:00 |
https://www.cloudflare.com/developer-platform/products/workers-ai/
|
[
{
"date": "2023/01/01",
"position": 3,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 2,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 3,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 3,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 3,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 3,
"query": "AI workers"
},
{
"date": "2023/10/01",
"position": 3,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 3,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 3,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 3,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 3,
"query": "AI workers"
},
{
"date": "2024/05/01",
"position": 3,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 4,
"query": "AI workers"
},
{
"date": "2024/09/26",
"position": 1,
"query": "AI workers"
},
{
"date": "2024/11/01",
"position": 3,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 3,
"query": "AI workers"
},
{
"date": "2025/02/01",
"position": 2,
"query": "AI workers"
},
{
"date": "2025/05/01",
"position": 2,
"query": "AI workers"
},
{
"date": "2025/05/01",
"position": 46,
"query": "artificial intelligence workers"
},
{
"date": "2025/06/01",
"position": 47,
"query": "artificial intelligence workers"
}
] |
|
What is an AI Agent? - WorkFusion
|
What is an AI Agent?
|
https://www.workfusion.com
|
[] |
AI Agents are highly skilled AI-enabled digital employees that work alongside real-world colleagues to reduce manual work, enhance quality, increase speed, ...
|
At WorkFusion, we are pioneers in AI Agents for Financial Crime Compliance.
Our pre-built AI Agents are process automation personified. They are fully digital members of your team who work alongside their real-world colleagues to reduce manual work, enhance quality, increase speed, save money, support regulatory compliance, and expand the overall capacity of your team.
They take care of the often mind-numbing and repetitive activities such as data collection, document handling, and false-positive clearing – freeing-up their colleagues to work on more strategic and fulfilling projects. And they expedite previously slow and ineffective work that helps to improve customer service.
| 2023-01-01T00:00:00 |
https://www.workfusion.com/ai-agent/
|
[
{
"date": "2023/01/01",
"position": 4,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 4,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 5,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 5,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 5,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 5,
"query": "AI workers"
},
{
"date": "2023/10/01",
"position": 6,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 5,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 5,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 6,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 6,
"query": "AI workers"
},
{
"date": "2024/05/01",
"position": 5,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 5,
"query": "AI workers"
},
{
"date": "2024/11/01",
"position": 5,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 5,
"query": "AI workers"
},
{
"date": "2025/02/01",
"position": 7,
"query": "AI workers"
},
{
"date": "2025/05/01",
"position": 8,
"query": "AI workers"
}
] |
|
The effects of AI on firms and workers - Brookings Institution
|
The effects of AI on firms and workers
|
https://www.brookings.edu
|
[
"Malihe Alikhani",
"Martin Neil Baily",
"Aidan T. Kane",
"Mark Maccarthy",
"Eduardo Levy Yeyati",
"Xiang Hui",
"Oren Reshef"
] |
Instead, AI adoption is associated with firm growth, increased employment, and heightened innovation, particularly in product development.
|
This article synthesizes recent research—including new findings from Babina, et al. (2024) and Babina, et al. (2023) —to assess the real-world impacts of AI on firms and workers. Contrary to common fears, we find that AI has so far not led to widespread job loss. Instead, AI adoption is associated with firm growth, increased employment, and heightened innovation, particularly in product development. However, the effects are not uniformly distributed: AI-investing firms increasingly seek more educated and technically skilled employees, alter their internal hierarchies, and contribute to rising industry concentration. These trends carry important implications for public policy, including workforce development, education and reskilling initiatives, and antitrust enforcement. This article reviews the evidence and highlights key takeaways for policymakers navigating the AI-driven economy.
The rapid rise of commercial AI has inevitably brought concerns regarding its potential to displace human workers. There is evidence that AI can automate some cognitive tasks or increase worker productivity in a way that could reduce the number of workers needed. For example, Brynjolfsson, et al. (2025) find that AI tools make customer service workers much more efficient. Fedyk, et al. (2022) find that audit firms that use AI reduce their audit workforce. But the good news is that the labor-displacing effects seem confined to select sectors and occupations. On aggregate, recent academic research finds evidence that companies’ use of AI has been accompanied by an increase in the workforce.
The past decade has seen tremendous growth in commercial investments in artificial intelligence (AI). The first wave came after the 2012 ImageNet challenge , which was a pivotal moment in the history of artificial intelligence, particularly computer vision and deep learning. Then, advances in computing power—GPU hardware —powered neural network models trained on large amounts of data. Across industries, from construction to pharmaceuticals to finance, companies rushed to implement AI in their operations. This trend has only accelerated with the release of OpenAI’s ChatGPT in late 2022. Even larger models trained on even larger datasets are showing even greater power, and AI applications are becoming ubiquitous across U.S. businesses (Babina, et al. 2024) .
AI has spurred firm growth—and increased employment
Babina, et al. (2024) leverage detailed data on job postings and individual employees, covering as much as 64% of the U.S. workforce, to track individual companies’ investments in artificial intelligence and the accompanying changes in firms’ operations and workforces. The approach builds on the heavy reliance of AI implementation on skilled AI workers to measure firm-level AI investments by tracking AI researchers and software engineers. This method enables investigation of firm-level effects of AI investments, which was previously lacking. Most prior work focused on the effects of AI on occupations or industries due to the dearth of firm-level data. Exceptions include studies such as Alderucci, et al. (2019), which look at AI patents. This approach is great for identifying firms that are producing AI tools but is less suitable to capture all firms using AI in their everyday operations.
The method to measure firm-level AI investments proceeds in three steps. First, job postings can be used to identify the skills and terms that are related to AI. Starting with the set of general, core AI skills (“artificial intelligence,” “machine learning,” “natural language processing,” and “computer vision”), every required skill from the job postings is assigned a score based on its co-occurrence with these core AI skills. For example, the skill “Tensorflow” has a value of 0.9, which means that 90% of job postings with Tensorflow as a required skill also require one of the core AI skills or contain one of the core AI skills in the job title. Hence, a “Tensorflow” requirement in a job posting is highly indicative of that job being AI-related. On the other hand, the AI-relatedness measure of the skill “Snow Removal” is literally zero. Having identified the most AI-relevant terms, the second step is to search for them in the resume data. If someone has a job title of “Machine Learning Engineer” or a patent in “deep learning” they are likely implementing AI as their job. The final step is to aggregate the measure up to the firm level. What percentage of the employees at a given firm in a given year are AI workers? This percentage will be very low at all firms—AI workers are highly specialized labor, about as frequent as patent-holding inventors. But for some firms this percentage will be 0 (these firms are not investing in AI), whereas for other firms it may be a full 1% (these firms have a dedicated AI team). The difference in the increase in the share of AI workers from 2010 to 2018 gives a consistent measure of the extent to which different firms invested in artificial intelligence during the period when AI emerged as commercially valuable technology.
The measure of firm-level investments in artificial intelligence shows a striking positive relationship with firm growth. A one-standard-deviation difference in AI investments has translated—over the course of a decade—into around a 20% difference in sales growth. That’s roughly 2% additional sales growth per year. Looking at the timing of the effects, they are typically not immediate. It takes approximately two to three years for firms’ AI investments to trickle down to increased sales, but after that initial ramp up period, there is a persistent increase. This delay between investment in a new technology and ultimate performance improvements is not surprising given what we know from the history of new technologies. As described in Brynjolfsson, et al. (2019), it typically takes time for firms to invest in the necessary complementary assets needed to take advantage of the new technology.
Given popular press concern about the link between AI and jobs, a perhaps even more surprising finding is that the growth in sales has been accompanied by similar growth in employment. Firms that invested more in AI actually increased their total employee headcount. Similar to sales, employment growth begins to show up approximately two to three years after AI investments and remains elevated thereafter. In terms of magnitude, growth in employment is similar to growth in sales: an extra 2% per year per one-standard-deviation increase in AI investment. This also shows up in costs: Both costs of goods sold and operating expenses increase roughly proportionally to sales as companies invest in AI.
As a result, productivity measures have not moved much on aggregate over the past decade of increasing AI investments. Several papers examining the effects of AI have found strong evidence of increased growth in firm sales, coupled with null effects on productivity. For example, Rock (2019) and Babina, et al. (2024) find that AI investments have not been associated with increases in either sales per worker or revenue total factor productivity.
Thus, it does not appear to be the case that the main use of AI so far has been to cut costs and replace human workers. This may be relevant in certain specific sectors, such as audit, where artificial intelligence is especially well-suited to the task and where there might not be much potential to innovate and grow. But in most sectors, the primary effect of AI on firms is through sales growth and expansion.
AI-fueled growth has come from innovation
It appears that AI-fueled growth is coming from increased product innovation. Over the course of 2010-2018, we find that a one-standard-deviation increase in firm-level AI investments has been associated with a 13% increase in trademarks and a 24% increase in product patents. Both effects are statistically significant. In contrast, process patents go up by just over 1%, and the effect is not statistically significant. This finding is consistent with firms using AI predominantly to innovate in the product space, rather than for process innovation and improved efficiency.
AI-powered innovation includes both incremental changes such as improving products and breakthrough innovations such as completely new product creation. For example, computer vision that makes cars “see” makes them safer, improving car quality. In terms of breakthrough innovations, the leadership of Moderna highlighted advances in machine learning and AI as being the driving force behind the firm’s ability to very rapidly create a vaccine against COVID-19. Experimentation processes that would have previously taken years can happen in a matter of months due to the new prediction technology.
Workforce upskilling when firms adopt AI
AI-fueled innovation means that the overall relationship between commercial adoption of AI and employment has been positive. But does this mean that there is no reason for workers to worry about their jobs? Not quite. What the granular employer-employee data show is a more nuanced picture. While overall employment has increased at AI-investing firms, the composition of those firms’ workforces has also changed.
Babina, et al. (2023) show that as firms invest in AI they start tilting their workforces towards (i) more educated workers, (ii) more technically skilled workers, and (iii) more independent contributors. Over the course of eight years, a one-standard-deviation increase in firm-level AI investment has been associated with a 3.7% increase in the share of college-educated workers, a 2.9% increase in the share of workers with master’s degrees, and a 0.6% increase in the share of workers with doctoral degrees. Correspondingly, the share of workers without a college degree has declined by 7.2%.
Since total employment went up, this does not necessarily mean that firms fired non-college-educated workers. But there has been a substantial reallocation in terms of new hiring, with AI-investing firms looking for an increasingly educated workforce. Furthermore, AI-investing firms are also looking for different types of education: The share of employees whose most recent degree was in a STEM field has increased in firms investing in AI, while the relative share of other types of majors (social science, arts, medicine, etc.) has correspondingly declined.
This is one way in which AI is similar to prior technologies—it is a skill-biased technological change favoring higher-skilled workers (Autor, et al. 1998; Autor, et al. 2003; Acemoglu and Autor 2011; Katz and Murphy 1992). The fact that firms’ AI investments favor higher-skilled workers highlights the importance of reskilling, which allows the workforce to keep pace with new technological advances.
Changes in firms’ hierarchical structure
Interestingly, when we look at the hierarchical structure of firms’ workforces, we see that AI investments are associated with increased hiring of independent, deputized workers and decreased hiring of top and middle management positions. This empirical finding is not obvious ex ante. On the one hand, increased product innovation spurred by firms’ AI investments can lead to a larger, more complex firm structure that would require greater management. On the other hand, firms’ investments in AI can reduce the costs of accessing knowledge through reduced data processing, resulting in increased problem-solving ability of individual employees at all levels. Garicano and Rossi-Hansberg (2006) suggest that this can lead to increased span of control of individual employees and less reliance on top-heavy hierarchical structures. In their model, technology that improves knowledge acquisition is an equalizing force across employees.
Using detailed resume data, Babina, et al. (2023) find that a one-standard-deviation increase in firms’ AI investments from 2010 to 2018 is associated with a 1.6% increase in the share of junior employees (i.e., any employees not managing others—either entry-level employees or more experienced single contributors). Correspondingly, AI-investing firms have experienced a 0.8% decrease in the share of middle managers (i.e., team leads or managers with a cluster of teams under them) and a 0.7% decrease in the share of senior management (i.e., division heads and firm-level management including the C-Suite). Importantly, there was no contemporaneous trend towards more bottom-heavy hierarchical structures: The shares of junior employees, mid-level management, and senior management remained more or less flat across U.S. public firms from 2010 to 2018. The differential tilt towards less top-heavy hierarchical structures seems to be unique to AI-investing firms.
Overall, investments in AI are associated with major changes in firms’ labor composition and organization, translating into a broader shift toward more junior employees with high educational attainment and technical expertise. The shifts in hierarchical structure and employees’ technical education go hand in hand with each other. Caroli and Van Reenen (2001) point out the complementarity between organizational change and employee skills. The flattening of hierarchical structures requires higher human capital from each individual employee. This is what appears to be happening with AI. Greater access to this technology empowers highly skilled employees to innovate and achieve more. By deputizing these employees, the firm becomes less reliant on heavy management layers.
Effects from artificial intelligence on US industries
Artificial intelligence has already brought about significant changes to firm operations and workforces. But what has been the net effect on U.S. industries? Have firms that invested more in AI benefited at the expense of their competitors? Or has AI been a generally uplifting trend?
There are a few ways we can think about the broader, industry-level effects of AI. The first is to look at what happens to industry-level sales and employment. This is the most immediate way to see whether the benefits from a new technology such as AI aggregate up or if it’s purely a reallocation effect—where some firms benefit by grabbing revenues away from other firms. For some prior technologies, including robotics, there is evidence that suggests a reallocation effect. For example, Acemoglu, et al. (2020) find that investments in robots are associated with increases in firm-level employment but decreases in industry-level employment. That is, some firms automate their workforces, become more efficient, grab market share from their competitors, grow, and hire more workers—but the concentration of activity in the automating firm means that aggregate employment falls at the industry level.
To date, there has been no evidence of a displacement effect from AI at the industry level. Babina, et al. (2024) examine how AI investments at the industry level (i.e., the increase in the share of AI workers in an industry) relate to industry-level growth in sales and employment. Both industry-level sales and industry-level employment increase with AI, at least in the sample of publicly traded (Compustat) firms. Looking at total industry employment (including non-publicly traded firms) shows milder growth, suggesting that there is some reallocation from smaller, private firms to larger, publicly traded firms. But the reallocation effect does not dominate, and on net there is weakly positive growth in total industry employment.
The second way to look at the industry-level trends is to consider the distributional effects between firms. While industry-level growth is good news, the distributional effects can shed light on potential concerns such as increased concentration and decreased competition. And indeed, investments in artificial intelligence do not generate the same kind of benefits for all firms. Larger firms, which have extensive proprietary data and more resources to invest in bespoke AI models, can reap greater benefits from their AI investments.
Babina, et al. (2024) slice the sample of Compustat firms into terciles based on initial firm size measured as of 2010. They then examine the effect of AI investments—that is, differential growth between firms that invest more in AI versus those that invest less—separately within each tercile. The results show that the effect of AI has been most pronounced in the top tercile of firms (i.e., the largest firms). The effect of AI has been milder but still significant in the middle tercile of firms. But the beneficial effect of AI has been statistically insignificant and economically small when we look at the lowest tercile of firms based on firm size. This means that among smaller firms, there has been virtually no difference between those firms that invested in AI and those that did not.
At the industry level, this means that AI investments are associated with increased industry concentration. There are different ways to measure concentration: the share of sales that goes to the single largest firm in an industry and the Herfindahl-Hirschman Index. Both of these measures have increased in industries that invest more in artificial intelligence. Thus, AI investments appear to be generally beneficial for industry growth, but they also lead to increased concentration, whereby the largest firms benefit the most and grow even larger.
Is this increase in concentration a cause for concern? Some might worry that an industry dominated by a few large firms leads to higher prices for consumers. We do not know yet. Firms’ AI investments have not been associated with increased markups yet. But it’s not implausible that firms investing in AI first focus on growth through innovation and new product creation and then later take advantage of their greater market dominance by increasing prices. Potential for decreased competition is one area where policy should remain flexible and responsive to future incoming data. But so far, AI has brought positive effects for U.S. firms and industries without decreasing employment—and that is good news.
Policy implications
The rapid diffusion of AI across firms has already begun to reshape labor markets, organizational structures, and industry dynamics. While the evidence to date is largely positive—pointing to growth in firm sales, employment, and innovation—these benefits have accrued disproportionately to larger, better-resourced firms and more highly educated workers. As a result, AI adoption is contributing to increased industry concentration and a more skill-biased labor market. Policymakers should prepare for these structural changes by investing in education and workforce development programs that emphasize STEM and digital skills, supporting mid-career reskilling for displaced workers, and monitoring the competitive dynamics of increasingly AI-driven industries.
In parallel, expanding access to data through frameworks like open banking or open data can help level the playing field for smaller firms that lack the proprietary data resources of their larger competitors. Indeed, evidence from Babina et al. (2025) shows that open banking policies, which allow bank customers to share their financial data from their bank with financial technology services (fintechs), have led to increased fintech entry and innovation, potentially counteracting the monopoly power of incumbent banks stemming from their proprietary data. A forward-looking policy approach will be essential to ensure that the benefits of AI adoption are widely shared and that innovation continues to enhance, rather than erode, equitable economic growth.
| 2023-01-01T00:00:00 |
https://www.brookings.edu/articles/the-effects-of-ai-on-firms-and-workers/
|
[
{
"date": "2023/01/01",
"position": 7,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 7,
"query": "AI workers"
},
{
"date": "2025/07/01",
"position": 9,
"query": "artificial intelligence workers"
},
{
"date": "2025/07/01",
"position": 2,
"query": "AI labor market trends"
},
{
"date": "2025/07/01",
"position": 2,
"query": "AI workers"
},
{
"date": "2025/07/01",
"position": 6,
"query": "ChatGPT employment impact"
},
{
"date": "2025/07/01",
"position": 6,
"query": "artificial intelligence employment"
},
{
"date": "2025/07/01",
"position": 6,
"query": "artificial intelligence workers"
},
{
"date": "2025/07/01",
"position": 75,
"query": "future of work AI"
},
{
"date": "2025/07/01",
"position": 4,
"query": "machine learning workforce"
}
] |
|
Rise of the AI Workforce - How AI Workers will Change Business
|
How AI Workers will Change Business
|
https://www.qualified.com
|
[] |
The AI Workforce is transforming B2B as we know it. AI Workers are tackling roles laden with manual tasks to make workers and businesses more efficient.
|
The AI Era is bringing so much rapid change to the business world that at times it can feel daunting.
In less than two years, we have watched every aspect of work–our technology, our insights, and our processes–shift right before our eyes.
But rapid technology innovation is nothing new. To understand how we got here, we must look back at the different tech revolutions that have shaped the industry.
| 2023-01-01T00:00:00 |
https://www.qualified.com/rise-of-the-ai-workforce
|
[
{
"date": "2023/01/01",
"position": 8,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 9,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 8,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 8,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 8,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 9,
"query": "AI workers"
},
{
"date": "2023/10/01",
"position": 9,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 8,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 9,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 8,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 9,
"query": "AI workers"
},
{
"date": "2024/05/01",
"position": 8,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 8,
"query": "AI workers"
},
{
"date": "2024/09/04",
"position": 2,
"query": "AI workers"
},
{
"date": "2024/11/01",
"position": 9,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 8,
"query": "AI workers"
},
{
"date": "2025/02/01",
"position": 21,
"query": "AI workers"
},
{
"date": "2025/05/01",
"position": 21,
"query": "AI workers"
}
] |
|
AI Worker
|
ROBOTIS
|
https://ai.robotis.com
|
[] |
Physical AI-based Imitation Learning. Learn from human demonstrations and adapt to environmental changes through real-world interaction and intelligence.
|
Overview of the ROBOTIS Physical AI Lineup
Progressing toward advanced Physical AI through a scalable research lineup
The ROBOTIS Physical AI Lineup consists of three scalable levels of research-focused robots:
Level 3 (Enterprise): AI Worker : Semi-humanoid robot systems
: Semi-humanoid robot systems Level 2 (Middle): OMY : Advanced AI Manipulators
: Advanced AI Manipulators Level 1 (Entry): OMX: Cost-effective AI Manipulators [Coming Soon]
Each level supports a progressive research journey in Physical AI. It begins with basic motion learning and continues through full-body imitation to autonomous operation.
Lineup Breakdown
Full-body semi-humanoid platform (19 DOF ~ 25 DOF robot body)
Supports bimanual manipulation
Designed for imitation learning and autonomous policy training
Compatible with ROS 2 and Physical AI Tools
Collaborative robot style arms (6 DOF robot arm + gripper)
Gravity compensation, self-collision detection
Suitable for advanced control
Compatible with ROS 2 and Physical AI Tools
3. OMX Series (Entry Level) [Coming Soon]
Affordable, lightweight AI manipulators (5 DOF robot arm + gripper)
Ideal for educational and basic RL/IL experiments
Compatible with ROS 2 and Physical AI Tools
Our Vision for Physical AI
At ROBOTIS, our vision for Physical AI is to solve real-world industrial and societal problems that traditional, rule-based systems cannot. We believe that true intelligence emerges when robots learn from humans, adapt to dynamic environments, and perform safely and autonomously in the physical world. Through our scalable lineup from entry-level manipulators to full-body robots,
we aim to:
Lower the barriers to real-world AI research Accelerate the development of intelligent machines that move, sense, and learn like humans Empower researchers to build robots that are not just smart in code, but capable in the real world
By embedding intelligence into physical systems, we take a step closer to a future where robots collaborate with people, extend human capabilities, and bring freedom from repetitive or dangerous labor.
What is Physical AI?
Physical AI refers to artificial intelligence that learns and acts through real-world physical interaction using robotic bodies.
Unlike traditional AI, which operates purely in simulation or digital environments, Physical AI:
Receives feedback through motion, contact, and force
Learns by interacting with the environment in real time
Uses robotic hardware to sense, move, and adapt
This approach enables learning that is grounded in reality — shaped by friction, gravity, uncertainty, and the complexity of the physical world .
Physical AI allows us to:
Train robots to perform real-world tasks with precision
Collect meaningful demonstrations through human guidance (teleoperation, VR)
Deploy policies that bridge simulation and reality
By embedding intelligence into physical systems, we open the door to AI that can not only understand the world, but also act in it safely and effectively.
| 2023-01-01T00:00:00 |
https://ai.robotis.com/
|
[
{
"date": "2023/01/01",
"position": 20,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 20,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 21,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 21,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 22,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 16,
"query": "AI workers"
},
{
"date": "2023/10/01",
"position": 29,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 22,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 16,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 20,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 17,
"query": "AI workers"
},
{
"date": "2024/05/01",
"position": 21,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 21,
"query": "AI workers"
},
{
"date": "2024/11/01",
"position": 16,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 20,
"query": "AI workers"
}
] |
|
What's an AI Worker? | SS&C Blue Prism
|
What’s an AI Worker?
|
https://www.blueprism.com
|
[] |
How do AI workers work? AI (co)workers are software programs that collect and analyze data using machine learning (ML) algorithms to perform tasks.
|
Digital workers aren’t a new concept in the automation sphere. They’ve worked for organizations and alongside humans for years, acting as automation software robots that can enact tasks with accuracy and without breaks. But now, with artificial intelligence (AI) taking on new life through generative AI, predictive AI and other emerging technologies, digital workers are stepping into a new era: The era of the AI coworker. In this guide, we explore: What is an AI (co)worker?
How do AI workers work?
What’s the difference between AI and digital workers?
The benefits of having an AI coworker
What Is an AI Coworker?
An AI coworker, also called an AI agent, is a highly skilled digital worker infused with cognitive intelligence. They’re smarter, meaning they can expand the work they do – moving from routine, transactional tasks to performing complex, creative, decision-making activities with ease. Since AI coworkers are a relatively new concept, the terms differ between vendors and analysts. The names you might see for these AI-powered automating machines include: AI workers
AI coworkers
AI digital workers
Intelligent digital workers
AI agents
AI digital twins
Enterprise agent
Digital colleague
Agentic coworker
Virtual coworker Agentic AI is the class of AI systems that deploys your AI workers to perform tasks, make decisions, learn, think and interact with processes; it’s also the interface with the human worker.
How do AI workers work? AI (co)workers are software programs that collect and analyze data using machine learning (ML) algorithms to perform tasks. They can make decisions based on inputs, communicate using natural language processing (NLP), respond and adapt to changes in their environment, and react based on predefined desired outcomes. In other words, you tell your AI worker what you need done, give them the resources and data to see what’s currently happening in your business processes, and the AI worker acts, reacts and makes a decision based on that information. These developing AI solutions aren’t here to take human jobs – they’re here to take over the error-prone, time-consuming tasks so your people can focus on creative and strategic activities. They augment human work so people don’t have to do the work they don’t want to.
What’s the difference between AI coworkers and digital workers/bots? Historically, digital workers and robotic process automation (RPA) software bots have been limited in what they can do. But now with AI, those capabilities are expanding. While a digital workforce can handle routine tasks to streamline processes, an AI workforce can take that further with its deep learning and cognitive abilities. Digital workers mimic human actions based on step-by-step instructions and interact with systems and applications like a human would. Meanwhile, AI workers can handle complex activities and make decisions.
A real-world example Our customer Danica Pension implemented AI workers into their organization, giving a digital colleague to 80% of their employees. They’re on a journey powered by AI to grow their digital workforce further with ML and generative AI. So far, they’ve seen their success reflected in their impressive +70 net promoter score (NPS), and their SS&C Blue Prism digital workforce gives nearly 500,000 hours back to the business each year. Read Danica Pension’s entire success story to find out more.
Benefits of Having an AI Coworker
Unlike humans, AI workers aren’t constrained by experience or niche skills. And unlike your basic RPA bot, AI workers aren’t limited to one technology focused on routine functions such as data collection or task execution. AI coworkers are: Adaptable : They can learn, develop and act, working off human prompts to achieve their objectives.
: They can learn, develop and act, working off human prompts to achieve their objectives. Skilled: They comprise multiple technologies with the skills and functions needed to get work done, providing enterprise AI-level solutions to help your organization grow.
They comprise multiple technologies with the skills and functions needed to get work done, providing enterprise AI-level solutions to help your organization grow. Efficient: They work efficiently and without errors to execute complex processes such as responding to customer inquiries.
They work efficiently and without errors to execute complex processes such as responding to customer inquiries. Compliant: With built-in security, governance and guardrails, they can provide full auditability of all actions performed within a business process.
With built-in security, governance and guardrails, they can provide full auditability of all actions performed within a business process. Secure: AI workers work autonomously only when instructed to do so; they won’t make decisions outside of the guardrails you put in place without first consulting their human counterpart for the go-ahead.
AI workers work autonomously only when instructed to do so; they won’t make decisions outside of the guardrails you put in place without first consulting their human counterpart for the go-ahead. Fast: They execute cognitive work autonomously and across the enterprise.
They execute cognitive work autonomously and across the enterprise. Perceptive: They can perceive and process data as it happens through sensors and data inputs, evaluating their operating environment and adapting accordingly.
They can perceive and process data as it happens through sensors and data inputs, evaluating their operating environment and adapting accordingly. Consistent : By storing plans, actions and interactions, AI workers can maintain consistency across their work, informing and improving their performance as they go.
: By storing plans, actions and interactions, AI workers can maintain consistency across their work, informing and improving their performance as they go. Intelligent: They learn from their experiences, increasing their accuracy and effectiveness over time.
How Do I Implement a Trusted AI Solution?
The average workplace is full of multiple entities, each needing to be sourced, managed, maintained and trained; keeping up with all that work can be exhausting. The SS&C | Blue Prism® Enterprise AI automation platform offers AI coworkers who thrive in your ecosystem. These AI coworkers work together and with your people to ensure the best resources, insights, skills, etc., are used to accomplish your business goals. And now, with process orchestration, organizations can get the maximum value from every resource, be that human or virtual. Business process management (BPM) orchestrates work end-to-end, ensuring everything is done correctly, on time and in the most efficient way possible.
AI coworker best practices Here are some of the practices you should consider when implementing a safe, secure AI solution: Responsible AI: Ensure your AI has transparency and auditability of all of its interactions and activities. Define the scope of your AI workers with guardrails to keep them operating within safe parameters that align with your business values and standards. Keep your AI systems up to date to ensure compliance and reliability.
Ensure your AI has transparency and auditability of all of its interactions and activities. Define the scope of your AI workers with guardrails to keep them operating within safe parameters that align with your business values and standards. Keep your AI systems up to date to ensure compliance and reliability. Security: Keep sensitive data protected by implementing robust data governance frameworks. AI workers can help with this by removing sensitive information from their inputs automatically. Data access should also be restricted so only essential information is available.
Keep sensitive data protected by implementing robust data governance frameworks. AI workers can help with this by removing sensitive information from their inputs automatically. Data access should also be restricted so only essential information is available. Data privacy: When implementing AI workers, security is crucial. To protect your data, set up advanced encryption, secure access points and conduct regular security assessments. Your stored data should require multi-factor authentication and robust cybersecurity infrastructure to protect against threats.
What’s In the Future for AI Workers?
| 2023-01-01T00:00:00 |
https://www.blueprism.com/guides/ai/ai-worker/
|
[
{
"date": "2023/01/01",
"position": 21,
"query": "AI workers"
},
{
"date": "2023/01/01",
"position": 68,
"query": "artificial intelligence workers"
},
{
"date": "2023/02/01",
"position": 67,
"query": "artificial intelligence workers"
},
{
"date": "2023/03/01",
"position": 21,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 22,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 70,
"query": "artificial intelligence workers"
},
{
"date": "2023/05/01",
"position": 22,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 21,
"query": "AI workers"
},
{
"date": "2023/08/01",
"position": 63,
"query": "artificial intelligence workers"
},
{
"date": "2023/09/01",
"position": 20,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 70,
"query": "artificial intelligence workers"
},
{
"date": "2023/10/01",
"position": 8,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 21,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 61,
"query": "artificial intelligence workers"
},
{
"date": "2024/01/01",
"position": 20,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 65,
"query": "artificial intelligence workers"
},
{
"date": "2024/02/01",
"position": 22,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 20,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 38,
"query": "artificial intelligence workers"
},
{
"date": "2024/05/01",
"position": 22,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 7,
"query": "AI workers"
},
{
"date": "2024/07/01",
"position": 66,
"query": "artificial intelligence workers"
},
{
"date": "2024/11/01",
"position": 20,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 22,
"query": "AI workers"
},
{
"date": "2025/02/01",
"position": 25,
"query": "AI workers"
},
{
"date": "2025/05/01",
"position": 25,
"query": "AI workers"
}
] |
|
Workers and AI - Brookings Institution
|
Workers and AI
|
https://www.brookings.edu
|
[
"Molly Kinder",
"Xavier De Souza Briggs",
"Mark Muro",
"Sifan Liu"
] |
Recent breakthroughs in generative AI have raised concerns about the technology's impact on jobs and livelihoods. Brookings Metro has embarked on a new, ...
|
Recent breakthroughs in generative AI have raised concerns about the technology’s impact on jobs and livelihoods. Brookings Metro has embarked on a new, multi-year effort focused on raising awareness and shaping societal responses. The project involves three main components: a storytelling series that centers workers’ experiences and perspectives; innovative quantitative and qualitive analysis to understand the specific risks and opportunities of AI and work; and cross-sector convenings to develop policy solutions and best practices that ensure equitable benefits from AI advancements and mitigate potential harms.
| 2023-01-01T00:00:00 |
https://www.brookings.edu/collection/workers-and-ai/
|
[
{
"date": "2023/01/01",
"position": 22,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 22,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 25,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 26,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 24,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 24,
"query": "AI workers"
},
{
"date": "2023/10/01",
"position": 56,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 28,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 24,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 24,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 22,
"query": "AI workers"
},
{
"date": "2024/04/12",
"position": 31,
"query": "AI employment"
},
{
"date": "2024/04/12",
"position": 3,
"query": "AI workers"
},
{
"date": "2024/04/12",
"position": 10,
"query": "artificial intelligence workers"
},
{
"date": "2024/05/01",
"position": 28,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 24,
"query": "AI workers"
},
{
"date": "2024/11/01",
"position": 24,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 27,
"query": "AI workers"
},
{
"date": "2025/02/01",
"position": 16,
"query": "AI workers"
},
{
"date": "2025/05/01",
"position": 16,
"query": "AI workers"
}
] |
|
AI Worker your new Workforce - AI Worker
|
AI Worker your new Workforce
|
https://www.aiworker.digital
|
[] |
AI workers generate personalized marketing campaigns, automate ad placements, and optimize SEO strategies. They also assist in copywriting, video editing, and ...
|
1. Cost Savings
AI workers significantly reduce operational costs by automating tasks that would otherwise require expensive human labor. Companies can save up to 70% compared to traditional hiring.
2. Efficiency & Scalability
AI-driven solutions streamline workflows, allowing businesses to scale operations without increasing overhead. AI workers can handle repetitive tasks, freeing up human employees for strategic initiatives.
3. Hassle-Free Hiring & Compliance
Platforms offering AI-powered workforce solutions often manage contracts, payroll, and compliance, eliminating administrative burdens for businesses.
4. Access to Top-Tier Talent
Some AI workforce solutions combine AI automation with human expertise, ensuring businesses get high-quality results without the complexities of traditional hiring.
5. Seamless Integration
AI workers integrate smoothly into existing workflows, tools, and business processes, making adoption easy and minimizing disruptions.
Would you like me to refine this further or explore additional AI workforce benefits? 🚀
| 2023-01-01T00:00:00 |
https://www.aiworker.digital/
|
[
{
"date": "2023/01/01",
"position": 32,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 32,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 43,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 43,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 42,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 37,
"query": "AI workers"
},
{
"date": "2023/10/01",
"position": 35,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 44,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 37,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 43,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 37,
"query": "AI workers"
},
{
"date": "2024/05/01",
"position": 44,
"query": "AI workers"
},
{
"date": "2024/11/01",
"position": 38,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 42,
"query": "AI workers"
},
{
"date": "2025/02/01",
"position": 41,
"query": "AI workers"
},
{
"date": "2025/05/01",
"position": 41,
"query": "AI workers"
}
] |
|
The AI Workforce is Here: The Rise of a New Labor Market - NFX
|
The AI Workforce is Here: The Rise of a New Labor Market
|
https://www.nfx.com
|
[] |
The rise of AI workers is creating a fusion of the software and labor market. This is going to create massive opportunities for Founders.
|
With traditional B2B SaaS, we augmented human work and services with software. Now, the software itself is doing the whole job.
AI is forcing a reversal of the SaaS acronym. From Software-as-a-Service to Service-as-a-Software.
The big picture: the rise of AI workers is creating a fusion of the software and labor market. This is going to create massive opportunities for Founders.
Labor and Software Are Becoming One Market
SaaS companies have historically brought analog processes into the digital world. They were aimed at making certain aspects of existing job descriptions easier to manage.
But SaaS could never run itself. It always required a company to maintain a workforce to operate that software.
For example, you could purchase a SaaS sales tool but you still had to hire, and train a salesperson to do the work.
Across the whole economy, this means the labor market, and the software markets have been separate – and within a company, the hiring budget has always been orders of magnitude larger than the software budget.
If you run a very rough calculation, US businesses spend upwards of $5 trillion on knowledge workforces. By comparison, companies spend about $230 billion on B2B SaaS.
Now, software can both organize and execute tasks. Labor and software are fusing into one massive market.
This opportunity, however, is not just about market expansion. It’s also about margin expansion.
In this labor transition, we expect the historical margin gap between service businesses (below 30%) and SaaS businesses (above 80%) to shrink as AI services replace human-centric services enabled by SaaS tools. Service margins will become software margins.
Market and margin expansions combined are creating opportunities for new tech companies to emerge in areas not yet touched by traditional software.
Note that these estimates only tackle knowledge work. We expect this concept to expand into more manual tasks as well. This will happen as new bridges between Generative AI and the physical world are created in the future. Construction and manufacturing, large sections of the labor market, are likely the first to witness these changes. (We have briefly covered the emergence of this in construction here).
We do expect some roles to disappear as this fusion accelerates. But AI is likely to create a form of Jevons paradox in the long run – where increased efficiency leads to a short term reduction in a resource, but a long-term surge in demand that creates more resource use.
Applied here, that means we expect to see more demand for these types of services in the future, providing more job opportunities. To aid with that, AI also provides the opportunity for rapid workforce re-skilling, allowing people to shift careers and align themselves with those opportunities.
Labor is going to be “baked in” to any software an enterprise buys. Meet your new AI colleagues.
Two Approaches to “AI Workforce” Companies
So far, we’re seeing two dominant approaches to building companies in this space.
1. Sell “AI Colleagues” (Internal)
The first approach is to sell into an existing job description.
A good example of this would be Devin, Cognition Lab’s “AI software engineer.”
First, Devin works across the whole software engineer’s workflow. It encounters issues and finds solutions, and tells you what it’s doing along the way. It works like human labor – down to the communication styles.
Other examples in this vein would be 11x or Artisan, companies creating “digital SDRs.” In this case, Alice and Ava are able to book 2-3 prospective client meetings per week, work 24/7, and work across the whole sales technology stack. In the legal space, our portfolio company EvenUp has replaced the demand letter writing process with AI automation.
Finally, a company on the leading edge of this developing space would be NVIDIA and Hippocratic.ai’s AI-powered healthcare agents. These AI “nurses” conduct patient interviews, perform health-risk assessments, and perform post-operative follow ups.
In this case, AI falls short of providing the whole spectrum of care provided by a human nurse, but may lessen the burden on human nurses (currently in the midst of a prolonged labor shortage).
Here we see a developing spectrum of “AI colleagues.” They are not only adept at basic job functions, but also posses a range of “soft skills” that make them more like colleagues than software.
2. Sell “AI Vendors/ Services” (External)
The second approach is to automate an entire workflow that would typically encompass many different jobs. This concept will basically replace the work provided by an entire service business. E.g. a full stack AI law firm, an AI broker, etc.
This comes in several flavors.
The first flavor, and what we see a lot of right now, is a re-imagination of the existing BPO.
This is likely to happen in fields like: customer service, Sales, marketing, finance & accounting, supply chain management (logistics & procurement), legal services, data collection/entry/analysis, human resources, translation & localization, software development, quality assurance, cybersecurity, or construction takeoff and estimation.
We’re already seeing this happen. Our portfolio company Smith.ai has developed AI-powered customer service agents specifically for SMBs. Their platform can respond to customer calls and messages 24/7, with the accuracy usually required by hiring large teams of human specialists.
The second flavor is the creation of a new type of “firm” that couldn’t exist under one roof without AI.
The key to this playbook is to seek fragmented processes that require multiple stakeholders. Architecture or renovation services are other great examples of this because of equal ratios of analog and digital tasks.
This category of business is capable of encompassing both the “services” market and the “labor/employee” market. In both cases, you deliver human-quality labor with software margins.
An added benefit is that this trend also creates an opportunity to disrupt SaaS incumbents. First, certain SaaS tools will become superfluous as AI service providers build the tools they need internally. Secondly, there may be business model conflicts. The pay-per-seat models increases revenues provided headcount keeps increasing – and initially, AI workforces will decrease that headcount.
Overall, SaaS spending may go down, disrupt SaaS incumbents, and create more space for startups.
Which is why this opportunity is truly big. Even bigger than enterprise software.
Where Will AI Workers First Dominate?
The biggest opportunities will exist where the unit economics of hiring AI are 100x better than the unit economics of hiring or subcontracting a person to do the job. Under those conditions, for AI workers will thrive.
That is usually achieved via a combination of AI’s cost-cutting capabilities (automating repetitive work etc), AND AI’s added value (driving greater revenues via enhanced personalization).
Here’s how we look for spaces with those characteristics:
First, we ask: where does AI excel where human labor may be weak?
There are several key factors here:
Large amount of process is automatable. This includes simple, repetitive, high volume tasks. This likely does not include complex, multi-step, bespoke tasks, initially.
Human labor is particularly expensive.
Hiring is difficult and there are poor labor market dynamics (including worker shortages and attrition)
Long “time to ROI” for human workers (e.g. significant onboarding/ training required)
High level of tool fragmentation, which provides an opportunity to consolidate tools into one top layer.
High fault tolerance: i.e. the stakes are not life or death.
Fields with large amounts of training data – preferably proprietary
An example of areas where AI excels here would be legal document inquiry, account payable positions, social media content moderation, data entry, or basic customer service.
Second, we ask: Where does AI add additional value that may go beyond that of a human worker?
Personalization will drive significant customer value
Speed is a key factor in service quality, and 24/7 service matters
Heterogeneity is a hindrance to high quality service
To illustrate both, let’s take education for example. There are cost advantages to AI tutors over human teachers (about 80x cheaper, if you compare Khan Academy’s AI tutor to the salary of a public school teacher, for example).
While it is unlikely that AI will replace public school teachers in our lifetime, we will likely see AI play an increasingly large role in education in other ways. The more transformational application of this technology is in the additional market for customized education that these AI tutors create.
AI tutors are available 24/7. In theory, they should be able to instantly tailor teaching styles to student needs. It’s instant personalized learning that can happen outside of a traditional classroom.
This is an area where we see AI-driven industry expansion, rather than AI-driven automation and replacement.
Who Will Be the First to Adopt AI Workers?
We expect the first adopters to be operations-heavy companies or SMBs. These AI companies should open additional pathways to scale for these businesses, which have traditionally scaled linearly with labor, and are constrained by their ability to add new employees.
Now they’ll be able to increase their workforce at the click of a button. And equally decrease it, accessing infinite scale and flexibility.
For these businesses AI provides infinite leverage, at lower costs, and better outcomes. For these types of businesses, that’s transformational.
AI works 24/7. It doesn’t have bad days. And there are cases where an AI work product may naturally be better than that of a human worker.
From there we see a few other contenders:
Fast growing businesses, such as tech startups, that are struggling to hire for specific job functions at a sufficient pace.
Private-equity-backed rollups hyper focused on operational efficiency (who may otherwise resort to layoffs)
Solopreneurs who face a variety of challenges in areas where they don’t have experience and it does not make sense to hire full-time human employees, which explains why they already spend billions per year on freelancers.
Large incumbents with high turnover, low-margin businesses driven by big human workforces. A strategy could be to target industries with the lowest ratio of revenue per employee. Or businesses in industries that have traditionally scaled revenue linearly with labor.
Soon, huge businesses will be run by just three (or perhaps fewer) people. These AI colleagues/vendors are a large part of this transition.
Why Startups Have a Head Start
In the AI era, there’s always a question of who reaps greater rewards: startups or incumbents? There are ample opportunities for startups here for several reasons:
Advantage 1: The Specialization Advantage
Foundational models or large incumbents might be in a good position to automate most requests. But it is likely they will struggle to automate that final 10-20 percent of tasks.
Look at the performance of Devin compared to coding functions in ChatGPT or other LLMs:
Specialized AI workers will likely out-perform AI incumbents at first because they are performing very specific knowledge work where perfection matters. Code that’s “close enough” isn’t a good enough proposition for a software company.
This is where specialized startups, with niche data, and a human in the loop will vastly outperform unfocused incumbents, and gain market share in the opening innings of this transition.
Advantage 2: Business Model Conflicts Create Opportunities
Eventually, every company and service provider will need to adopt AI to remain competitive. But this may not be the case right out of the gate. In classic Innovator’s Dilemma fashion, incumbent service providers in certain industries will stumble with the adoption of a new technology. This presents large opportunities for startups.
Take legal services as an example. A white-glove law firm that works on a billable hours model may initially resist taking on AI if it reduces the amount of hours per client. Since keeping the number of clients constant will reduce their overall revenue.
In this context, imagine a full stack AI Law Firm (startup) comes along that can provide compatible services to the white-glove firm, at a fraction of the cost, across far more cases and clients. They may begin to steal market share away from the white glove law firm, despite not having the same brand recognition.
These business model conflicts present rare moments of network restructuring. This advantage window will close as the previous generation adapts, but startups that gain preferential attachment will be better positioned to fight for market share long-term.
Massive businesses can be built by capitalizing on this fast.
Advantage 3: Faster Paths to Enterprise Selling
Every company is considering adopting AI right now, or is at least being pressured to do so. This means that the willingness to work with startups is higher than it has been in the past.
Of course, some companies will choose to build these automations themselves. But others may choose to work with a startup early on.
Even if an incumbent manages to automate one aspect of their operations in house, it’s unlikely they will do that for every arm of the business.
While incumbents focus on rolling out these services to their customers, there’s room for startups to sell directly into enterprises/ incumbents themselves.
The Near Future: Software with a Soul
Initially, many of these Service-as-a-Software companies will just look like automation. You might automate away 99 percent of the daily “admin” tasks.
For labor and software to truly become one market, some companies will need to go beyond this. The companies that will complete the fusion process will have a degree of “humanness.”
This is because truly good service isn’t just efficient. It’s delightful.
Existing automation excels at relatively simple tasks: ordering food, sending cash. Removing friction is hugely effective here. But if something is complex, or disordered…you still end up on the phone with a representative.
For software to truly replace services, there has to be relatability, room for the disorder inherent in human use, mistakes, and patient understanding. Removal of friction isn’t sufficient. It has to look, and feel, like interacting with a person.
Put differently, this software has to have, in some ways, soul. That soul could exist in different ways, from a magical and intuitive user interface to a thoughtful personalized “personality.”
This next wave of AI automation will understand and adapt to the user, the same way a great customer service agent, or sales agent, or service provider does.
We’re already starting to see AI develop these emotional intelligence skills, like Hume.AI, based on a “empathic large language model” that intakes subtleties of human communication, like tone, voice modulation, etc.
As the tasks we look to automate become more complex, this “soul” becomes more important. This is how AI will be able to truly become useful in sectors that require a more hands on approach, like education, therapy, or healthcare.
In the long term, software with a soul may endure far beyond software that seeks to automate repetitive tasks.
It’s the final step of the true fusion of software and labor. It’s not here quite yet, but it is coming.
If you’re building in this space, reach out to us.
Thanks to Brandon Nydick for notes on this essay.
| 2024-04-11T00:00:00 |
2024/04/11
|
https://www.nfx.com/post/ai-workforce-is-here
|
[
{
"date": "2023/01/01",
"position": 35,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 34,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 23,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 23,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 23,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 22,
"query": "AI workers"
},
{
"date": "2023/10/01",
"position": 58,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 23,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 22,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 23,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 23,
"query": "AI workers"
},
{
"date": "2024/04/11",
"position": 1,
"query": "AI workers"
},
{
"date": "2024/04/11",
"position": 4,
"query": "AI workforce transformation"
},
{
"date": "2024/05/01",
"position": 23,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 23,
"query": "AI workers"
},
{
"date": "2024/11/01",
"position": 22,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 23,
"query": "AI workers"
},
{
"date": "2025/02/01",
"position": 34,
"query": "AI workers"
},
{
"date": "2025/05/01",
"position": 34,
"query": "AI workers"
}
] |
AI Sales Agent for Businesses - Automate Follow-Up & Book More ...
|
Automate Follow-Up & Book More Calls
|
https://www.gohighlevel.com
|
[] |
AI Employee is your personal AI-powered business assistant, designed to handle tasks like content creation, customer engagement, funnel building, and more.
|
Don’t just keep up with marketing technology. Get ahead of the curve with AI Employee. No matter your business, HighLevel’s cutting-edge AI automation tools are designed to meet your specific needs and help you achieve your goals.
| 2023-01-01T00:00:00 |
https://www.gohighlevel.com/ai
|
[
{
"date": "2023/01/01",
"position": 36,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 35,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 36,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 37,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 37,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 36,
"query": "AI workers"
},
{
"date": "2023/10/01",
"position": 65,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 37,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 36,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 36,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 36,
"query": "AI workers"
},
{
"date": "2024/05/01",
"position": 37,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 41,
"query": "AI workers"
},
{
"date": "2024/11/01",
"position": 36,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 37,
"query": "AI workers"
}
] |
|
What Workplaces Miss When They Panic About AI Tools | Built In
|
What Workplaces Miss When They Panic About AI Tools
|
https://builtin.com
|
[] |
Some employees now use AI to complete workplace training, revealing not laziness but a mismatch in learning design. When integrated ...
|
Some employees now use AI to complete workplace training, revealing not laziness but a mismatch in learning design. When integrated intentionally, AI can boost engagement, critical thinking and equity in learning — turning compliance tasks into opportunities for collaboration and growth.
Some employees now use AI to complete workplace training, revealing not laziness but a mismatch in learning design. When integrated intentionally, AI can boost engagement, critical thinking and equity in learning — turning compliance tasks into opportunities for collaboration and growth. more
A few months ago, our team at Moodle ran a survey exploring how people are using AI at work. The headline that grabbed attention? Some employees (20 percent of those surveyed) were using AI to complete mandatory workplace training. Depending on where you sit, that sounds either wildly efficient or slightly alarming.
Plenty of outlets chose the second. And, although I agree with the concern, I also notice the underlying curiosity, willingness to experiment and appetite to try new tools that this behavior demonstrates.
Yes, there are pitfalls when AI is introduced into daily workflows carelessly — especially in areas like training, communication and decision-making. But if we approach AI with the right mix of transparency, autonomy and design, it becomes a catalyst for learning, not a threat to it.
More on AI Use in the WorkplaceIs ‘Shadow AI’ Putting Your Business at Risk?
The Trouble With Traditional Training
Training is a staple of professional development, but its delivery hasn’t evolved much. In our research, 80 percent of employees had taken part in mandatory training, but just 44 percent fully engaged. Some muted the videos. Others sped through. And some had AI assist them in answering questions.
These behaviors may read like resistance, but they actually highlight a failure of design. People aren’t avoiding learning. They’re avoiding systems that don’t respect their time, knowledge level or preferred way of working.
Let’s Talk About AI and Training
Rather than seeing AI as a cheat code, we should be asking why employees are reaching for these tools in the first place. What does it tell us about how they want to learn?
If workers are using AI to summarize dense training modules or find quick answers to compliance quizzes, that’s not laziness — it’s a signal that our current systems aren’t matching how people engage, retain or apply information today.
This is a design problem. And we can solve it.
What if training programs didn’t just allow AI use, but taught people how to use it well?
Imagine a workplace module that includes AI-assisted research, but also asks the learner to critique the result. Or a session that uses an AI-generated scenario as a starting point for team discussion: What’s missing from this output? How would you improve it? What assumptions is the AI making?
You could build in explainability moments. Have learners pause a session to explore how an AI tool reached its conclusion or flag when the model might be confidently wrong. These are small shifts, but they change the role of the employee from passive consumer to critical evaluator.
In peer-based exercises, teams might generate AI-assisted summaries of a module, then compare and refine their drafts together. Or they could use generative AI to draft a new compliance policy and then critique each other’s versions for tone, accuracy and risk.
Another option: give learners AI-generated FAQs and ask them to identify which responses are helpful, misleading or lack context. These kinds of activities don’t just build technical discernment. They encourage reflection, spark conversation and raise assumptions that might otherwise go unspoken.
Transparency is still crucial. People should always know when AI is being used and where their data goes. But just as important is making space for reflection and response. That’s what builds real literacy.
Human Connection Is Still the Killer App
AI can generate content and automate tasks. But it can’t replace what makes learning stick: relevance, reflection and relationships.
The best workplace learning environments, AI-powered or not, are the ones where people feel seen and supported. That means creating space for conversation: between team members, between the learner and the content, and yes, even between humans and machines.
It also means designing experiences that invite collaboration, not just between colleagues, but across modes of thinking. One person might use AI to kickstart an idea, while another builds on it, questions it or adds lived experience the model could never access. That interplay is where true learning happens.
The real question isn’t whether employees should use AI in training. It’s how we can help them use it more critically and effectively.
Designing for Digital Fluency — With an Equity Lens
Supporting AI literacy in the workplace isn’t just about offering tool tips or best practices. It means helping people build real fluency: understanding how AI systems work, recognizing where they fall short and learning to evaluate their output with a healthy mix of skepticism, curiosity and an equitable mindset.
3 Ways to Ensure Equity in AI Programs Bias audits.
Content checks.
Inclusive feedback loops.
Bias in AI isn’t abstract. Algorithms frequently reflect historical and systemic inequities, from facial recognition that misidentifies darker-skinned individuals to language models that echo stereotype-laden data. Teaching people to use AI responsibly means training them to spot those biases. That could look like any of the following.
Bias Audits
Ask learners to test AI-generated content for stereotype-driven assumptions, possibly by feeding the model profiles from diverse backgrounds and spotting inconsistent responses.
Content Checks
Use AI tools to scan training materials for exclusive language or lack of representation and then workshop revisions as a group.
Inclusive Feedback Loops
After sharing AI outputs, invite colleagues with different perspectives to reflect on whether the content feels fair, complete and culturally aware.
Embedding these activities into learning not only builds digital and critical fluency, it also fosters a culture of inclusion and accountability. Those who learn to question an AI output are better prepared to question their own assumptions and to advocate for equity in technology and beyond.
More on TrainingWhy Education at All Levels Will Create the Foundation for Data Literacy
Moving From Experimentation to Intention
The fact that people are already using AI to navigate workplace learning isn’t a failure. It’s a signal that they’re curious, resourceful and ready to engage on their own terms. As we’ve seen, this opens up enormous potential: not just to improve training outcomes, but to build the kinds of critical, inclusive and reflective habits that modern workplaces need.
Now it’s on us to move from experimentation to intention. We need to design AI-integrated learning that’s transparent, context-rich and grounded in digital fluency. Let’s stop designing for compliance alone and start designing for compliance learning that drives curiosity, collaboration and smarter conversations between AI and humans.
| 2023-01-01T00:00:00 |
https://builtin.com/articles/improved-workplace-training-ai
|
[
{
"date": "2023/01/01",
"position": 42,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 40,
"query": "AI workers"
}
] |
|
11X – Digital workers, Human results
|
11X – Digital workers, Human results
|
https://www.11x.ai
|
[] |
For Sales, RevOps, and Go-to-Market Leaders Transform your revenue team with digital AI workers that execute, learn, and optimize across every customer ...
|
"I was a skeptic, I don't believe AI can ever replicate the skills of a human, and 11x blew me away by doing just that"
| 2023-01-01T00:00:00 |
https://www.11x.ai/
|
[
{
"date": "2023/01/01",
"position": 44,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 42,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 53,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 46,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 47,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 40,
"query": "AI workers"
},
{
"date": "2023/10/01",
"position": 44,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 45,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 40,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 44,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 40,
"query": "AI workers"
},
{
"date": "2024/05/01",
"position": 45,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 55,
"query": "AI workers"
},
{
"date": "2024/11/01",
"position": 40,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 43,
"query": "AI workers"
},
{
"date": "2025/02/01",
"position": 36,
"query": "AI workers"
},
{
"date": "2025/05/01",
"position": 36,
"query": "AI workers"
}
] |
|
Despite Enthusiasm, Employees Underwhelmed About AI's Potential
|
Despite Enthusiasm, Employees Underwhelmed About AI’s Potential
|
https://www.planadviser.com
|
[
"Yasin Mohamud"
] |
Even with widespread eagerness about the potential for artificial intelligence to have a positive impact on workers' productivity, ...
|
Even with widespread eagerness about the potential for artificial intelligence to have a positive impact on workers’ productivity, most employees believe “they were overpromised on its potential,” according to a new report from cloud communications and IT company GoTo.
“The Pulse of Work in 2025: Trends, Truths, and the Practicality of AI”, completed in partnership with research firm Workplace Intelligence, found that 62% of workers believe there has been too much hype around AI. The report examined the findings of a survey of 2,500 global employees and IT leaders about AI use and sentiment.
Employees’ feelings about the “overhype” around AI is likely because they are not prepared for “making the most of what these tools have to offer,” according to the report. Most of the respondents (86%) admitted to not using AI tools to their full potential and not being very familiar with how they can deploy them in their daily tasks (82%).
Employees also said they estimate spending 2.6 hours per day (13 hours per week) on tasks that AI could do. This means that in the U.S. alone, businesses are potentially not taking advantage of more than $2.9 trillion annually in efficiency, according to the report.
Although many workers recognize AI’s value, they still feel underwhelmed by “the revolutionary change they were promised,” said Rich Veldran, GoTo’s CEO, in a statement.
“The solution is clear: companies must go beyond just providing access to AI by ensuring employees have both the right tools and the right education,” said Veldran in the statement, noting that in practice, this means teams should be equipped with effective training and clear guidelines.
Use and Misuse
According to the report, employees are already using AI for some tasks, just not the ones for which their managers believe they are using. Instead of using the tool as a time-saver, 54% of employees reported that they’ve used it for “sensitive tasks” or “high-stakes decision-making.”
These tasks include ones that require emotional intelligence (29%), tasks impacting safety (26%) and ethical or sensitive personnel actions (16%). When prompted if they regret using AI for these tasks, 77% of workers said they did not.
The survey also found mistrust of the tools among employees: 86% of workers said they are not confident in its accuracy and reliability, and 76% reported that AI often produces outputs that need to be revised by users.
Predictably, when it comes to who is at the forefront of AI use, smaller companies are already behind. At the smallest companies (50 employees or fewer), just 59% of workers use AI and 46% said they do not know how to use it to save time or improve their work, according to the report.
‘Proficiency Has Flatlined’
Although enterprises are investing in AI, Section Inc.—a company dedicated to AI transformation and upskilling—found that workforce proficiency “is still in neutral,” raising reservations about return on investment.
According to the report, since September 2024, employees’ general AI proficiency has “flatlined,” with only 10% of the workforce scoring as AI-proficient.
The report’s survey examined 5,013 knowledge workers across the U.S., U.K. and Canada, including individual contributors and C-suite executives, measuring workers’ knowledge, usage and skill with generative AI tools.
A key reason for the lack of proficiency in enterprise organizations is because there is a lack of “wide-spread deployment,” according to Greg Shove, Section’s CEO.
“Our research echoes what we hear from enterprise organizations: they’ve rolled out ChatGPT to leadership or a few groups and stopped there,” Shove said in a statement. “Without widespread deployment, AI vendors will start seeing churn, CEOs will get frustrated by lack of ROI and workers will be left to figure it out for themselves.”
| 2025-07-07T00:00:00 |
2025/07/07
|
https://www.planadviser.com/?p=111893
|
[
{
"date": "2023/01/01",
"position": 46,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 45,
"query": "AI workers"
}
] |
Build Powerful AI Agents With MindStudio
|
Build Powerful AI Agents With MindStudio
|
https://www.mindstudio.ai
|
[] |
AI-native workflow automation. MindStudio is ... Restrict employees to approved models and services to maintain compliance and security at every level.
|
Anyone can create AI Agents for their bespoke needs
Individuals who want to build custom AI-powered tools for their own workflows—gain productivity, efficiency, intelligence.
Professionals and Team Leaders who want to empower their team with AI power tools for their specific job function.
Operations, IT, and HR professionals who want to automate processes, and dramatically increase operational efficiency
| 2023-01-01T00:00:00 |
https://www.mindstudio.ai/
|
[
{
"date": "2023/01/01",
"position": 53,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 51,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 61,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 56,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 57,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 51,
"query": "AI workers"
},
{
"date": "2023/10/01",
"position": 69,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 54,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 51,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 56,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 51,
"query": "AI workers"
},
{
"date": "2024/05/01",
"position": 54,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 60,
"query": "AI workers"
},
{
"date": "2024/11/01",
"position": 51,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 54,
"query": "AI workers"
},
{
"date": "2025/02/01",
"position": 44,
"query": "AI workers"
},
{
"date": "2025/04/07",
"position": 66,
"query": "AI graphic design"
},
{
"date": "2025/05/01",
"position": 44,
"query": "AI workers"
}
] |
|
How Gen Z workers use AI at work when no one is looking
|
How Gen Z workers use AI at work when no one is looking
|
https://www.humanresourcesonline.net
|
[] |
AI can significantly enhance our ability to perform tasks more efficiently and easily. As digital natives, Gen Z workers are naturally savvier ...
|
Nearly a third (30%) of respondents said they have generated fake work using AI to appear more productive.
AI can significantly enhance our ability to perform tasks more efficiently and easily.
As digital natives, Gen Z workers are naturally savvier at using these tools. But how deeply is AI shaping their work lives?
The recent Gen Z and AI in the Workplace Report released by Resume Genius has surveyed 1,000 full-time Gen Z employees in the U.S. The results revealed that AI has become an everyday essential for many young workers, with some even testing boundaries of acceptable use.
*While the survey was conducted in the US, HRO believes the results remain relevant to our readership in Asia.
According to the report, the majority of Gen Z professionals surveyed said AI makes their job easier:
60% said AI helps them get their work done faster and with less effort.
56% said it improves the accuracy and quality of their work.
54% said it frees them up to focus on creative or strategic tasks.
42% said AI has opened up new career opportunities for them.
Therefore, Gen Z office workers have deeply integrated AI into their day-to-day workflow, such as:
74% use AI for brainstorming or generating creative ideas.
68% use it for writing or editing reports and emails.
62% turn to it for creating digital content or designing presentations.
61% use it to analyse large datasets for insights.
61% automate repetitive administrative tasks.
57% use it for competitive research or business intel.
56% use it to manage meetings and scheduling.
Beyond productivity, many Gen Z employees are increasingly turning to AI for help with interpersonal situations at work, including:
57% use AI to review or improve work before handing it to their manager, 22% do this often or always.
56% use AI for advice on how to communicate with managers or coworkers, 19% do this often or always.
55% use AI to clarify tone or meaning in messages, 23% do this often or always.
51% turn to AI for help navigating workplace conflicts or difficult conversations, 16% do this often or always.
Gen Z employees are also relying on AI to guide them in making significant career decisions, as follows:
56% use AI to write CVs and cover letters when applying for jobs.
53% use AI to help with career decisions, such as salary negotiation or getting a promotion.
50% use AI to better understand company policies or workplace rules.
While many Gen Z workers use AI responsibly, a significant number admit to engaging in questionable practices. These may include:
39% have used AI to automate tasks without their manager’s knowledge, 14% say they do this often or always.
31% have used AI in ways that may violate company policies, such as sharing internal data, 11% say they do this often or always.
30% have generated fake work using AI to appear more productive, 11% say they do this often or always.
The survey also revealed that 28% of Gen Z workers have passed off AI-generated work as their own without disclosure. Among those who did:
43% said their work was well received.
41% said they would do it again.
26% said they felt guilty about it.
13% said their work was poorly received.
9% said they were caught.
When analysed by gender, 40% of Gen Z men reported submitting AI-generated work without telling anyone, compared to 20% of women. Among those who presented AI-generated work as their own:
44% of men said they would do it again (vs. 37% of women).
24% of men said they felt guilty about it (vs. 28% of women).
Interestingly, not all Gen Z workers are thriving with AI on the job. The same tools boosting productivity are raise new concerns among them:
49% are concerned that AI could lead to unfair or biased decisions that affect them at work.
40% said AI is forcing them to learn new skills just to keep up with their work.
39% feel burned out by how often AI tools are updated.
38% said they need to use AI just to manage their workload.
37% said AI makes them feel replaceable.
23% said using AI at work has negatively affected their mental health.
Segmented by gender, Gen Z men tend to be more enthusiastic about AI’s potential. Meanwhile, Gen Z women are more likely to report emotional fatigue from the rise of AI.
48% of women said they are concerned that AI will lead to unfair biases in workplace decisions (vs. 50% of men).
41% of women said frequent AI updates are burning them out (vs. 35% of men).
22% said AI has negatively affected their mental health (vs. 26% of men).
When asked how they would respond if AI tools were banned at work, the results indicated a wide range of dependencies:
53% said it would have no effect because they don’t use AI.
52% said they would support a ban and prefer to work without AI.
51% said they would continue using AI after hours or on personal devices.
48% said they wouldn’t support a ban.
39% said they would need to find alternative ways to complete tasks.
34% said a ban would make them less efficient and slow them down.
33% said they would continue using AI at work on company devices, despite the ban.
18% said they wouldn’t be able to do their current job without AI and would need to quit or change roles.
"For many Gen Z office workers, AI acts as a digital co-pilot that helps them write, plan, and come up with ideas," said Geoffrey Scott, Senior Hiring Manager at Resume Genius. "The danger lies in when that co-pilot takes over and becomes the captain.”
"It’s clear that AI is becoming an everyday support system for many Gen Z professionals," added Eva Chan, Career Expert at Resume Genius.
"But it’s also becoming their go-to solution when they don’t know what to say or do and how to handle tough situations. The concern is when workers start outsourcing not just tasks, but their judgment, confidence, and even their voice. If we’re not careful, we could see a generation that struggles to make decisions without AI hand-holding.”
| 2023-01-01T00:00:00 |
https://www.humanresourcesonline.net/how-gen-z-workers-use-ai-at-work-when-no-one-is-looking
|
[
{
"date": "2023/01/01",
"position": 54,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 52,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 62,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 60,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 60,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 58,
"query": "AI workers"
},
{
"date": "2023/10/01",
"position": 25,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 57,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 57,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 57,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 59,
"query": "AI workers"
},
{
"date": "2024/05/01",
"position": 57,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 63,
"query": "AI workers"
},
{
"date": "2024/11/01",
"position": 57,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 57,
"query": "AI workers"
}
] |
|
CWRU joins national AI labor study backed by $1.6M grant
|
CWRU joins national AI labor study backed by $1.6M grant
|
https://thedaily.case.edu
|
[] |
Research aims to guide decision-makers on real-world effects of artificial intelligence on American workers. Case Western Reserve University ...
|
Research aims to guide decision-makers on real-world effects of artificial intelligence on American workers
Case Western Reserve University economics professor Mark Schweitzer has joined a new, multi-university research collaboration examining the impact of artificial intelligence (AI) on workers and the labor market—an urgent area of inquiry as AI adoption accelerates across industries.
Mark Schweitzer
The $1.6 million project is supported by the Alfred P. Sloan Foundation and led by Carnegie Mellon University’s Block Center for Technology and Society and MIT’s FutureTech. Researchers from eight academic institutions—including the University of Pittsburgh, Northeastern University, the University of Virginia and the California Policy Lab—are contributing their expertise, along with collaborators from the U.S. Chamber of Commerce Foundation.
“This is an important opportunity to bring rigorous, data-driven insights to some of the most pressing economic questions of our time,” said Schweitzer, whose research at Case Western Reserve and the Federal Reserve Bank of Cleveland focuses on labor markets and regional economics. “By pooling knowledge across institutions, we can better understand where AI is helping workers—and where it’s leaving them behind.”
During the next two years, the team will work to improve labor-market data and produce both academic research and policy-relevant reports, he said. The goal is to support research-driven decision-making by employers, labor organizations and government.
More information on the Block Center’s AI and Work initiative.
For more information, contact Colin McEwen at [email protected].
| 2025-07-08T00:00:00 |
2025/07/08
|
https://thedaily.case.edu/case-western-reserve-university-economist-joins-national-ai-labor-study-backed-by-1-6m-sloan-foundation-grant/
|
[
{
"date": "2023/01/01",
"position": 55,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 53,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 64,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 64,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 66,
"query": "AI workers"
},
{
"date": "2024/11/01",
"position": 63,
"query": "AI workers"
}
] |
Companies That Tried to Save Money With AI Are Now ... - Futurism
|
Companies That Tried to Save Money With AI Are Now Spending a Fortune Hiring People to Fix Its Mistakes
|
https://futurism.com
|
[] |
Companies that rushed to replace human labor with AI are now shelling out to have IRL workers to fix the technology's screwups.
|
Companies that rushed to replace human labor with AI are now shelling out to get human workers to fix the technology's screwups.
As the BBC reports, there's now something of a cottage industry for writers and coders who specialize in fixing AI's mistakes — and those who are good at it are using the opportunity to rake in cash.
Sarah Skidd, an American product marketing manager, told the British broadcaster that she's not concerned about being replaced by the technology because, as her recent work experiences have taught her, she's often tasked with cleaning up its many mistakes.
Earlier this year, Skidd was approached by an agency that urgently needed someone to redo copy for a client after having an undisclosed AI chatbot do the work to save a few bucks. The writing was typical of AI, she noted, calling it "very basic" and uninteresting.
"It was supposed to sell and intrigue," Skidd told the BBC, "but instead, it was very vanilla."
When the marketing maestro got down to business, she realized it was going to require a complete overhaul. Ultimately, she spent 20 hours redoing the copy from scratch — and with her $100-per-hour rate, that meant her client was shelling out $2,000 for copy that likely would have ended up being far cheaper had a human just written it in the first place.
With more and more companies rushing to replace the workers they fired during the pivot-to-AI craze over the past few years, things are shaking out in unexpected ways.
According to Sophie Warner, the co-owner of the UK-based digital marketing agency Create Designs, she's been fielding more and more requests from clients to clean up after AI mistakes.
"Before clients would message us if they were having issues with their site or wanted to introduce new functionality," Warner told the BBC. "Now they are going to ChatGPT first."
In one recent case, a client ended up going without a website for three days and having to pay Create Designs nearly $500 over a small line of code that ChatGPT had written for them. The original update would, Warner said, have taken about 15 minutes to implement manually.
"We often have to charge an investigation fee to find out what has gone wrong, as they don't want to admit it," she told the broadcaster, "and the process of correcting these mistakes takes much longer than if professionals had been consulted from the beginning."
Given that they're now profiting off the technology's mistakes, neither woman is particularly concerned about or even against AI — but they are frustrated that people think it can replace expert work.
"While it seems like a quick and inexpensive option, AI rarely takes into account unique brand identity, target demographics, or conversion-focused design," Warner said. "It simply cannot replace the value of human expertise and context in our industry."
Skidd, meanwhile, is confident about her job security in the age of AI.
"Maybe I'm being naive," the American marketer said, "but I think if you are very good, you won't have trouble."
More on AI fails: You'll Spit Take When You Hear How Little Time Workers Are Saving With AI, According to This Huge New Study
| 2023-01-01T00:00:00 |
https://futurism.com/companies-fixing-ai-replacement-mistakes
|
[
{
"date": "2023/01/01",
"position": 57,
"query": "AI workers"
},
{
"date": "2023/01/01",
"position": 45,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 44,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 55,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 44,
"query": "AI hiring"
},
{
"date": "2023/08/01",
"position": 37,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 44,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 80,
"query": "AI workers"
},
{
"date": "2023/12/01",
"position": 42,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 39,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 80,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 78,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 57,
"query": "artificial intelligence workers"
},
{
"date": "2024/06/01",
"position": 41,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 40,
"query": "AI hiring"
},
{
"date": "2024/11/01",
"position": 77,
"query": "AI workers"
},
{
"date": "2025/01/01",
"position": 43,
"query": "AI hiring"
},
{
"date": "2025/07/06",
"position": 78,
"query": "AI hiring"
},
{
"date": "2025/07/06",
"position": 81,
"query": "AI hiring"
},
{
"date": "2025/07/06",
"position": 81,
"query": "AI hiring"
}
] |
|
Contact Center AI Is Failing Because Leaders Aren't Listening
|
Contact Center AI Is Failing Because Leaders Aren’t Listening
|
https://www.cmswire.com
|
[
"Dom Nicastro",
"About The Author"
] |
The Gist · Agents aren't anti-AI—they're anti-neglect. Reddit threads show call center workers fear being left behind, not by bots, but by poor ...
|
The Gist
Agents aren’t anti-AI—they’re anti-neglect. Reddit threads show call center workers fear being left behind, not by bots, but by poor leadership and lack of support.
Reddit threads show call center workers fear being left behind, not by bots, but by poor leadership and lack of support. AI is increasing chaos, not clarity. From hallucinated call notes to clunky “efficiency” tools, agents say AI often creates more work instead of less.
From hallucinated call notes to clunky “efficiency” tools, agents say AI often creates more work instead of less. Leaders must step up. To make AI succeed in contact centers, leaders must communicate transparently, invest in upskilling and design AI that actually helps humans—not replaces or monitors them.
The problem for your contact center agents isn't artificial intelligence.
It's you. Leadership.
The underlying sentiment across some Reddit threads featuring contact center agents isn’t hatred of AI. It’s the fear of being left behind without support, context or a future.
"I hate to say, but employees will likely prefer the AI vs. slanted evaluators who may perceive things differently call to call," one Reddit commenter, be_just_this, posted on a thread about how long it will take for AI to replace contact center agents."
Table of Contents
Call Center Leaders Don't Listen to Agents, Enough
Call center leaders: some of you are just not listening. It's not so much the vendors and the integrators; it's your leadership around these critical functions.
According to loofsdrawkcab, call center agents are not allowed to edit automatic call notes generated by AI. Sometimes it will notate things that are clearly wrong, but call center leaders still hold agents accountable.
"So if QA gives me some BS like, 'Well the call notes say...' then I know I can just look up the call and be like, 'That's cool that you're QA and all but if you could do your job and realize that that shit didn't actually happen, that'd be wonderful :).'"
No wonder turnover for contact center agents is high. Angry customers and biased bosses giving unfair criticism? If there isn't a call to action for leaders of contact centers now, when will there ever be one?
All told, if contact center leaders want successful AI integration, and they're listening to agents who share their tales publicly, they must:
Communicate proactively
Empower agents with tools and training
Redefine roles with human strengths in mind
As u/TheReal_AI puts it:
“AI will handle tasks, not relationships… Emotional labor will be the true differentiator.”
Industry Reports: Call Center Agent Frustration With AI Is Real
Ok, a reality check: these are anonymous comments. It's how Reddit works, of course. And, who doesn't like to bash the boss every now and again anonymously on the internet? That's a rite of passage for job boards and sites like Reddit; an act as common as customer-service calls that include the word "representative!"
We get it. Take anonymous comments for what they are.
However, we do have some not-so-anonymous comments and concerns from contact center agents. Our reporting yesterday on the booming conversational AI space revealed a study published this month titled “Customer Service Representative’s Perception of the AI Assistant”. It reports how frontline agents experience AI in the contact center. While AI tools like real-time transcription and automated summaries are intended to save time, many agents say they often create extra work.
Investors and tech innovators don't seem to care. They are doubling down on artificial intelligence in the contact center and customer service and support space. According to a July 4 Research and Markets report, the global conversational AI market is expected to grow from $17.05 billion in 2025 to $49.8 billion by 2031. That marks a growth projection of 192% overall from 2025 to 2031. And it has a compound annual growth rate of 24.7% projected through 2029.
However, that exciting investment and innovation was tempered with this sobering reality: Just yesterday, July 7, cloud communications platform provider Infobip released findings from a new study conducted by Harvard Business Review Analytic Services (HBR-AS) revealing a hard truth for conversational CX: while 93% of those surveyed from the HBR audience recognize the high importance of creating positive conversational experiences, only 36% believe their organization is highly effective at it. Further, just 11% report they’re highly effective using AI to deliver human-like conversations.
Related Article: The Importance of Conversational Intelligence for Customer Experience
Customer Service and Support Functions at a Crossroads
Reddit. Real research. Industry reports. Whatever. Wherever.
It's clear: the contact center agent of today is at a crossroads. So, too, is their boss.
Where AI certainly has enormous potential and has produced real results in the customer service and support arena, it's a tender moment for the contact center agents who have to execute these marketing and technology promises of AI in customer experience.
Here’s a summary of key themes and direct quotes from Reddit conversations about AI in call centers. These insights capture how frontline employees are experiencing and thinking about AI—not just as a tool, but as a force reshaping their careers, workplaces and mental wellbeing.
We analyzed these three Reddit trails:
What Call Center Workers Really Think About AI
Third Party AI Company Replaces QA Staff
Many contact center employees report that AI is actively reshaping their jobs today, not in some distant future. This includes everything from real-time transcription to automated QA.
“My company already utilizes AI for a portion of the calls that we receive. But they have recently decided to replace our entire QA department with some 3rd party AI company that will be responsible for analyzing every call we receive to 'make us better agents.' What happened to the QA staff? We never got a straight answer. So, I think it’s obvious they were all let go. Which doesn’t make me feel very good about the security of my position because if they can replace one department with AI, there's no stopping them from doing it to us." — u/FlyingFox
AI Fluency Rises, Worker Mobility Collapses
Another call center worker described the monotonous nature of routine B2B inquiries and the increasing reliance on low-cost, outsourced labor that often feels disconnected and underqualified. More recently, AI-driven voice bots have started handling some of these calls with surprisingly fluent language mimicry, signaling how far automation has come.
"These models are almost to the point where they can do our jobs, and once they get there, it'll take time for companies to implement them at scale, but they will," u/RichardBottom wrote. "We already represent a huge bottom chunk of the workforce, and we're already shoving each other for whatever trace of upward mobility we can get our hands on. I think this is gonna be a shit show. I've been typecasted as a call center monkey my whole adult life, and whatever routes there are out are about to get blown to hell."
Takeaway for contact center leaders: Don’t ask if AI is affecting your agents—ask how. The technology’s presence is uneven but expanding quickly, especially in backend automation and QA.
The Fear Is Real—and Grounded in Experience
Several commenters express genuine anxiety about job loss, often pointing to departments already downsized or outsourced.
“My company is outsourcing and moving towards automation. I'd be surprised if there was anyone left by this time next year," u/HausWife88 said.
Takeaway for contact center leaders: AI rollouts without clear communication fuel fear and distrust. Employees need transparency and a path forward—not just automation.
Simpler Media Group
Leadership Prioritizes Optics and Cost Savings—Not Experience
From investor buzzwords to vacationing C-suites, agents are skeptical that leaders are prioritizing quality or employee impact in AI decisions.
“Most call centers will say they're AI-integrated just to fool investors... all they will do is put AI in an internal search bar or something stupid like that.” — u/toocontroversial_4u
“Our C-suite will get their 2 weeks in the Bahamas. We’ll get pay reductions, more work, and less accuracy in our day to day.” — u/DirectionHot8175
Takeaway for contact center leaders: Communicate real use cases and tie AI investments to agent success—not just investor narratives. People notice when the benefits only flow one way.
Related Article: The True Cost of Contact Center Turnover (And How to Lower It)
Agents Want Support Tools, Not Surveillance Systems
Many workers are fine with AI that helps—like suggesting next steps or summarizing notes—but object strongly to AI tools that feel invasive or judgmental.
“When they said they were going to incorporate AI I thought maybe it was going to take the workload off us... no, it’s just language model AI that is listening to you which gives me the creeps.” — u/DiscombobulatedLie91
Takeaway for contact center leaders: AI for productivity = welcomed. AI for grading and watching = resented. Respect privacy, allow overrides and involve agents in deployment feedback.
AI Isn’t Replacing Humans—It's Making Work More Chaotic
While few believe AI is eliminating jobs wholesale yet, many workers say it’s increasing their workload through inefficiencies, AI hallucinations and broken workflows.
“The content it [AI] produced was often filled with errors and redundancies… If it's increasing the staff's workload, how is it also enhancing work efficiency?” — u/Algernon_Asimov
“I have to do 5 extra things that take more total time than just not using the AI in the first place… Because the task only took 3 minutes. The other new work obviously needs an AI tool of its own…” — u/SkeetySpeedy
“AI... just makes everything (expletive deleted) more difficult due to the constant mistakes the AI makes.” — u/DiscombobulatedLie91
Takeaway for contact center leaders: If your AI rollout adds friction instead of removing it, it won’t be seen as progress. Efficiency gains on paper can still feel like burnout on the floor.
Call Center Jobs Aren’t Disappearing—They’re Evolving
Some actual positive vibes here. Rather than extinction, many predict a transition: fewer level 1 agents, more escalations and complex cases for skilled human reps. Some even welcome AI as a “copilot” that enhances their work.
“The jobs will change, not be replaced… AI will handle repetitive queries… Humans will focus on creating value through empathy, understanding and deep problem-solving.” — u/TheReal_AI
“I’m pretty high up in a contact center and the rise of AI has only made the job of a front line agent easier… It’s like having a little helper on your shoulder as you take calls.” — u/Advisor-Unhappy
Takeaway for contact center leaders: Reframe the narrative. The future workforce isn’t smaller—it’s smarter. Train agents for complexity, relationship-building and AI fluency.
Some See opportunity, Not Threat With AI in Call Centers
And more positive vibes. A minority of agents are already working with AI or proactively training for what’s next.
“I already get ChatGPT to do most of my job for me…” — u/BeefBaeby
“I’ve already started training my small team to be more sales minded as I think outbound will last a bit longer…” — u/ehfrehneh
Takeaway for contact center leaders: Highlight and reward these early adopters. Create programs to help agents reskill, upskill and transition into higher-value roles.
Consistency Is Welcomed, but Emotional Intelligence Is Missed
While AI is praised for standardizing processes and reducing frustration from inconsistent answers, most workers agree that it can’t replicate empathy or human nuance.
“What did our customers hate the most? It was actually calling and getting different answers every time by a rep. Well now it’s the same answers albeit different delivery.” — u/Impossible-Affect202
“AI will never fully deal with that irate caller who feels they are right. AI will need to transfer to an actual human for final resolution of any matter.” — u/blackintel
The technology still struggles with edge cases, emotional calls or industry jargon—leaving workers to clean up its mess or calm customers who feel ignored.
“Installers... use odd terminology to describe what is or isn't working. There's no way current AI would understand… it would most likely cite wrong information.” — u/kinisonkhan
“If it's a complex problem... the automated service gets confused easily. Currently, heavy accents also make it fail.” — u/TPWilder
Takeaway for contact center leaders: AI can’t replace emotional labor. Let it handle the repetitive—but keep humans in the loop for complexity and compassion. AI is useful for what needs to be said. But how it’s said still matters. Customers value empathy, flexibility and connection—things AI still struggles with.
Customers Still Want Humans—but Hate the Current System
Ironically, many workers believe customers still prefer humans—just not the ones buried behind bad menus, long holds or inconsistent service.
“Customers would rather an AI relieve them of these horrors than endure them to speak to a human. From a customer perspective, modern human-based customer service is a hardcore (expletive deleted) nightmare.” — u/highDrugPrices4u
“Half of my calls each day are people telling me they hate AI.” — u/OkInvestigator4220
Takeaway for contact center leaders: Bad experiences—not AI itself—are the enemy. If your human service is slow, inconsistent or unavailable, customers will welcome AI. The goal isn’t replacing humans—it’s delivering better service.
Burnout Is Real—and Some Want to Be Replaced
This surprising undercurrent emerged multiple times: despair with call center work so intense that some welcome AI as an escape.
“PLEASE replace me and put me out of my misery.” — u/john_b_walsh
Not all contact center agents are all in on AI, though.
“Give me the complicated manual tasks instead of AI garbage any day... I don’t need stupid AI.” — u/StoneTown
“It is insane to think what we’ll be delivering to clients. Probably why we’re losing them left and right 🙃” — u/DirectionHot8175
Takeaway for contact center leaders: AI won’t solve workplace morale problems—it might intensify them if introduced carelessly. Invest equally in human support.
Contact Center Leadership Action Plan: What to Fix and How
This table outlines key issues raised by contact center agents across multiple Reddit threads and pairs each with a clear action for leaders to take.
Problem Action for Leaders AI increases workload instead of reducing it Evaluate tools based on actual agent experience, not just surface metrics like handle time. Streamline workflows end-to-end. Lack of communication around AI changes fuels fear Communicate proactively about AI deployments, including what's changing, why and how it affects each role. Leadership prioritizes investor optics over agent experience Ensure AI investments have clear internal use cases tied to agent productivity and satisfaction—not just external messaging. AI tools feel invasive or overly punitive Use AI for support, not surveillance. Give agents visibility into how AI assessments work and allow overrides when needed. Emotional labor and complexity still require humans Keep humans in the loop for nuanced issues and emotionally charged calls. Train agents for high-complexity tasks. Inconsistent or slow human service drives customers to prefer AI Fix broken human service experiences before replacing them. Use AI to support—not mask—underperforming systems. Some agents want to reskill, but aren’t supported Identify and reward early AI adopters. Provide upskilling paths into higher-value roles like escalation support or AI training oversight. Burnout drives disengagement and turnover Address morale directly. Improve workload balance and recognize the emotional toll of frontline roles in a hybrid AI environment.
Conclusion: Listen Before You Automate
With contact center turnover rates somewhere between 30% and 45%, contact center leaders naturally have their work cut out.
AI isn’t the villain in the contact center—neglect is. Across dozens of Reddit threads and agent testimonies, one message is clear: your frontline teams aren’t afraid of technology, they’re afraid of being ignored. Poorly implemented tools, lack of transparency and a disconnect between leadership and agent experience are fueling burnout more than the bots themselves.
If leaders want successful AI integration, they must shift from automation at all costs to collaboration with purpose—communicating clearly, training intentionally and building AI that serves both customers and agents. The call center of the future depends not just on smarter machines, but on smarter leadership.
| 2023-01-01T00:00:00 |
https://www.cmswire.com/contact-center/your-contact-center-agents-dont-fear-aithey-fear-your-leadership/
|
[
{
"date": "2023/01/01",
"position": 59,
"query": "AI workers"
},
{
"date": "2023/02/01",
"position": 78,
"query": "AI replacing workers"
},
{
"date": "2023/03/01",
"position": 77,
"query": "AI replacing workers"
},
{
"date": "2023/03/01",
"position": 57,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 83,
"query": "AI replacing workers"
},
{
"date": "2023/04/01",
"position": 70,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 66,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 73,
"query": "AI replacing workers"
},
{
"date": "2023/06/01",
"position": 66,
"query": "AI workers"
},
{
"date": "2023/08/01",
"position": 81,
"query": "AI replacing workers"
},
{
"date": "2023/09/01",
"position": 80,
"query": "AI replacing workers"
},
{
"date": "2023/09/01",
"position": 68,
"query": "AI workers"
},
{
"date": "2023/10/01",
"position": 82,
"query": "AI replacing workers"
},
{
"date": "2023/10/01",
"position": 40,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 79,
"query": "AI replacing workers"
},
{
"date": "2023/11/01",
"position": 66,
"query": "AI workers"
},
{
"date": "2023/12/01",
"position": 78,
"query": "AI replacing workers"
},
{
"date": "2024/01/01",
"position": 57,
"query": "AI replacing workers"
},
{
"date": "2024/01/01",
"position": 68,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 81,
"query": "AI replacing workers"
},
{
"date": "2024/02/01",
"position": 65,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 76,
"query": "AI replacing workers"
},
{
"date": "2024/03/01",
"position": 69,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 99,
"query": "artificial intelligence workers"
},
{
"date": "2024/04/01",
"position": 79,
"query": "AI replacing workers"
},
{
"date": "2024/05/01",
"position": 80,
"query": "AI replacing workers"
},
{
"date": "2024/05/01",
"position": 66,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 80,
"query": "AI replacing workers"
},
{
"date": "2024/06/01",
"position": 71,
"query": "AI workers"
},
{
"date": "2024/07/01",
"position": 80,
"query": "AI replacing workers"
},
{
"date": "2024/10/01",
"position": 78,
"query": "AI replacing workers"
},
{
"date": "2024/11/01",
"position": 81,
"query": "AI replacing workers"
},
{
"date": "2024/11/01",
"position": 67,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 82,
"query": "AI replacing workers"
},
{
"date": "2024/12/01",
"position": 65,
"query": "AI workers"
},
{
"date": "2025/01/01",
"position": 80,
"query": "AI replacing workers"
}
] |
|
Microsoft announces another round of AI-related layoffs, targeting ...
|
Microsoft announces another round of AI-related layoffs, targeting gaming and engineering workers
|
https://www.wsws.org
|
[] |
Most of the workers to be laid off are apparently not unionized. A minority of impacted gaming workers, however, are organized by the ...
|
A Microsoft sign and logo are pictured at the company's headquarters, Friday, April 4, 2025, in Redmond, Washington. [AP Photo/Jason Redmond]
On July 2, Microsoft expanded a long run of layoffs by announcing a workforce reduction of up to 4 percent, or about 9,100 jobs. These add to the over 8,000 layoffs this year at the company, including about 6,000 layoffs in May. In total, this year’s layoffs have hit over 7 percent of its global workforce.
Most of the specific cuts to be made in this latest round have yet to be identified. Company executives have emphasized an aim to “remove layers of management to increase agility and effectiveness.” So far this year, although the layoffs have affected product managers and program managers, over 40 percent of the job cuts have been in software engineering. Jobs in Microsoft’s home state of Washington have been hardest hit, but the layoffs affect its global workforce more generally, including layoffs in California, as well as in Europe, Australia and New Zealand.
Most of the workers to be laid off are apparently not unionized. A minority of impacted gaming workers, however, are organized by the Communication Workers of America (CWA). The CWA has issued a statement expressing that it is “deeply disappointed in Microsoft’s decision to lay off thousands more workers, including union-represented CWA members, at a time when the company is prospering. ... We will be bargaining with the company over these layoffs.”
A popular Reddit comment responded to the CWA statement:
It needs to made clear that this statement is really all any union can do about “restructuring.” Some people on the internet, who have never been in a union themselves and sure as hell aren’t getting off their asses to unionize their own work place, love telling other folks to unionize when they have no idea what a union actually is. Unions are not an answer to mass layoffs. Possible solutions include wildcat work stoppage (which is illegal for unions to do), and abolishing capitalism instead of pretending it can be saved.
Another popular Reddit comment in a separate thread described work at Microsoft:
There is a perpetual climate of fear inside the company. Instead of ripping the band aid off and being done it’s a continuous parade of monthly layoffs causing many to be fearful. I have seen a regression towards the old way of teams fighting each other instead of working towards a common goal. The secrecy is the worst. Layoffs in my group happened and they won’t tell us who is gone from the people I work with and rely on. The work didn’t go away though. It was just added onto the backs of those who remain. The cost cutting isn’t limited to people. They took away the post it notes and pads of paper in the supply rooms in my building.
In January this year, Microsoft terminated about 2,000 workers in ostensible “performance-based” cuts. In May, it laid off about 6,000, with vague references to “efficiency” and “business priorities” being the reasons given. In June, it laid off hundreds more, once again in ostensible “performance-based” cuts.
Workers subject to the “performance-based” cuts lose healthcare insurance coverage immediately, and are denied severance pay. The company has imposed a two-year rehiring ban on workers cut under the pretext of poor performance, and has deemed the cuts to be “good attrition,” suggesting that company management intends to incorporate layoff targets for specified divisions as a regular feature of its business plans. These measures replicate similar ones taken in recent years by other tech giants like Amazon and Meta.
Online commenters, apparently tech workers or those with personal relations to tech workers, have disputed the company’s claims that layoffs in January and June were truly “performance-based.” For example, another popular Reddit comment reads:
I know people personally who were affected. None of them had any indication of “low performance.” They received annual bonuses and positive reviews. One even asked for specific performance metrics for promotions and was given vague responses stating they were on a promotion track and to keep doing what they were doing. In the end, this is a callous layoff under the guise of “low performances” so they can justify culling thousands of people with no severance and leaving them without insurance or a high amount of earned stock set to divest [sic] again in two weeks.
Other online commenters have confirmed the practices described above. Very apparently, the comment refers to a practice of terminating workers shortly before a scheduled vesting event for their equity compensation, which, at large tech companies, commonly comprises 50 percent or more of workers’ income. Such a practice would enable the company to deprive workers of very large amounts of equity compensation which they had worked toward for months and years, under a pretext of allegedly poor performance.
Notably, the “performance-based” cuts in January and June affected primarily workers in Microsoft’s gaming divisions, including Xbox. Xbox and other Microsoft gaming divisions have again been targeted in the latest round of much larger layoffs (which are not “performance-based”). It is cutting jobs from divisions that produce the games Candy Crush and Forza Motorsport. It is canceling entirely the popular Perfect Dark and Everwild games, as well as several unannounced projects.
In an X post made in reference to the layoffs, Matt Turnbull, executive producer at Xbox Game Studios Publishing, demonstrated the pervasive indifference of the capitalist class toward the workers it exploits. The post condescendingly explains, “I’ve been experimenting with ways to use LLM Al tools (like ChatGPT or Copilot) to help reduce the emotional and cognitive load that comes with job loss.” He goes on to suggest “some prompt ideas and use cases that might help if you’re feeling overwhelmed,” i.e., that laid-off workers should use AI chatbots to help them with career planning, job seeking, networking, as well as the emotional impact of their job loss.
Thus far, Microsoft company management has not admitted openly to any connection between the layoffs this year and the introduction and development of generative AI technologies. However, media observers, analysts and online commenters generally take it as a given that the job cuts are part of a large-scale restructuring of the tech industry related to AI. The company plans to invest $80 billion in AI-related development in fiscal year 2025 alone.
At the Build industry conference in May, Microsoft CEO Satya Nadella demonstrated AI software tools that could, with relatively very little human direction, very quickly perform tasks previously carried about by entire teams of engineers. At present, about 30 percent of software coding work at Microsoft is done by AI.
In a move widely recognized as part of an AI-related strategic shift, Microsoft cut 10,000 jobs in early 2023. In 2024, it cut an undisclosed number of jobs, probably around 3,500-4,500 total. Business analysts, including Gil Luria, have suggested that Microsoft’s increased investments will necessitate annual workforce reductions of about 10,000.
According to the World Economic Forum’s annual Future of Jobs Report published in January, 41 percent of employers surveyed internationally “foresee staff reductions due to skills obsolescence” related to the implementation of AI technologies. International companies that underwent AI-related layoffs this year include Adidas, Ally, Automattic (parent company of Tumblr and WordPress), Block, Blue Origin, Boeing, BP, Bridgewater, Bumble, Burberry, Chevron, CNN, Coty, CrowdStrike, Disney, Dropbox, Estée Lauder, Geico, GrubHub, Hewlett Packard Enterprise, Intel, Johns Hopkins University, Kohl’s, Meta, Microchip Technology, Morgan Stanley, Nissan, Panasonic, Paramount, Porsche, PwC, Salesforce, Sonos, Southwest Airlines, Starbucks, Stripe, UPS, the Washington Post, Wayfair, and Workday.
A Business Insider report published in March explains bluntly:
Across tech, the tables have turned for employees as performance pressure and proclamations of “efficiency” and “intensity” replace perks and pampering. Sweeping layoffs have become the norm in an industry that, in recent memory, enjoyed job security. The pressure to dominate in AI has created intense competition, as companies use the technology to do more with fewer workers. Already hard-driving workplaces have become even harder.
DesignWhine reports, “The Microsoft layoffs of 2025 mark not just a corporate restructuring but a fundamental shift in how technology companies view human capital in an AI-dominated future.”
Amazon CEO Andy Jassy has also spoken bluntly about the connection between workforce reductions and AI. He explained in a message June 17 on aboutamazon.com:
As we roll out more Generative AI and agents, it should change the way our work is done. We will need fewer people doing some of the jobs that are being done today, and more people doing other types of jobs. It’s hard to know exactly where this nets out over time, but in the next few years, we expect that this will reduce our total corporate workforce as we get efficiency gains from using AI extensively across the company.
So far this year, Amazon has introduced new return-to-office and performance review policies that will intensify job performance pressures on workers while their compensation stagnates and even falls, primarily through cuts to equity and bonus pay.
An Amazon tech worker told the WSWS:
The so-called “performance-based” layoffs are not really performance-based. This has happened at Amazon, too. We’ve also had layoffs carefully planned by management to come shortly before RSU [restricted stock unit: a common type of equity compensation] vesting for large numbers of workers. It happens at pretty much every tech company. Historically, Google had not followed such practices. However, recently, even Google has been adapting, also because of AI. I’ve heard that they haven’t been making generous hiring offers anymore. They’ve taken away some of the perks. For example, Google used to have free meal services and onsite laundry. I heard they took most of it away. There are no longer any employers offering generous conditions to tech workers anymore.
University of Washington professor Margaret O’Mara told the Seattle Times that, in the context of business history, the Microsoft layoffs are very unusual: “When you see thousands of workers laid off, it’s been deindustrialization or companies in crisis, but these tech companies are the most valuable in human history.” In fact, Microsoft reported nearly $26 billion in profits in the first quarter of 2025, one of the best ever for the company.
The major shifts in the computer gaming industry—coupled with the Trump administration’s economic warfire against the entire world—have recently led to massive price hikes for games. Last month, a 10-month strike of video game performers, members of the Screen Actors Guild-American Federation of Television and Radio Artists (SAG-AFTRA), was suspended after the union announced a tentative agreement.
Jacobin, Labor Notes, and other pseudo-left publications have remained silent so far about the Microsoft layoffs.
In a related development, an online petition “Stop Killing Games” has gathered over 1.2 million signatures. It is a consumer-based initiative aimed at pressuring governments to enact laws that would restrict tech companies from canceling popular computer games.
| 2025-07-07T00:00:00 |
2025/07/07
|
https://www.wsws.org/en/articles/2025/07/07/qdhs-j07.html
|
[
{
"date": "2023/01/01",
"position": 61,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 60,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 14,
"query": "AI layoffs"
},
{
"date": "2023/04/01",
"position": 14,
"query": "AI layoffs"
},
{
"date": "2023/05/01",
"position": 15,
"query": "AI layoffs"
},
{
"date": "2023/06/01",
"position": 15,
"query": "AI layoffs"
},
{
"date": "2023/07/01",
"position": 14,
"query": "AI layoffs"
},
{
"date": "2023/09/01",
"position": 13,
"query": "AI layoffs"
},
{
"date": "2023/09/01",
"position": 65,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 15,
"query": "AI layoffs"
},
{
"date": "2024/01/01",
"position": 14,
"query": "AI layoffs"
},
{
"date": "2024/01/01",
"position": 65,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 67,
"query": "AI workers"
},
{
"date": "2024/05/01",
"position": 14,
"query": "AI layoffs"
},
{
"date": "2024/06/01",
"position": 12,
"query": "AI layoffs"
},
{
"date": "2024/07/01",
"position": 13,
"query": "AI layoffs"
},
{
"date": "2024/08/01",
"position": 13,
"query": "AI layoffs"
},
{
"date": "2024/11/01",
"position": 64,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 13,
"query": "AI layoffs"
}
] |
Workers must define and shape a future living with AI - Forsa
|
Workers must define and shape a future living with AI
|
https://www.forsa.ie
|
[] |
Fórsa NEC member Ursula Cox tells ICTU conference that unions must assert their role in shaping how AI is introduced in the workplace.
|
Fórsa national executive member Ursula Cox has told delegates attending the ICTU biennial delegate conference that unions must urgently assert their role in shaping how artificial intelligence is introduced in the workplace.
Supporting a motion on AI proposed by the Financial Services Union (FSU), Ms Cox said the rise of AI systems represents a significant challenge for workers, and warned that “we need to move, and we need to move fast.” The motion was tabled this morning (Thursday) on the final day of the conference, which is taking place in Belfast.
“Having feasted on our personal data, the AI is coming for our jobs,” she said, referencing figures that suggest 40% of jobs globally are due to be impacted by AI. She said that generative AI “is not likely to replace jobs… it is already replacing jobs: data entry, document processing and customer service, jobs which are often undertaken by women.”
Ms Cox called for a structured mechanism for union engagement with Government, agencies and employers, “not as an afterthought, but as a partner in shaping the world of work,” and said workers must have the opportunity to reskill and upskill in ways that support them in sustainable work, warning that those not supported “will be displaced by entire AI ecosystems that reshape industries.”
She urged collective engagement between unions, governments and employers to protect the humanity of the workplace and to prepare for a potential “productivity cliff” – where AI increases output while reducing the human workforce faster than replacement roles can be developed.
Highlighting the role of personal data in the development of AI, she said: “All that lovely personal data soaked up by the tech firms means we’ve all had a hand in the construction of these AI systems.
“We must ensure the future of work is built with workers, not without them. Let’s stand together to ensure AI serves the people but does not replace them.”
The motion recognises the risks AI poses to employment and calls for frameworks that involve trade unions in decision-making on AI adoption, investment in targeted training for workers, and worker-centred priorities in EU regulation.
Join a union that wins. Join Fórsa.
| 2025-07-03T00:00:00 |
2025/07/03
|
https://www.forsa.ie/artificial-intelligence-in-the-workplace/
|
[
{
"date": "2023/01/01",
"position": 65,
"query": "AI workers"
},
{
"date": "2023/02/01",
"position": 60,
"query": "AI replacing workers"
},
{
"date": "2023/03/01",
"position": 57,
"query": "AI replacing workers"
},
{
"date": "2023/03/01",
"position": 64,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 75,
"query": "AI replacing workers"
},
{
"date": "2023/06/01",
"position": 62,
"query": "AI replacing workers"
},
{
"date": "2023/08/01",
"position": 59,
"query": "AI replacing workers"
},
{
"date": "2023/09/01",
"position": 61,
"query": "AI replacing workers"
},
{
"date": "2023/09/01",
"position": 72,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 67,
"query": "artificial intelligence labor union"
},
{
"date": "2023/10/01",
"position": 62,
"query": "AI replacing workers"
},
{
"date": "2023/11/01",
"position": 58,
"query": "AI replacing workers"
},
{
"date": "2023/12/01",
"position": 57,
"query": "AI replacing workers"
},
{
"date": "2024/01/01",
"position": 35,
"query": "AI replacing workers"
},
{
"date": "2024/01/01",
"position": 72,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 61,
"query": "AI replacing workers"
},
{
"date": "2024/02/01",
"position": 89,
"query": "artificial intelligence labor union"
},
{
"date": "2024/03/01",
"position": 57,
"query": "AI replacing workers"
},
{
"date": "2024/03/01",
"position": 73,
"query": "AI workers"
},
{
"date": "2024/04/01",
"position": 58,
"query": "AI replacing workers"
},
{
"date": "2024/05/01",
"position": 62,
"query": "AI replacing workers"
},
{
"date": "2024/06/01",
"position": 58,
"query": "AI replacing workers"
},
{
"date": "2024/07/01",
"position": 61,
"query": "AI replacing workers"
},
{
"date": "2024/10/01",
"position": 59,
"query": "AI replacing workers"
},
{
"date": "2024/11/01",
"position": 61,
"query": "AI replacing workers"
},
{
"date": "2024/11/01",
"position": 70,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 62,
"query": "AI replacing workers"
},
{
"date": "2025/01/01",
"position": 58,
"query": "AI replacing workers"
}
] |
AI Will Not Kill the American Worker - Wide Moat Research
|
AI Will Not Kill the American Worker – Wide Moat Research
|
https://www.widemoatresearch.com
|
[] |
Thanks to AI, it has reduced its employee count from 5,000 to 3,000. Bill Gates told Jimmy Fallon in March that AI would make human engagement ...
|
There’s a lot of tech news that has come out in the last week or two… such as yesterday’s update that Microsoft (MSFT) will be letting around 9,000 employees go, mostly from its Xbox (video game) division.
That’s on top of the 6,000 layoffs it already conducted earlier this year.
To be clear, this has nothing to do with budget concerns as far as I can see. Microsoft reported third-quarter results only two months ago, with significantly better-than-expected earnings per share of $3.46 versus $3.22.
Revenue, meanwhile, was $70.07 billion instead of the predicted $68.42 billion. Plus, it rose 13% year over year. And net income rose 17% to $25.8 billion.
Oh, and the company has just over $28 billion of cash on the books.
In short, Microsoft isn’t hurting for money.
Instead, it says it’s trying to streamline the process between contributors and executives. As Phil Spencer, CEO of Microsoft’s gaming division, explained:
To position Gaming for enduring success and allow us to focus on strategic growth areas, we will end or decrease work in certain areas of the business and follow Microsoft’s lead in removing layers of management to increase agility and effectiveness.
Translation 1: You’re fired.
Translation 2: Artificial intelligence (“AI”) is allowing them to cut out middlemen left and right.
I recently mentioned another example of this in Klarna, a Swedish financial tech company that’s slashing its workforce. Thanks to AI, it has reduced its employee count from 5,000 to 3,000.
Bill Gates told Jimmy Fallon in March that AI would make human engagement obsolete “for most things.” It’s a scary thought, but I don’t think it’s an accurate one.
AI is certainly a game changer – even a disruptor. But I expect the U.S., at least, is on the right path to handle it well.
This Time, It’s (Somewhat) Different
Seth Godin, best-selling author of books like This Is Strategy: Make Better Plans and This Is Marketing: You Can’t Be Seen Until You Learn to See, blogged yesterday about how:
Plato was sure that the invention of handwriting would destroy memory, and I’m confident there were scribes who thought that the Gutenberg press was the end of civilization. Yet, all around us, there are writers who use spell check, guitarists who use electronic pitch tuners, and photographers who use digital cameras. Productivity wins out.
He also mentions the invention of laser printers, which ended the typesetter profession… streets that are paved with machines instead of by hand… and cars that allow us to drive from place to place instead of walking or riding a horse.
In each case, he points out, some people did lose their jobs. Others bewailed the theoretical end of the world.
And yet humanity lived on anyway. They adapted and advanced with and because of the changes.
Therefore, it’s reasonable to conclude that humanity will do the exact same thing now. It’s not any different this time around, Godin argues.
It’s a compelling argument, but I do think it has two flaws to it:
In all the cases he cites, one industry was targeted at a time. So society had much more room to rearrange itself. Previous historical disruptions have actually created jobs, with expertise created across entirely new industries. AI’s ultimate potential involves eliminating human expertise completely.
Those two factors make a difference.
Where do out-of-work accountants turn to if most other financial positions have also been wiped out? And “learning how to code” (i.e., studying for a whole new trade) won’t really be an option since so many other sectors will be AI-dominated as well.
With that said – and call me an optimistic fool if you’d like – I still think I’ll be proven correct… I still believe society will survive this latest change.
In fact, I think it’s going to thrive because of it.
AI Versus Humanity (Humanity Wins)
I know that, from an investor perspective, it’s hard to see anything but dollar signs in artificial intelligence. But, as I’ve mentioned in previous articles, that’s not necessarily how others see it.
Don’t forget about the Hollywood writers and actors strikes of 2023…
The United Auto Workers strike the same year…
And the dockworkers strike last year and into 2025.
Each one involved industry employees fighting back against what AI would do to their livelihoods. And every single one managed to set boundaries for how it was used.
In Hollywood’s case, Brookings explained:
The [final] contract explicitly spells out that AI is not itself a writer competing with humans, but rather a tool for writers’ beneficial use. To the extent that AI is used, the regulations specify that AI should complement the work of writers instead of replacing them. The contract permits studios and writers to use generative AI under specific circumstances, but with guardrails that protect writers’ employment, credit, and creative control, while also protecting the studios’ copyright.
There were similar concessions in the dockworkers strike. And while that wasn’t the case with the autoworkers exactly, they did get the right to strike over plant closures – which was largely happening because of shifts toward electric vehicle manufacturing and the AI-empowered automation behind it.
It proves that when American workers stand up for themselves, positive progress really can come from AI. It can turn artificial intelligence into a true tool for human beings instead of a replacement.
I expect we haven’t seen the end of protests on this issue. And that’s a good thing. AI still has plenty of bugs to figure out, and the more voices involved in solving those problems, the better.
I know that Trump lost his bid for federal control over AI this week as the Senate cut that aspect from the One Big Beautiful Bill. And that is disappointing. As I said in the past, centralizing legislation for AI at the federal level would mean AI companies wouldn’t have to deal with a patchwork system of regulations at the state level. All else equal, that’s good for innovation and growth.
But it also gives Americans more room to speak up and turn AI into the asset it’s meant to be. As they do, I know the Trump administration will be behind them just like it was involved in resolving the dockworkers dispute.
As he stated last December, the short-term money companies save from automation isn’t worth the long-term effects of destroying American workers. I know he hasn’t changed that stance; his goal is to Make America Great Again by empowering its citizens.
AI is just supposed to be one of many means toward that goal.
Regards,
Brad Thomas
Editor, Wide Moat Daily
| 2023-01-01T00:00:00 |
https://www.widemoatresearch.com/wide-moat-daily/ai-will-not-kill-the-american-worker/
|
[
{
"date": "2023/01/01",
"position": 66,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 48,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 52,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 51,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 53,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 54,
"query": "AI workers"
},
{
"date": "2023/10/01",
"position": 57,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 53,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 54,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 53,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 54,
"query": "AI workers"
},
{
"date": "2024/05/01",
"position": 53,
"query": "AI workers"
},
{
"date": "2024/11/01",
"position": 54,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 53,
"query": "AI workers"
},
{
"date": "2025/07/03",
"position": 45,
"query": "AI workers"
},
{
"date": "2025/07/03",
"position": 45,
"query": "AI workers"
}
] |
|
A Real-Time Look at How AI Is Reshaping Work - USC Viterbi
|
A Real-Time Look at How AI Is Reshaping Work
|
https://viterbischool.usc.edu
|
[
"Julia Cohen",
"Usc Students",
"Researchers Track Where Ai Is Having The Biggest Impact On Jobs",
"Salaries"
] |
The researchers suggest this may signal the early effects of automation, where AI is starting to replace workers instead of augmenting them. “In ...
|
Artificial intelligence may take over some tasks and transform others, but one thing is certain: it’s reshaping the job market. Researchers at USC’s Information Sciences Institute (ISI) analyzed LinkedIn job postings and AI-related patent filings to measure which jobs are most exposed, and where those changes are happening first.
The project was led by ISI research assistant Eun Cheol Choi, working with students in a graduate-level USC Annenberg data science course taught by USC Viterbi Research Assistant Professor Luca Luceri. The team developed an “AI exposure” score to measure how closely each role is tied to current AI technologies. A high score suggests the job may be affected by automation, new tools, or shifts in how the work is done.
Which Industries Are Most Exposed to AI?
To understand how exposure shifted with new waves of innovation, the researchers compared patent data from before and after a major turning point. “We split the patent dataset into two parts, pre- and post-ChatGPT release, to see how job exposure scores changed in relation to fresh innovations,” Choi said. Released in late 2022, ChatGPT triggered a surge in generative AI development, investment, and patent filings.
Jobs in wholesale trade, transportation and warehousing, information, and manufacturing topped the list in both periods. Retail also showed high exposure early on, while healthcare and social assistance rose sharply after ChatGPT, likely due to new AI tools aimed at diagnostics, medical records, and clinical decision-making.
In contrast, education and real estate consistently showed low exposure, suggesting they are, at least for now, less likely to be reshaped by current AI technologies.
AI’s Reach Depends on the Role
AI exposure doesn’t just vary by industry, it also depends on the specific type of work. Jobs like software engineer and data scientist scored highest, since they involve building or deploying AI systems. Roles in manufacturing and repair, such as maintenance technician, also showed elevated exposure due to increased use of AI in automation and diagnostics.
At the other end of the spectrum, jobs like tax accountant, HR coordinator, and paralegal showed low exposure. They center on work that’s harder for AI to automate: nuanced reasoning, domain expertise, or dealing with people.
AI Exposure and Salary Don’t Always Move Together
The study also examined how AI exposure relates to pay. In general, jobs with higher exposure to current AI technologies were associated with higher salaries, likely reflecting the demand for new AI skills. That trend was strongest in the information sector, where software and data-related roles were both highly exposed and well compensated.
But in sectors like wholesale trade and transportation and warehousing, the opposite was true. Jobs with higher exposure in these industries tended to offer lower salaries, especially at the highest exposure levels. The researchers suggest this may signal the early effects of automation, where AI is starting to replace workers instead of augmenting them.
“In some industries, there may be synergy between workers and AI,” said Choi. “In others, it may point to competition or replacement.”
From Class Project to Ongoing Research
The contrast between industries where AI complements workers and those where it may replace them is something the team plans to investigate further. They hope to build on their framework by distinguishing between different types of impact — automation versus augmentation — and by tracking the emergence of new job categories driven by AI. “This kind of framework is exciting,” said Choi, “because it lets us capture those signals in real time.”
Luceri emphasized the value of hands-on research in the classroom: “It’s important to give students the chance to work on relevant and impactful problems where they can apply the theoretical tools they’ve learned to real-world data and questions,” he said. The paper, Mapping Labor Market Vulnerability in the Age of AI: Evidence from Job Postings and Patent Data, was co-authored by students Qingyu Cao, Qi Guan, Shengzhu Peng, and Po-Yuan Chen, and was presented at the 2025 International AAAI Conference on Web and Social Media (ICWSM), held June 23-26 in Copenhagen, Denmark.
Published on July 7th, 2025
| 2023-01-01T00:00:00 |
https://viterbischool.usc.edu/news/2025/07/a-real-time-look-at-how-ai-is-reshaping-work/
|
[
{
"date": "2023/01/01",
"position": 67,
"query": "AI workers"
},
{
"date": "2023/02/01",
"position": 53,
"query": "generative AI jobs"
},
{
"date": "2023/03/01",
"position": 63,
"query": "AI workers"
}
] |
|
Managing AI agents: These are the core skills we'll need
|
Leaders will soon be managing AI agents – these are the skills they'll need, according to experts
|
https://www.weforum.org
|
[] |
In the future, humans will be managing AI agents as 'digital workers', experts suggest. But what skills will they need?
|
Artificial intelligence experts predict a future where humans will be managing AI agents as 'digital workers'.
But what skillset will those managers need when working with AI?
From prompting to trust, training to soft skills, three experts share their views.
"Very soon, I think the valuation metric for a good manager will be: How many digital workers can you manage? That's a different skill set. It's about how you can prompt your agents to do the best work they can do.”
So says Wang Guanchun, Chairman and CEO of Laiye, a Chinese company that creates AI agents or 'digital workers' to carry out tasks including lead generation and candidate screening.
He was speaking at the World Economic Forum's 'Summer Davos' event in China, in a session on Building an Agentic Economy.
Although they use generative AI, AI agents are different because they can actually perform tasks, rather than merely producing something.
So, for example, AI agents can write code or book your next holiday – chatting to an AI agent working for a travel company to secure the best deal.
In future, 'multi-agent systems' will be able to collaborate and communicate to get things done, and we may also see 'embodied agents'.
Nvidia CEO Jensen Huang said in October 2024 that he hopes the company will one day employ 50,000 people, working with 100 million agents.
"AIs will recruit other AIs to solve problems. AIs will be in Slack channels with each other, and with humans," Huang said. "We'll just be one large employee base, if you will – some of them are digital and AI, and some of them are biological."
But if we're already entering an era where we'll be managing those AI agents and systems, what skills will we need?
We spoke to three experts to find out.
Discover How is the World Economic Forum creating guardrails for Artificial Intelligence? Show more In response to the uncertainties surrounding generative AI and the need for robust AI governance frameworks to ensure responsible and beneficial outcomes for all, the Forum’s Centre for the Fourth Industrial Revolution (C4IR) has launched the AI Governance Alliance. The Alliance unites industry leaders, governments, academic institutions, and civil society organizations to champion responsible global design and release of transparent and inclusive AI systems. This includes the workstreams part of the AI Transformation of Industries initiative, in collaboration with the Centre for Energy and Materials, the Centre for Advanced Manufacturing and Supply Chains, the Centre for Cybersecurity, the Centre for Nature and Climate, and the Global Industries team.
Checking after prompting is vital
The founder and CEO of Women in Tech Global, Ayumi Moore Aoki, says prompting is the core skill for managing AI: learning to define your question in a way that can be easily comprehended.
"But most importantly, you have to verify the answer. Don't take anything that's just given to you as if it were the truth. Check the answer and check the data where the answer was from. I know it's a lot of work, but honestly, it's so important."
Even in her own research work, Moore Aoki says she finds AI tools are hallucinating.
"I would say, 'give me the top academic papers in this field and the references'. But if you click on it and you go look at the data, it doesn't exist. It was false.
"So you have to check every single step ... I try to find the source of the data and interpret it myself. Sometimes our data is dirty, you can make it say so many different things, so finding the core and making your own decisions about it, your own reflections, is super important."
There is a huge risk from not checking sources, she adds.
"Misinformation can lead to drastic consequences because if you are making decisions with wrong information, then things can get bad."
Learning boundaries of trust
Babak Hodjat is the CTO AI at Cognizant, which has just open-sourced The Neuro AI Multi-Agent Accelerator to enable businesses to scale collaborative agent networks.
"I think the most important skill is going to be getting over our fear and being able to express what we expect from these systems and also to learn that boundary of trust. So how much and when can we trust these systems?
"As these systems get better and better, our challenge is going be that we might over-trust them. And so that's one of the skills we'll have to learn and teach our kids – where is that boundary."
More broadly, we have to be very careful about how we define these systems, "what threshold we set for what we are comfortable allowing the agent to decide autonomously and what we're not comfortable with", Hodjat explained.
"We also need to make sure that we have safeguards. And good governance over these systems so that, as they're operating in unknown situations, we can monitor them and make sure that they're doing what we expect them to do and they're aligned with our values."
How AI agents and multi-agent systems will interact. Image: World Economic Forum
Agents are only as good as their training
An AI agent is essentially just "a piece of code", says Jarah Euston, CEO and Co-Founder of AI-powered labour platform WorkWhile, which connects frontline workers to shifts.
"It may not have the same understanding, empathy, awareness of the politics of your organization, of the fears or concerns or ambitions of the people around that it is serving.
"So managers have to be aware that the agent is only as good as how you've trained it. I don't think we're close yet to having agents that can operate without any human oversight.
"As a manager, you want to leverage the AI to make you and your team more productive, but you constantly have to be checking, iterating and training your tools to get the most out of them."
Not paying enough attention to the AI agent can be counterproductive, she warns: "If the tool isn't effective, people will stop using it, so the biggest risk is the potential loss of productivity because your organization no longer trusts or believes in the agent or the AI.
"You also have to be patient. And you have to keep changing, experimenting, testing and iterating."
Loading...
Soft skills will be even more important
Employers expect 39% of key skills required in the job market will change by 2030, according to the Forum's Future of Jobs Report 2025, including AI management.
Technological skills are expected to become increasingly vital over the next five years, outpacing the growth of all other skill categories. Leading the way are AI and big data, followed closely by networking, cybersecurity and overall technological literacy.
The so-called 'soft skills' of creative thinking and resilience, flexibility and agility are also rising in importance, along with curiosity and lifelong learning.
Empathy is one skill AI agents can't learn, says Women in Tech's Moore Aoki, and she believes this will advantage women.
"AI is just prediction, there's no ghost behind the machine. It's just a formula of prediction. Whatever results they give, the human has to decide whether that answer is ethical, if it really represents society and if it represents the culture and the values of the company.
"This discernment and decision-making can be done only by humans, right? And I think women are good in making these decisions because they have empathy."
| 2023-01-01T00:00:00 |
https://www.weforum.org/stories/2025/07/leaders-will-soon-be-managing-ai-agents-these-are-the-skills-theyll-need/
|
[
{
"date": "2023/01/01",
"position": 69,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 62,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 68,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 64,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 63,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 77,
"query": "AI workers"
},
{
"date": "2023/10/01",
"position": 26,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 63,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 77,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 61,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 75,
"query": "AI workers"
},
{
"date": "2024/05/01",
"position": 63,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 67,
"query": "AI workers"
},
{
"date": "2024/11/01",
"position": 75,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 63,
"query": "AI workers"
}
] |
|
How Much Do Workers Really Need to Know About AI?
|
How Much Do Workers Really Need to Know About AI?
|
https://aimmediahouse.com
|
[
"Mukundan Sivaraj",
"Mukundan Is A Writer",
"Editor Covering The Ai Startup Ecosystem At Aim Media House. Reach Out To Him At Mukundan.Sivaraj Aimmediahouse.Com."
] |
Upskilling has become a go-to solution for AI-Human adaption, referring to helping workers build new skills as technology evolves. But the term ...
|
Join tech and business leaders who read AIM every day. Unlimited articles
Subscriber-only newsletters
No ad distraction
Please upgrade your account to read the rest of this content and gain unlimited access to all of our content, newsletters, invitations and events updates Subscribe now or log in your existing account
According to EY Americas Consulting’s CTO, Jason Noel, the workforce doesn’t necessarily need to upskill for AI. “This idea of up-skilling the entire workforce to use AI,” he told Business Insider, “I think it's kind of silly.” This seems like the opposite of what we’ve been hearing for the past few years, but it does happen to highlight a practical challenge many companies are dealing with today: how much do workers actually need to know about artificial intelligence to make use of it? Upskilling has become a go-to solution for AI-Human adaption, referring to helping workers build new skills as technology evolves. But the term has taken on a broad meaning. Does it mean learning to code? Understanding how machine learning works? Or just getting comfortable with a new inter
| 2025-07-07T00:00:00 |
2025/07/07
|
https://aimmediahouse.com/market-industry/how-much-do-workers-really-need-to-know-about-ai
|
[
{
"date": "2023/01/01",
"position": 73,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 70,
"query": "AI workers"
}
] |
AI is coming for entry-level jobs. Everybody needs to get ready.
|
AI is coming for entry-level jobs. U.S. needs a new talent pipeline. - The Washington Post
|
https://www.washingtonpost.com
|
[
"Editorial Board",
"David Ignatius",
"Beatrix",
"Maya Scarpa",
"Bill Cassidy",
"Tim Kaine"
] |
AI may replace a lot of entry-level skills. So how will workers acquire more advanced ones?
|
Is the great AI disruption happening? Have we reached the point where AI starts displacing lots of workers? AI watchers know to ask these questions as jobs numbers roll in — but no one knows when they will be answered and what the jobs market will look like when they are.
Certainly, CEOs are saying that AI is coming for a lot of jobs, and soon — perhaps as many as half of all white-collar workers. That’s likely to show up first in entry-level jobs, where the basic skills required are the easiest to replicate, and in tech, where the ability to rapidly adapt the latest software tools is itself an entry-level job requirement. Sure enough, in recent years unemployment has risen fastest among new college graduates, which spurred LinkedIn executive Aneesh Raman to write that the bottom rungs of the white-collar career ladder are “breaking.”
As Raman concedes, however, “we haven’t yet seen definitive evidence that A.I. is the reason for the shaky entry-level job market.” An analysis by the Economist suggests that the “relative unemployment” of young college graduates — the ratio of their unemployment rate to the general jobless figures — began rising in 2009, well before the first chatbots were released. Nor has there been any appreciable decline in the share of workers doing office jobs.
Advertisement
So, no, it may not be happening yet — at least not enough to leave definite patterns in the economic data. But if CEOs driving this change are to be believed, it is likely to eventually. Yet it doesn’t have to be a disaster. Educators, CEOs and policymakers should start thinking now about what will replace the entry-level job — not just for the workers who need a way to support themselves, but for the companies who will still need skilled mid- and high-level employees long after AI has automated away data entry and basic report-writing.
Those workers, in turn, will need the human capital that is typically acquired by laboring in the trenches. That includes obvious things such as technical skills, knowledge of their industry and a professional network, but also a lot of tacit knowledge that is absorbed by watching your elders work and hearing their war stories: What are the most common pitfalls in our industry? Where are the ethical gray areas, and how do we resolve questions that fall into them? What does good management look like? What’s the best way to handle conflicts with difficult co-workers? How should we balance competing priorities?
None of this can be taught by a book, or by a LLM course. This know-how is transmitted human to human, in real time and in real life. Until now, that hasn’t been a problem, because young employees doing grunt work picked up human capital along with their paycheck.
Advertisement
AI disruption threatens that process. Entry-level workers’ paychecks will be the first and most obvious casualties, but companies will feel the disruption soon enough as they try to hire the next generation of skilled mid-level workers and realize the economy has stopped cultivating them. If they are wise, they will look beyond the dazzling immediate possibility of smaller payrolls and think about developing the talent they’ll need to stay competitive in the future.
A brand-new talent pipeline will not be built by editorialists or researchers sitting in their offices, spinning out theoretical possibilities. Bosses who know what they need the pipeline to deliver and are willing to endure some patient trial and error to get it working, will construct it.
As they work, however, they should partner with the operators of one of our biggest existing pipelines, the American university system. Universities have been successfully delivering fresh talent to companies for decades. Now, in the face of AI, they need to reimagine what they do.
Advertisement
This doesn’t just mean fighting chatbot-enabled cheating. The bigger threat to the higher education system as we know it is that many of the skills colleges develop, such as the ability to do basic research or write coherent prose, will be devalued in the job market as AI takes over. On the other hand, other skills universities cultivate — such as critical thinking and analysis of text — could empower graduates to use and evaluate AI tools.
A job credential is not the only reason to pursue higher education. But the wage premium for college graduates is why so many people have been willing to pay steadily increasing tuition to secure one. In 1940, fewer than 5 percent of Americans had completed a college degree. By 2017, that figure had expanded to a third of the population. That shift didn’t just benefit the students who enhanced their intellectual capacities and their earning power; it also enabled a massive expansion of the higher education system and its other, nonpecuniary missions, such as developing engaged citizens and preserving and extending human knowledge.
Those missions will be threatened unless universities can figure out how to teach different skills, ones that AI can’t master. Otherwise, the value of a college diploma will fall, and many schools will close.
| 2025-07-08T00:00:00 |
2025/07/08
|
https://www.washingtonpost.com/opinions/2025/07/08/ai-entry-level-jobs-talent/
|
[
{
"date": "2023/01/01",
"position": 75,
"query": "AI workers"
},
{
"date": "2023/02/01",
"position": 6,
"query": "AI unemployment rate"
},
{
"date": "2023/03/01",
"position": 72,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 7,
"query": "AI unemployment rate"
},
{
"date": "2023/04/01",
"position": 93,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 11,
"query": "AI unemployment rate"
},
{
"date": "2023/05/01",
"position": 88,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 88,
"query": "AI workers"
},
{
"date": "2023/07/01",
"position": 11,
"query": "AI unemployment rate"
},
{
"date": "2023/08/01",
"position": 10,
"query": "AI unemployment rate"
},
{
"date": "2023/09/01",
"position": 12,
"query": "AI unemployment rate"
},
{
"date": "2023/09/01",
"position": 87,
"query": "AI workers"
},
{
"date": "2023/10/01",
"position": 21,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 11,
"query": "AI unemployment rate"
},
{
"date": "2023/11/01",
"position": 87,
"query": "AI workers"
},
{
"date": "2023/12/01",
"position": 11,
"query": "AI unemployment rate"
},
{
"date": "2024/01/01",
"position": 87,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 86,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 87,
"query": "AI workers"
},
{
"date": "2024/05/01",
"position": 12,
"query": "AI unemployment rate"
},
{
"date": "2024/05/01",
"position": 87,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 92,
"query": "AI workers"
},
{
"date": "2024/08/01",
"position": 10,
"query": "AI unemployment rate"
},
{
"date": "2024/09/01",
"position": 12,
"query": "AI unemployment rate"
},
{
"date": "2024/11/01",
"position": 87,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 84,
"query": "AI workers"
},
{
"date": "2025/04/01",
"position": 88,
"query": "AI unemployment rate"
}
] |
Companies keep slashing jobs. How worried should workers be ...
|
Companies keep slashing jobs. How worried should workers be about AI replacing them?
|
https://www.timeswv.com
|
[
"Queenie Wong",
"Los Angeles Times",
"Photo Noah Berger Getty Images"
] |
LOS ANGELES (TNS)— Tech companies that are cutting jobs and leaning more on artificial intelligence are also disrupting themselves.
|
Fairmont, WV (26555)
Today
Thunderstorms this evening with some fog possible late. Low 68F. Winds light and variable. Chance of rain 70%..
Tonight
Thunderstorms this evening with some fog possible late. Low 68F. Winds light and variable. Chance of rain 70%.
| 2023-01-01T00:00:00 |
https://www.timeswv.com/news/business/companies-keep-slashing-jobs-how-worried-should-workers-be-about-ai-replacing-them/article_66af0106-c21d-4080-8bde-e035398e3a09.html
|
[
{
"date": "2023/01/01",
"position": 78,
"query": "AI workers"
},
{
"date": "2023/02/01",
"position": 69,
"query": "AI replacing workers"
},
{
"date": "2023/03/01",
"position": 67,
"query": "AI replacing workers"
},
{
"date": "2023/03/01",
"position": 73,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 92,
"query": "AI replacing workers"
},
{
"date": "2023/06/01",
"position": 93,
"query": "AI replacing workers"
},
{
"date": "2023/08/01",
"position": 91,
"query": "AI replacing workers"
},
{
"date": "2023/09/01",
"position": 92,
"query": "AI replacing workers"
},
{
"date": "2023/10/01",
"position": 92,
"query": "AI replacing workers"
},
{
"date": "2023/11/01",
"position": 98,
"query": "AI replacing workers"
},
{
"date": "2023/12/01",
"position": 91,
"query": "AI replacing workers"
},
{
"date": "2024/02/01",
"position": 84,
"query": "AI replacing workers"
},
{
"date": "2024/03/01",
"position": 84,
"query": "AI replacing workers"
},
{
"date": "2024/04/01",
"position": 94,
"query": "AI replacing workers"
},
{
"date": "2024/05/01",
"position": 88,
"query": "AI replacing workers"
},
{
"date": "2024/06/01",
"position": 89,
"query": "AI replacing workers"
},
{
"date": "2024/07/01",
"position": 93,
"query": "AI replacing workers"
},
{
"date": "2024/10/01",
"position": 94,
"query": "AI replacing workers"
},
{
"date": "2024/11/01",
"position": 89,
"query": "AI replacing workers"
},
{
"date": "2024/12/01",
"position": 81,
"query": "AI replacing workers"
},
{
"date": "2025/01/01",
"position": 97,
"query": "AI replacing workers"
}
] |
|
10 jobs AI will replace and what workers can do instead
|
10 jobs AI will replace and what workers can do instead
|
https://azbigmedia.com
|
[
"Az Business Magazine"
] |
There is no doubt that there are jobs AI will replace, but there are things workers can do to prepare. Here is a closer look.
|
There is no doubt that there are jobs AI will replace, but there are things workers can do to prepare. AI is no longer a distant threat; it’s reshaping job security, skills priorities, and career plans:
To help job seekers keep up with the changing landscape, LiveCareerUK, a CV builder service, has released its Jobs AI Will Replace Report, which outlines the 10 professions most likely to be displaced by AI, and offers expert guidance on resilient career paths workers can pivot to instead.
LOCAL NEWS: 100 best places to work and live in Arizona for 2025
INDUSTRY INSIGHTS: Want more news like this? Get our free newsletter here
1. Data Entry Clerks
What to do instead: Reskill in data analysis or data management
Learn Excel, SQL, or Python to shift into roles that interpret and act on data, not just record it.
2. Telemarketers
What to do instead: Reskill in digital marketing or customer success
Build skills in CRM tools, social media engagement, and sales strategy to stay valuable in a human-centered sales role.
3. Basic Customer Service Representatives
What to do instead: Reskill in technical support or customer success
Focus on more complex problem-solving roles that require empathy, expertise, and relationship-building.
4. Retail Cashiers
What to do instead: Reskill in retail management or supply chain operations
Move into areas that require strategic thinking, leadership, or technical know-how in the retail ecosystem.
5. Proofreaders and Copy Editors
What to do instead: Reskill in content strategy or digital marketing
Leverage your writing instincts in higher-order tasks like brand storytelling, SEO, and campaign planning.
6. Paralegals and Legal Assistants
What to do instead: Reskill in legal tech, compliance, or litigation support
Apply your legal knowledge in tech-forward fields that blend law with AI and automation tools.
7. Bookkeepers
What to do instead: Reskill in financial analysis or advisory roles
Move beyond basic number-crunching to deliver strategic insights that businesses can act on.
8. Fast Food and Restaurant Frontline Workers
What to do instead: Reskill in culinary innovation or restaurant management
Creativity, leadership, and operations knowledge will always be in demand, even if robots flip the burgers.
9. Warehouse Workers
What to do instead: Reskill in logistics coordination or warehouse technology roles
Learn to operate, oversee, or improve the systems that are replacing repetitive labor.
10. Entry-Level Market Research Analysts
What to do instead: Reskill in business analytics or data storytelling
Go beyond data collection by learning to turn insights into decisions with tools like Tableau, Power BI, or Python.
| 2025-07-14T00:00:00 |
2025/07/14
|
https://azbigmedia.com/business/10-jobs-ai-will-replace-and-what-workers-can-do-instead/
|
[
{
"date": "2023/01/01",
"position": 82,
"query": "AI workers"
},
{
"date": "2023/02/01",
"position": 58,
"query": "AI replacing workers"
},
{
"date": "2023/03/01",
"position": 58,
"query": "AI replacing workers"
},
{
"date": "2023/03/01",
"position": 77,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 71,
"query": "AI replacing workers"
},
{
"date": "2023/04/01",
"position": 90,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 87,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 65,
"query": "AI replacing workers"
},
{
"date": "2023/06/01",
"position": 87,
"query": "AI workers"
},
{
"date": "2023/08/01",
"position": 64,
"query": "AI replacing workers"
},
{
"date": "2023/09/01",
"position": 64,
"query": "AI replacing workers"
},
{
"date": "2023/09/01",
"position": 88,
"query": "AI workers"
},
{
"date": "2023/10/01",
"position": 63,
"query": "AI replacing workers"
},
{
"date": "2023/10/01",
"position": 97,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 68,
"query": "AI replacing workers"
},
{
"date": "2023/11/01",
"position": 90,
"query": "AI workers"
},
{
"date": "2023/12/01",
"position": 62,
"query": "AI replacing workers"
},
{
"date": "2024/01/01",
"position": 61,
"query": "AI replacing workers"
},
{
"date": "2024/01/01",
"position": 88,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 52,
"query": "AI replacing workers"
},
{
"date": "2024/02/01",
"position": 88,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 58,
"query": "AI replacing workers"
},
{
"date": "2024/03/01",
"position": 88,
"query": "AI workers"
},
{
"date": "2024/04/01",
"position": 67,
"query": "AI replacing workers"
},
{
"date": "2024/05/01",
"position": 63,
"query": "AI replacing workers"
},
{
"date": "2024/05/01",
"position": 90,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 62,
"query": "AI replacing workers"
},
{
"date": "2024/06/01",
"position": 93,
"query": "AI workers"
},
{
"date": "2024/07/01",
"position": 65,
"query": "AI replacing workers"
},
{
"date": "2024/10/01",
"position": 62,
"query": "AI replacing workers"
},
{
"date": "2024/11/01",
"position": 63,
"query": "AI replacing workers"
},
{
"date": "2024/11/01",
"position": 86,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 49,
"query": "AI replacing workers"
},
{
"date": "2024/12/01",
"position": 86,
"query": "AI workers"
},
{
"date": "2025/01/01",
"position": 69,
"query": "AI replacing workers"
},
{
"date": "2025/02/01",
"position": 77,
"query": "AI replacing workers"
},
{
"date": "2025/04/01",
"position": 66,
"query": "AI replacing workers"
},
{
"date": "2025/05/01",
"position": 74,
"query": "AI replacing workers"
},
{
"date": "2025/06/01",
"position": 79,
"query": "AI replacing workers"
}
] |
Laid-off workers should use AI to manage their emotions, says Xbox ...
|
Laid-off workers should use AI to manage their emotions, says Xbox producer
|
https://www.theverge.com
|
[
"Jess Weatherbed"
] |
Xbox producer Matt Turnbull suggested using AI to “help reduce the emotional and cognitive load that comes with job loss” before deleting ...
|
“These are really challenging times, and if you’re navigating a layoff or even quietly preparing for one, you’re not alone and you don’t have to go it alone.
I know these types of tools engender strong feelings in people, but I’d be remiss in not trying to offer the best advice I can under the circumstances. I’ve been experimenting with ways to use LLM AI tools (like ChatGPT or Copilot) to help reduce the emotional and cognitive load that comes with job loss.
Here are some prompt ideas and use cases that might help if you’re feeling overwhelmed:
Career Planning Prompts:
“Act as a career coach. I’ve been laid off from a [role] in the game industry. Help me build a 30-day plan to regroup, research new roles, and start applying without burning out.”
“What kinds of game industry jobs could I pivot to with experience in [Production/Narrative/LiveOps/etc.]?”
Resume & Linkedin Help
“Here’s my current resume. Give me three tailored versions: one for AAA, one for platform/publishing roles, and one for startup/small studio leadership.”
“Rewrite this resume bullet to highlight impact and metrics.”
“Draft a new LinkedIn ‘About Me’ section that focuses on my leadership style, shipped titles, and vision for game development.”
Networking & Outreach
“Draft a friendly message I can send to old coworkers letting them know I’m exploring new opportunities.”
“Write a warm intro message for reaching out to someone at [studio name] about a job posting.”
Emotional Clarity & Confidence
“I’m struggling with imposter syndrome after being laid off. Can you help me reframe this experience in a way that reminds me what I’m good at?”
No Al tool is a replacement for your voice or your lived experience. But at a time when mental energy is scarce, these tools can help get you unstuck faster, calmer, and with more clarity.
If this helps, feel free to share with others in your network.
Stay kind, stay smart, stay connected.”
| 2025-07-04T00:00:00 |
2025/07/04
|
https://www.theverge.com/news/698468/xbox-exec-reccommends-ai-to-laid-off-staff
|
[
{
"date": "2023/01/01",
"position": 84,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 80,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 48,
"query": "AI layoffs"
},
{
"date": "2023/04/01",
"position": 45,
"query": "AI layoffs"
},
{
"date": "2023/04/01",
"position": 92,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 45,
"query": "AI layoffs"
},
{
"date": "2023/05/01",
"position": 90,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 47,
"query": "AI layoffs"
},
{
"date": "2023/06/01",
"position": 90,
"query": "AI workers"
},
{
"date": "2023/07/01",
"position": 42,
"query": "AI layoffs"
},
{
"date": "2023/09/01",
"position": 46,
"query": "AI layoffs"
},
{
"date": "2023/09/01",
"position": 89,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 44,
"query": "AI layoffs"
},
{
"date": "2023/11/01",
"position": 89,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 45,
"query": "AI layoffs"
},
{
"date": "2024/01/01",
"position": 89,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 87,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 89,
"query": "AI workers"
},
{
"date": "2024/05/01",
"position": 43,
"query": "AI layoffs"
},
{
"date": "2024/05/01",
"position": 89,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 44,
"query": "AI layoffs"
},
{
"date": "2024/06/01",
"position": 94,
"query": "AI workers"
},
{
"date": "2024/07/01",
"position": 41,
"query": "AI layoffs"
},
{
"date": "2024/08/01",
"position": 44,
"query": "AI layoffs"
},
{
"date": "2024/11/01",
"position": 89,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 41,
"query": "AI layoffs"
},
{
"date": "2024/12/01",
"position": 85,
"query": "AI workers"
}
] |
Managers are using AI to hire and fire workers, survey finds - Yahoo
|
Managers are using AI to hire and fire workers, survey finds
|
https://www.yahoo.com
|
[] |
A growing number of managers in the U.S. are turning to artificial intelligence to make key personnel decisions, according to a new survey ...
|
A growing number of managers in the U.S. are turning to artificial intelligence to make key personnel decisions, according to a new survey by Resume Builder.
The survey found that 60% of managers use AI tools, such as ChatGPT, Microsoft Copilot and Google’s Gemini to help determine hiring, promotions, raises and even terminations.
Of those, 94% said they rely on AI to evaluate their direct reports.
Despite the widespread use, two-thirds of managers admitted they’ve received no formal training on using AI for people management. About 20% said they allow AI to make decisions without human oversight.
Advertisement Advertisement
Advertisement Advertisement
Experts warn that this trend could lead to biased or unfair practices and may be susceptible to manipulation. In response, a California lawmaker has proposed the “No Robo Bosses Act,” which would require human review of AI-driven employment decisions.
Copyright 2025 Nexstar Media, Inc. All rights reserved. This material may not be published, broadcast, rewritten, or redistributed.
For the latest news, weather, sports, and streaming video, head to KTLA.
| 2023-01-01T00:00:00 |
https://www.yahoo.com/news/managers-using-ai-hire-fire-155700570.html
|
[
{
"date": "2023/01/01",
"position": 85,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 78,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 97,
"query": "AI workers"
}
] |
|
Sam Altman's AI Empire Relies on Brutal Labor Exploitation - Jacobin
|
Sam Altman’s AI Empire Relies on Brutal Labor Exploitation
|
https://jacobin.com
|
[
"Ben Wray",
"Doug Henwood",
"Ramaa Vasudevan",
"David Calnitsky",
"David Moscrop",
"Marianela D Aprile",
"Hamilton Nolan"
] |
Firms like OpenAI are developing AI in a way that has deeply ominous implications for workers in many different fields.
|
Review of Empire of AI: Dreams and Nightmares in Sam Altman’s OpenAI by Karen Hao (Penguin Press, 2025)
Artificial intelligence (AI) is quite possibly the most hyped technology in history. For well over half a century, the potential for AI to replace most or all human skills has crisscrossed in the public imagination between sci-fi fantasy and scientific mission. From the predictive AI of the 2000s that brought us search engines and apps, to the generative AI of the 2020s that is bringing us chatbots and deepfakes, every iteration of AI is apparently one more leap toward the summit of human-comparable AI, or what is now widely termed Artificial General Intelligence (AGI). The strength of Karen Hao’s detailed analysis of America’s AI industry, Empire of AI, is that her relentlessly grounded approach refuses to play the game of the AI hype merchants. Hao makes a convincing case that it is wrong to focus on hypotheticals about the future of AI when its present incarnation is fraught with so many problems. She also stresses that exaggerated “doomer” and “boomer” perspectives on what is coming down the line both end up helping the titans of the industry to build a present and future for AI that best serves their interests. Moreover, AI is a process, not a destination. The AI we have today is itself the product of path dependencies based on the ideologies, infrastructure, and IPs that dominate in Silicon Valley. As such, AI is being routed down a highly oligopolistic developmental path, one that is designed deliberately to minimize market competition and concentrate power in the hands of a very small number of American corporate executives. However, the future of AI remains contested territory. In what has come as a shock to the Silicon Valley bubble, China has emerged as a serious rival to US AI dominance. As such, AI has now moved to the front and center of great-power politics in a way comparable to the nuclear and space races of the past. To understand where AI is and where it is going, we must situate analysis of the technology within the wider economic and geopolitical context in which the United States finds itself.
OpenAI’s Metamorphosis Hao’s story revolves around OpenAI, the San Francisco company most famous for ChatGPT, the AI chatbot that brought generative AI to the world’s attention. Through the trials and tribulations of its CEO Sam Altman, we are brought into a world of Machiavellian deceit and manipulation, where highfalutin moral ambition collides constantly with the brutal realities of corporate power. Altman survives the various storms that come his way, but only by junking everything he once claimed to believe in. AI has now moved to the front and center of great-power politics in a way comparable to the nuclear and space races of the past. OpenAI began with the mission of “building AGI that benefits humanity” as a nonprofit that would collaborate with others through openly sharing its research, without developing any commercial products. This objective stemmed from the convictions of Altman and OpenAI’s first major patron, Elon Musk, who believed that AI posed major risks to the world if it was developed in the wrong way. AI therefore required cautious development and tight government regulation to keep it under control. OpenAI was thus a product of AI’s “doomer” faction. The idea was to be the first to develop AGI in order to be best positioned to rein it in. The fact that Altman would end up flipping OpenAI 180 degrees — creating a for-profit company that produces proprietary software, based on extreme levels of corporate secrecy and shark-like determination to outcompete its rivals in the speed of AI commercialization, regardless of the risks — testifies to his capacity to mutate into whatever he needs to be in the pursuit of wealth and power. The motivation for the first shift toward what OpenAI would eventually become came from strategic considerations in relation to its doctrine of AI development, called “scaling.” The idea behind scaling was that AI could advance by leaps and bounds simply through the brute force of massive data power. This reflected a devout belief in “connectionism,” a school of AI development that was much easier to commercialize than its rival (“symbolism”). The connectionists believed that the key to AI was to create “neural networks,” digital approximations of real neurons in the human brain. OpenAI’s big thinkers, most importantly its first chief scientist Ilya Sutskever, believed that if the firm had more data-processing nodes (“neurons”) available to it than anyone else, it would position itself at the cutting edge of AI development. The problem was that scaling, an intrinsically data-intensive strategy, required a huge amount of capital — much more than a nonprofit was capable of attracting. Driven by the need to scale, OpenAI created a for-profit arm in 2019 to raise capital and build commercial products. As soon as it did so, there was a scramble between Altman and Musk to take over as CEO. Altman won out and Musk, having been sidelined, turned from ally to enemy overnight, accusing Altman of raising funds as a nonprofit under false pretenses. This was a criticism that would later develop into litigation against OpenAI. But Musk’s ideological justification for the split was an afterthought. If he had won the power struggle, the world’s richest man planned to lash OpenAI to his electric car company, Tesla. Whoever became CEO, OpenAI was on an irreversible path toward becoming just like any other Big Tech giant.
Generative AI Yet because of the company’s origins, it was left with a strange governance structure that gave board-level control to an almost irrelevant nonprofit arm, based on the ludicrous pretense that, despite its newly embraced profit motive, OpenAI’s mission was still to build AGI for humanity. The Effective Altruism (EA) movement gave a veneer of coherence to the Orwellian ideological precepts of OpenAI. EA promotes the idea that the best way of doing good is to become as rich as possible and then give your money to philanthropic causes. This junk philosophy found massive support in Silicon Valley, where the idea of pursuing maximum wealth accumulation and justifying it on moral terms was highly convenient. Altman, who in 2025 glad-handed Saudi Prince Mohammed Bin Salman alongside Trump just after the despotic ruler announced his own AI venture, epitomizes the inevitable endgame of EA posturing: power inevitably becomes its own purpose. Effective Altruism promotes the idea that the best way of doing good is to become as rich as possible and then give your money to philanthropic causes. Just four months after the for-profit launched, Altman secured a $1 billion investment from Microsoft. With Musk out of the picture, OpenAI found an alternative Big Tech benefactor to fund its scaling. More willing to trample on data protection rules than big competitors like Google, OpenAI began to extract data from anywhere and everywhere, with little care for its quality or content — a classic tech start-up “disruptor” mentality, akin to Uber or Airbnb. This data bounty was the raw material that fueled OpenAI’s scaling. Driven by a desire to impress Microsoft founder and former CEO Bill Gates, who wanted to see OpenAI create a chatbot that would be useful for research, the company developed ChatGPT, expecting it to be moderately successful. To everyone’s surprise, within two months ChatGPT became the fastest-growing consumer app in history. The generative AI era was born. From that point onward, OpenAI became relentlessly focused on commercialization. But the shockwaves of ChatGPT were felt well beyond the company. Scaling became the standard-bearer for AI development: observers deemed whichever company could marshal the greatest amount of “compute” (data power) to be the likely winner of the AI tech race. Alphabet and Meta started to spend sums on AI development that dwarfed those marshalled by the US Government and the European Commission. As Big Tech raced to get ahead on generative AI, the funding rush swept up almost all of the talent in the field. This transformed the nature of AI research, including in universities, with leading professors increasingly tied to one of the Big Tech players. As the stakes grew higher, research from within companies became increasingly secretive and dissent frowned upon. Corporate proprietary walls were dividing up the field of AI development. We have to place this heavily commodified form of AI development within its overall conjuncture. If generative AI was developed in the US in the 1950s, it would have gone years or even decades being largely backed by US military R&D budgets. Even after it had undergone commercialization, the state would have remained the main purchaser of the technology for decades. This was the developmental path of semiconductors. However, in the 2020s, at the tail end of the neoliberal era, it is the corporate–state nexus that drives and frames technological development in the United States, reducing incentives for long-term thinking, and stunting any open, pedagogical process of scientific inquiry. That will have long-term consequences for how AI is developed that are unlikely to be positive, whether for society in general or for American global leadership in particular.
AI and Labor One of the myths of AI is that it is a technology that does not rely on workers. There are essentially three parts to the generative AI re-production process: extracting the data, crunching the data, and testing or fixing the data. The extraction part relies on dead, rather than living, labor. For example, OpenAI scraped data from LibraryGenesis, an online repository of books and scholarly articles, making use of centuries of intellectual labor for free. One of the myths of AI is that it is a technology that does not rely on workers. The crunching data part of generative AI is all about computing power, which relies on labor only to the extent that the infrastructure required for “compute,” most importantly data centers, is based on a long digital value chain that includes Taiwanese chip manufacturers and Chilean copper miners. While the testing and fixing of the data is the part of generative AI re-production that is most often forgotten about, it is also the part that is most directly dependent on workers. There are two types of digital workers required for testing and fixing the enormous data requirements of generative AI. The first are click workers, also known as data annotators (or data labelers). These are gig workers who earn piece rates for completing short digital tasks, such as categorizing what is contained in an image. Click workers are vital because without them, AI systems like ChatGPT would be riddled with errors, especially when it comes to “edge cases”: rare or unusual situations that sit at the boundaries of AI’s categorization parameters. Click workers turn the data of generative AI systems from low grade to high quality. This is especially important for OpenAI, since so much of the company’s data has been extracted from the gutters of the internet. The barriers to entry for click work are extremely low, because anyone who can access the internet can perform the most basic tasks. Click workers are operating in a global labor market with little connection to their fellow workers, meaning they have very limited leverage over their digital bosses. As such, the pay rates are rock-bottom and the conditions as precarious as it gets. Hao finds that Venezuela became the global hotbed of click work for a period of time, due to its high education levels, good internet access, and massive economic crisis. The tough US sanctions on Venezuela didn’t preclude its AI companies from exploiting the South American country’s desperate and impoverished workforce. Once click-work outsourcing firms like RemoTasks feel that they have maximized the labor exploitation of one crisis-hit country, or start to face resistance over working conditions, they simply “robo-fire” workers from that location and bring workers from somewhere else on board. The second type of worker in the AI industry is the content moderator. Because OpenAI and other AI companies are scraping the detritus of the internet for data, a substantial portion is saturated with racism, sexism, child pornography, fascist views, and every other ugly thing one can think of. A version of AI that doesn’t have the horrors of the internet filtered out will develop these characteristics in its responses; indeed, earlier versions of what would become ChatGPT did produce neo-Nazi propaganda, alarming OpenAI’s compliance team. The solution has been to turn to human content moderators to extract the filth out of the AI’s system, in the same way content moderators have been tasked for years now with policing social media content. Unlike click workers, the content moderator workforce tends to be subject to a regime of digital Taylorism, rather than one of piece work. This takes the form of a call center-style setup where workers are motivated by bonuses in target-driven environments, all the time under the watchful eyes of human supervisors and digital surveillance.
Into the Abyss Like the click workers, they are completing small digital tasks by annotating data, but the data they are annotating consists of the vilest content humans can produce. Because they are training the AI, it’s necessary for content moderators to look closely at all the gory details that flash up on their screen in order to label each part correctly. Being exposed to this repeatedly and exhaustively is a mental health nightmare. Hao follows the story of Mophat Okinyi, a Kenyan content moderator working for outsourcing firm Sama, moderating Meta and OpenAI content. The longer Okinyi worked for Sama, the more his behavior became erratic and his personality changed, destroying his relationship and leading to spiraling costs for mental health support. It’s necessary for content moderators to look closely at all the gory details that flash up on their screen in order to label each part correctly. Having reported on content moderation myself, I know that Okinyi’s case is by no means exceptional. It is the norm for content moderators to have their minds systematically broken down by the relentless brutality they must witness repeatedly just to do their job. While most click work and content moderation is done in the Global South, there are signs that as AI becomes more complex, it will increasingly need data workers in the Global North as well. The main reason for this is the increasing importance of Reinforcement Learning from Human Feedback (RLHF) to AI development. RLHF is a more complex form of data annotation, because click workers need to compare two responses from an AI and be able to explain why one is better than the other. As AI tools are developed for specific industries, the need for specialist expertise as well as an understanding of culturally specific cues means that RLHF increasingly requires high-skill workers to enter the AI industry. In keeping with the style of the book, Hao does not speculate on where RLHF might lead, but it is worth briefly considering its potential impact on the future of work. If generative AI tools can produce content which is as good as or better than material from a human, then it is not inconceivable that such tools could replace the worker in any content-producing industry. However, that would not mean that the skills of those workers would disappear entirely: there would still be a need, for example, for paralegals, but their job would be to test and fix the paralegal AI. At that point, these professional service-sector jobs would be exposed to the Uberized model of work that click workers in the Global South have now experienced for years. It’s not for nothing that Altman has said “there will be some change required to the social contract.” Of course, there remain significant question marks about generative AI’s true capacities in a wide range of content production. But wherever one sits on the scale between skeptic and true believer, there’s little doubt that AI will increasingly be relevant not only to the jobs of the most impoverished sections of the working class, but also to workers who are used to having some level of financial security due to their position higher up the labor-market ladder. The drawing of a much larger pool of workers into the precariat could have explosive social consequences.
Data Centers and DeepSeek AI’s effect on the environment is likely to be just as dramatic as its impact on labor, if not more so. Generative AI’s enormous data usage requires gigantic data centers rammed with high-energy usage GPU chips to service it. These data centers need vast amounts of land to build on and huge quantities of water to cool them down. As generative AI products become increasingly widely used, the ecological footprint of the industry expands relentlessly. AI’s effect on the environment is likely to be just as dramatic as its impact on labor, if not more so. Hao highlights some stunning statistics and predictions. Every AI-generated image has the equivalent energy consumption of charging a smartphone by 25 percent. AI’s water usage could match half of all the water used in the UK by 2027. By 2030, AI could be using more energy than all of India, the world’s third-largest consumer of electricity. The environmental consequences have already been significant. Iowa, two years into a drought, had Microsoft guzzling 11.5 million tonnes of the state’s potable water. Uruguay, a country that has experienced repeated droughts, saw mass protests after the courts forced its government to reveal the extent of the drinking water that Google’s data centers in the country were using. “This is not drought, it’s pillage,” graffiti in Montevideo reads. What makes the arrival of data centers en masse especially hard to stomach for local populations is the fact that they provide hardly any upsides. Data centers generate very few jobs in the places they are located, while draining local areas of their land and water, thus actively damaging more labor-intensive industries. In spite of this, following the logic of the scaling doctrine, we should expect data centers to grow ever bigger as “compute” expands to keep AI moving forward. While Altman has invested heavily in a nuclear fusion start-up as the golden ticket to abundant and free energy, just like AGI, it is a bet on a miracle cure tomorrow that distracts from the real problems AI scaling is causing today. However, in a rare bit of good news for the world’s ecology, the scaling doctrine received a hammerblow from the far east in January. DeepSeek, a Chinese generative AI chatbot, launched and quickly surpassed ChatGPT as the most downloaded app in the United States. The remarkable thing about DeepSeek is not what it did, but how it did it. The chatbot cost just $6 million to train — about one-fiftieth of the cost of ChatGPT, with a higher quality on some benchmarks. DeepSeek was trained on old GPU chips, designed by Nvidia to be of lower quality to comply with US chip export restrictions to China. Because of its efficiency, DeepSeek’s energy consumption is 90 percent lower than that of ChatGPT. The technical workings behind this engineering marvel were made open-source, so anyone could see how it was done. DeepSeek was a technological marvel and a geopolitical earthquake rolled into one. Not only did it mark China’s arrival as a tech superpower, but it also demonstrated that the scaling doctrine embraced by the whole of Silicon Valley as the go-to methodology for generative AI had proven to be behind the curve, at best. The shock that a Chinese company could embarrass Silicon Valley was so great that it triggered panic on Wall Street about whether the trillions already invested in American AI constituted a bet gone badly wrong. In one day, the fall in the market capitalization of tech stocks was equivalent to the entire financial value of Mexico. Even Donald Trump weighed in to say that DeepSeek’s emergence was “a wake-up call” for US Big Tech. On X, Altman struck a positive tone in response, but OpenAI quickly started to brief the press that DeepSeek might have “distilled” OpenAI’s models in creating its chatbot, though little has been heard about this claim since. In any case, distillation can’t explain the enormous efficiency gains of DeepSeek compared to OpenAI. It’s unfortunate that DeepSeek doesn’t appear in Empire of AI. Hao writes that she finished the book in January 2025, the month of DeepSeek’s launch. It would have been wise for the publisher to have given Hao a six-month extension to write a chapter on DeepSeek and the fallout in the US, especially considering how much of the book is a critique of the dogma that scaling is the only way to seriously develop AI. However, she has commented elsewhere on DeepSeek’s dramatic arrival and the flaws it reveals about the US AI industry: “DeepSeek has demonstrated that scaling up AI models relentlessly, a paradigm OpenAI introduced and champions, is not the only, and far from the best, way to develop AI.”
Alternatives DeepSeek also raised more profoundly ideological questions about AI development. If a Chinese company could develop cutting-edge tech on an open-source basis, giving everyone else the opportunity to test the underlying assumptions of their innovation and build on them, why were American companies busy constructing giant proprietary software cages around their tech — a form of enclosure that was bound to inhibit the speed of scientific progress? Some have started asking whether Chinese communism offers a better ecosystem for AI development than American capitalism. Both DeepSeek and ChatGPT operate based on capitalist business models, just with different principles of technical development. In fact, the question of open-source versus proprietary approaches just scratches the surface of the debates that society should be having about artificial intelligence. Ultimately, both DeepSeek and ChatGPT operate based on capitalist business models, just with different principles of technical development. While the Android open-source software operating system differentiates Google from Apple, no one today invests any hopes in Google as a model for socially just tech development. The bigger question we should be asking is this: if we can’t trust oligopolistic capitalist enterprises with a technology as powerful as this, how should AI be governed? Hao only really gets her teeth into this point in the book’s epilogue, “How the Empire Falls.” She takes inspiration from Te Hiku, a Māori AI speech recognition project. Te Hiku seeks to revitalize the te reo language through putting archived audio tapes of te reo speakers into an AI speech recognition model, teaching new generations of Māori who have few human teachers left. The tech has been developed on the basis of consent and active participation from the Māori community, and it is only licensed to organizations that respect Māori values. Hao believes Te Hiku shows there is “another way” of doing AI: Models can be small and task specific, their training data contained and knowable, ridding the incentives for widespread exploitative and psychologically harmful labor practices and the all-consuming extractivism of producing and running massive supercomputers. The creation of AI can be community driven, consensual, respectful of local context and history; its application can uplift and strengthen marginalised communities; its governance can be inclusive and democratic. More broadly, Hao says we should be aiming for “redistributing power” in AI along three axes: knowledge, resources, and influence. There should be greater funding for organizations pursuing new directions of AI research, holding Big Tech to account, or developing community-based AI tools like Te Hiku. There should also be transparency over AI training data, its environmental impact, supply chains, and land leases. Labor unions should be supported to develop power among data workers and workers whose jobs are under threat from automation. Finally, “broad-based education” is required to bust the myths surrounding AI, so that the public can come to a more grounded understanding of how AI tools are built, what their constraints are, and whose interests they serve.
Bringing the State Back In Although these are important ideas, in and of themselves they wouldn’t threaten the power of companies like OpenAI. The state is notably absent from Hao’s vision for bringing down the AI tech giants. The questions of how AI should be regulated and what ownership structure it should have go unexplored in Empire of AI. The state is notably absent from Karen Hao’s vision for bringing down the AI tech giants. Perhaps in the age of Trump there is a feeling of skepticism among progressives that the state can be anything other than a tool for entrenching the power of corporate elites. It is certainly hard not to be cynical when confronted with projects like Stargate, an OpenAI-backed private sector collaboration to invest $500 billion in AI infrastructure. Stargate is underpinned by a commitment from the Trump administration that it will bend and break regulations as necessary to ensure the project gets the energy supply it needs — a clear case of the state–corporate nexus working seamlessly, with little care about the consequences for society at large. Yet the left can’t sidestep the question of state power and AI. While projects like Te Hiku are no doubt valuable, by definition they cannot be scaled-up alternatives to the collective power of American AI capital, which commands resources far greater than many of the world’s states. If it becomes normal for AI tools like ChatGPT to be governed by and for Silicon Valley, we risk seeing the primary means of content production concentrated in the hands of a tiny number of tech barons. We therefore need to put big solutions on the table. Firstly, regulation: there must be a set of rules that place strict limits on where AI companies get their data from, how their models are trained, and how their algorithms are managed. In addition, all AI systems should be forced to operate within tightly regulated environmental limits: energy usage for generative AI cannot be a free-for-all on a planet under immense ecological stress. AI-powered automated weapons systems should be prohibited. All of this should be subject to stringent, independent audits to ensure compliance. Secondly, although the concentration of market power in the AI industry took a blow from DeepSeek’s arrival, there remain strong tendencies within AI — and indeed in digital tech as a whole — towards monopolization. Breaking up the tech oligarchy would mean eliminating gatekeepers that concentrate power and control data flows. Finally, the question of ownership should be a serious part of the debate. Te Hiku shows that when AI tools are built by organizations with entirely different incentive structures in place, they can produce wildly different results. As long as artificial intelligence is designed for the purposes of the competitive accumulation of capital, firms will continue to find ways to exploit labor, degrade the environment, take short cuts in data extraction, and compromise on safety, because if they don’t, one of their competitors will. It is possible to imagine a world where a socialized AI serves as a genuine aid to humanity. It would be one where instead of displacing jobs, AI would be designed to help workers reduce the amount of time they spend on technical and bureaucratic tasks, focusing human energies on problem-solving instead, and reducing the length of the working week. Rather than gobbling up water supplies, AI would function as a resource planning tool to help identify waste and duplication within and across energy systems. These possibilities are far removed from the fantasies of AGI, whereby artificial intelligence will supposedly become so powerful that it will resolve problems deeply embedded in the social relations of capitalism. Instead, this is a vision for AI that presupposes structural change.
| 2023-01-01T00:00:00 |
https://jacobin.com/2025/07/altman-openai-artificial-intelligence-labor-environment-deepseek
|
[
{
"date": "2023/01/01",
"position": 88,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 83,
"query": "AI workers"
}
] |
|
AI can provide 'emotional clarity and confidence' Xbox executive ...
|
AI can provide 'emotional clarity and confidence' Xbox executive producer tells staff after Microsoft lays off 9,000 employees
|
https://www.techradar.com
|
[
"Eric Hal Schwartz",
"Social Links Navigation"
] |
Microsoft has laid off 9,000 employees in recent months while investing heavily in AI. Microsoft has been hyping up its AI ambitions for the ...
|
An Xbox executive suggested that laid-off employees use AI for emotional support and career guidance
The suggestion sparked backlash and led the executive to delete their LinkedIn post
Microsoft has laid off 9,000 employees in recent months while investing heavily in AI.
Microsoft has been hyping up its AI ambitions for the last several years, but one executive's pitch about the power of AI to former employees who were recently let go has landed with an awkward thud.
Amid the largest round of layoffs in over two years, about 9,000 people, Matt Turnbull, Executive Producer at Xbox Game Studios Publishing, suggested that AI chatbots could help those affected process their grief, craft resumes, and rebuild their confidence.
The gesture was meant for support, but it left many game developers feeling outraged.
Turnbull took his possibly well-meaning but definitely poorly phrased and timed message to LinkedIn. He shared ideas for prompts to give an AI chatbot that he claimed might help laid-off colleagues navigate career uncertainty and emotional turbulence.
The backlash was swift and angry, leading him to delete the post, but you can still read it thanks to Brandon Sheffield's Bluesky post below.
Matt Turnbull, Executive Producer at Xbox Game Studios Publishing - after the Microsoft layoffs - suggesting on Linkedin that may maybe people who have been let go should turn to AI for help. He seriously thought posting this would be a good idea. — @brandon.insertcredit.com (@brandon.insertcredit.com.bsky.social) 2025-07-07T07:54:06.534Z
Turnbull urged colleagues to lean on AI to reduce the “emotional and cognitive load” of job loss in his post, along with the prompt ideas for 30-day recovery plans and LinkedIn messages. Probably the most eyebrow-raising suggestion was suggesting a prompt to help reframe impostor syndrome after being laid off.
“No AI tool is a replacement for your voice or lived experience," Turnbull wrote. "But in times when mental energy is scarce, these tools can help you get unstuck faster, calmer, and with more clarity.”
Get daily insight, inspiration and deals in your inbox Sign up for breaking news, reviews, opinion, top tech deals, and more. Contact me with news and offers from other Future brands Receive email from us on behalf of our trusted partners or sponsors
Even the most charitable interpretation of his post can't overlook just how condescending and poorly timed the advice is. And angry game developers flooded the comments, likely leading to the deletion of the post.
To put it mildly, they don't agree that being laid off is an emotional puzzle best solved with an algorithm. Instead, perhaps a human might understand the career and life upheaval it represents, and how that requires human compassion, support networks, and tangible help, like, say, an introduction to someone who can help you get a new job.
AI therapy
This incident is even worse in the context of Microsoft spending billions building AI infrastructure while dramatically shrinking its gaming teams. Urging laid-off developers to lean on AI right after losing their jobs is more than hypocritical; it's telling people to use the very technology that may have caused their job loss.
To be scrupulously and overly fair to Turnbull, using AI could help with some mental health concerns and might be useful in improving a resume or preparing for a job interview. Making AI part of outplacement services isn't a horrible idea. It could boost the internal coaching and career-transition arm Microsoft offers already, adding to the recruiters, résumé workshops, and counselling it offers. But it can't and shouldn't replace those human services. And having one of the people who let you go tell you to use AI to find a new job is the opposite of supportive. It's just an insult on top of injury.
Microsoft’s dual approach of laying people off and doubling down on AI infrastructure is a test of its company culture as much as its technical ability. Will we see a new standard where layoffs come with AI prompt packages instead of counseling and severance? If the message is, “Feel free to use chatbots to help you after we fire you,” expect plenty more outrageous, tone-deaf nonsense from executives.
Perhaps they should ask those chatbots how to interact with human beings without angering them, since it's a lesson they haven't learned well.
| 2025-07-07T00:00:00 |
2025/07/07
|
https://www.techradar.com/computing/artificial-intelligence/ai-can-provide-emotional-clarity-and-confidence-xbox-executive-producer-tells-staff-after-microsoft-lays-off-9-000-employees
|
[
{
"date": "2023/01/01",
"position": 94,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 90,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 88,
"query": "AI layoffs"
},
{
"date": "2023/05/01",
"position": 95,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 95,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 95,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 93,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 95,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 95,
"query": "AI workers"
},
{
"date": "2024/05/01",
"position": 93,
"query": "AI workers"
},
{
"date": "2024/11/01",
"position": 95,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 91,
"query": "AI workers"
},
{
"date": "2025/04/01",
"position": 94,
"query": "artificial intelligence layoffs"
},
{
"date": "2025/06/01",
"position": 75,
"query": "artificial intelligence layoffs"
}
] |
Microsoft laid off 9,000 workers to fund AI. Now that talent could use ...
|
Microsoft laid off 9,000 workers to fund AI. Now that talent could use AI to outplay Microsoft
|
https://www.freelanceinformer.com
|
[
"Katherine Steiner-Dicks"
] |
Microsoft is among the latest tech companies to lay off workers to fund AI ambitions. But with so much concentrated talent out on the market ...
|
Thousands of highly talented people out of work could go one of two ways.
Microsoft laid off 9,000 workers to fund AI. Now that talent could use AI to outplay Microsoft
When one Microsoft executive told laid-off workers to use ChatGPT for “emotional support,” they accidentally handed those ex-employees the perfect weapon: revenge. With tech layoffs mounting up, we could be entering an era of “Revenge of the Nerds-style” market disruption.
Big tech corporate culture has reached a new level of absurdity.
Microsoft just laid off 9,000 employees while announcing an $80 billion investment in AI. Then one of its executives reportedly suggested that these displaced workers should use AI chatbots for advice on how to cope with the mental anguish of their unemployment.
Matt Turnbull, an Xbox Game Studios Executive Producer who has been continuously employed at Microsoft since 2011, decided that what recently terminated employees needed wasn’t just job security or severance packages, but AI prompts. In a now-deleted LinkedIn post, Turnbull suggested that laid-off workers “use LLM AI tools (like ChatGPT or Copilot) to help reduce the emotional and cognitive load that comes with job loss.”
Let that sink in. The same company that just fired thousands of people to fund its AI ambitions is now recommending those very AI tools as therapy for the trauma they’ve inflicted.
AI-driven unemployment: Who can afford to buy stuff?
Turnbull’s arguably well-intentioned but insensitive suggestion reveals a much darker reality: we’re witnessing the beginning of an AI-driven employment crisis. When major corporations are willing to eliminate 9,000 jobs in a single sweep to fund AI development, we’re not just seeing isolated cost-cutting—we’re seeing the systematic replacement of human workers with algorithms.
The math is terrifying. If AI continues to eliminate jobs at this pace across every industry, we’ll soon reach a point where the very consumers these companies depend on won’t have the disposable income to buy their products. Microsoft is essentially killing its own customer base to feed its AI ambitions. Who’s going to buy Xbox games when the game developers are all unemployed? When promised games are shelved?
Nerds v. Nerds: A new kind of startup coming soon
But here’s where this sad story could end up with a happy ending. Those 9,000 laid-off Microsoft employees represent one of the most concentrated pools of tech talent suddenly available on the market. They know Microsoft’s weaknesses better than anyone since they’ve lived them, breathed them and probably complained about them in personal Slack channels.
Instead of using ChatGPT to “reduce their emotional and cognitive load,” these displaced workers should embrace the ultimate irony: use AI to create something better. Not maliciously, but strategically. They should band together and create a company built on everything their former employer gets wrong.
Imagine a collaborative effort where thousands of former Microsoft employees (and others made redundant at other big tech companies) use AI to systematically analyse every customer complaint, every negative review, every competitive weakness in Microsoft’s vast portfolio.
They could create AI-powered market research that identifies the gaps Microsoft has ignored, the features users desperately want, and the business opportunities their former employer is too suck in their ways to pursue.
The AI-powered business plan
Here’s the ironic twist that would make even the most cynical observer smile: Use the very AI tools that replaced you to build a business plan that could potentially outcompete your former employer.
Feed GPT-4 or Claude (or bespoke AI Agents) every negative Microsoft review from the past five years that has yet to be solved. Analyse competitor strengths where Microsoft is weak. Identify underserved markets that Microsoft’s corporate structure is too rigid to address.
AI could help these entrepreneurs develop, for example:
Product concepts based on genuine user frustrations with Microsoft’s offerings
Business models that prioritise employee retention over AI replacement
Company culture frameworks that explicitly reject the dehumanising practices they just experienced
Marketing strategies that highlight the human touch their former employer has abandoned
Building trust through transparency
Don’t cut gaming development projects too fast by letting gaming customers down
One of Microsoft’s biggest vulnerabilities is trust. Users are increasingly wary of big tech companies that treat employees as disposable and customers as data points. A new company founded by ex-Microsoft talent could differentiate itself by embracing radical transparency about its AI use. They could promote how they’re using AI to augment human capabilities rather than replace human workers.
They could create a company ethos that states: “We use AI to make our human employees more effective, not to eliminate them.” This approach would resonate with consumers who are growing tired of corporate rhetoric about “AI efficiency” that really means “fewer jobs for humans.”
Ultimate poetic justice?
The beautiful part of this scenario is the potential for poetic justice. Microsoft’s executives, sitting in their Redmond offices, would watch as their former employees use the very AI tools they were told to embrace for emotional support to build competing products. It’s the ultimate “hold my beer” moment in corporate history.
Turnbull’s suggestion that laid-off workers should use AI for “emotional clarity and confidence” could indeed provide clarity, however, just not the kind he intended. Sometimes the clearest path forward isn’t coping with your situation but using every tool at your disposal to create a better one.
The gaming industry employees who were told to use ChatGPT to find new jobs should absolutely take that advice, but not in the way their former boss intended. They should use AI to identify exactly what gamers hate about Xbox, what features they wish existed, and what kind of gaming company they’d actually want to support with their wallets.
A new breed of Microsoft?
Microsoft’s approach to both AI and human resources reveals a company that has lost touch with the very creativity and innovation that made it successful. For game developers, this is particularly true. By treating employees as line items and AI as a replacement for human ingenuity, they’ve created the perfect opportunity for disruption.
The 9,000 laid-off employees have something their former employer has lost: the hunger to prove themselves through creativity, and now, thanks to Turnbull’s suggestion, explicit permission to use AI as their secret weapon.
In the end, Microsoft’s greatest contribution to the future of technology might not be Copilot or ChatGPT integration. It might be the army of motivated, talented ex-employees they’ve created, armed with AI tools and a deep understanding of how not to run projects. Instead, they will give consumers what they have been waiting for.
That’s the kind of emotional clarity that no chatbot can spurt out, but that 9,000 unemployed Microsoft veterans might just deliver with like-minded grit and backers.
| 2025-07-07T00:00:00 |
2025/07/07
|
https://www.freelanceinformer.com/news/microsoft-laid-off-9000-workers-to-fund-ai-now-that-talent-could-use-ai-to-outplay-microsoft/
|
[
{
"date": "2023/01/01",
"position": 95,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 91,
"query": "AI workers"
}
] |
U.S. Workers Eager to Adopt AI with More Employer Support, D2L ...
|
U.S. Workers Eager to Adopt AI with More Employer Support, D2L Survey Finds
|
https://finance.yahoo.com
|
[
"Pr Newswire",
"Mon",
"Jul",
"Min Read"
] |
The survey reveals that of the respondents: Approximately 33% of workers fear AI may eventually replace their jobs. Most employees (69%) agree ...
|
New research from D2L shows employers should offer more interactive AI learning opportunities
TORONTO, July 7, 2025 /PRNewswire/ -- D2L, a global learning technology company, has released new survey results from Morning Consult that suggests U.S. workers who are eager to adopt artificial intelligence (AI) and grow their skills would like more structured support and more flexible opportunities to engage in learning.
D2L Logo (CNW Group/D2L)
D2L's annual report on skills development, Upskill with Purpose: Creating a Future-Ready Workforce, surveyed nearly 1,000 full-time, salaried workers across the United States.
The survey reveals that of the respondents:
Approximately 33% of workers fear AI may eventually replace their jobs.
Most employees (69%) agree AI will help them do their jobs better — 65% are excited for AI to support repetitive tasks, and 68% expect it may free up more time for strategic and creative work.
75% of employees state they want to supplement their skills to help advance professionally in the next three years, with 56% reporting they have been left to their own devices when it comes to learning about AI.
Most employees prefer the convenience of self-paced and employer-provided learning — 56% have learned on their own, and 52% have participated in employer training.
During training programs, 45% of workers identify interactive modules with instant feedback as most effective for building skills.
"As AI becomes more integrated into the way we work and learn, it's important that workers can feel empowered with the right tools and resources to help harness its potential," said John Baker, President and CEO of D2L "The new research shows that employers can have an opportunity to help workers in their careers and develop AI skills with a more flexible approach to upskilling that can be tailored to help suit their learning needs."
What employers can do
Upskill with Purpose suggests that employers adopt a more balanced approach to talent development that can promote human potential while they develop more technical skills and integrate AI into real-world workflows. To help bridge the gap between employer investment and employee skill development, the report recommends that employers:
| 2023-01-01T00:00:00 |
https://finance.yahoo.com/news/u-workers-eager-adopt-ai-191800964.html
|
[
{
"date": "2023/01/01",
"position": 96,
"query": "AI workers"
},
{
"date": "2023/03/01",
"position": 88,
"query": "AI workers"
},
{
"date": "2023/04/01",
"position": 95,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 89,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 89,
"query": "AI workers"
},
{
"date": "2023/09/01",
"position": 91,
"query": "AI workers"
},
{
"date": "2023/10/01",
"position": 93,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 91,
"query": "AI workers"
},
{
"date": "2024/01/01",
"position": 91,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 90,
"query": "AI workers"
},
{
"date": "2024/03/01",
"position": 91,
"query": "AI workers"
},
{
"date": "2024/05/01",
"position": 91,
"query": "AI workers"
},
{
"date": "2024/06/01",
"position": 95,
"query": "AI workers"
},
{
"date": "2024/11/01",
"position": 91,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 88,
"query": "AI workers"
}
] |
|
Leadership with AI - ISB
|
Leadership Course from ISB Institute
|
https://online-er.isb.edu
|
[] |
In today's rapidly evolving business landscape, effective leadership requires the ability to harness the potential of Artificial Intelligence (AI), ...
|
More than 300,000 professionals globally, across 200 countries, have chosen to advance their skills with Emeritus and its educational learning partners. In fact, 90 percent of the respondents of a recent survey across all our programmes said that their learning outcomes were met or exceeded. All the contents of the course would be made available to students at the commencement of the course. However, to ensure the programme delivers the desired learning outcomes, the students may appoint Emeritus to manage the delivery of the programme in a cohort-based manner during the course period the cost of which is already included in the overall Course fee of the course.
A dedicated programme support team is available 7 days a week to answer questions about the learning platform, technical issues, or anything else that may affect your learning experience.
| 2023-01-01T00:00:00 |
https://online-er.isb.edu/leadership-with-ai/index.php
|
[
{
"date": "2023/01/01",
"position": 44,
"query": "AI business leaders"
},
{
"date": "2023/02/19",
"position": 3,
"query": "AI business leaders"
},
{
"date": "2023/04/01",
"position": 45,
"query": "AI business leaders"
},
{
"date": "2023/05/01",
"position": 40,
"query": "AI business leaders"
},
{
"date": "2023/06/01",
"position": 87,
"query": "artificial intelligence business leaders"
},
{
"date": "2023/08/01",
"position": 40,
"query": "AI business leaders"
},
{
"date": "2023/11/01",
"position": 40,
"query": "AI business leaders"
},
{
"date": "2023/12/01",
"position": 74,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/01/01",
"position": 40,
"query": "AI business leaders"
},
{
"date": "2024/01/01",
"position": 92,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/07/01",
"position": 40,
"query": "AI business leaders"
},
{
"date": "2024/07/01",
"position": 97,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/09/01",
"position": 82,
"query": "AI business leaders"
},
{
"date": "2024/10/01",
"position": 44,
"query": "AI business leaders"
},
{
"date": "2024/11/01",
"position": 39,
"query": "AI business leaders"
},
{
"date": "2024/12/01",
"position": 40,
"query": "AI business leaders"
},
{
"date": "2025/01/01",
"position": 76,
"query": "AI business leaders"
},
{
"date": "2025/01/01",
"position": 97,
"query": "artificial intelligence business leaders"
}
] |
|
AI for Entrepreneurs and Business Leaders - Meetup
|
AI for Entrepreneurs and Business Leaders
|
https://www.meetup.com
|
[] |
A platform created to unravel the dynamic, rapidly evolving landscape of artificial intelligence and its transformative implications for businesses across ...
|
Welcome to "AI for Entrepreneurs and Business Leaders" - a platform created to unravel the dynamic, rapidly evolving landscape of artificial intelligence and its transformative implications for businesses across sectors and to spotlight YOU!
If you have a need, we probably have a solution, please don't hesitate to reach out for content suggestions, meetup requests, request for contacts, request us to promote your event or share ideas.
This AI Meetup group meets regularly in person every 4th Thursday of the month at Venture Cafe Phoenix, in downtown Phoenix! Free parking and 2 free drinks.
However if you don't resize in the greater Phoenix area, no worries! We do host many online events and other opportunities in person and online. Stay tuned!
In today's digitally-driven world, understanding and leveraging AI technologies is not just beneficial—it's crucial for growth, competitiveness, and innovation. Whether you are a startup founder seeking to disrupt industries, a seasoned business leader aiming to future-proof your enterprise, or a curious mind eager to learn about the AI frontier, this meetup is designed for you by you.
Our group fosters an open, collaborative space where you can:
Learn and Grow Deepen your understanding of AI and its subfields - Machine Learning, Deep Learning, NLP, and more. Keep abreast with the latest AI research, trends, tools, and applications in business.
Engage in Thought-Provoking Discussions Participate in enriching, robust discussions on the ethical, societal, and economic implications of AI. Understand how to effectively navigate the challenges and pitfalls in AI adoption.
Network with Diverse Professionals Connect with a diverse network of entrepreneurs, business leaders, AI enthusiasts, and experts. Gain unique insights from their journeys, experiences, and perspectives.
Discover Opportunities Learn about AI success stories and how businesses are using AI to gain a competitive edge. Explore possibilities for implementing AI in your own business context.
Collaborate Find potential collaborators, partners, and mentors. Forge strategic relationships to drive your AI journey.
Get Hands-On Participate in workshops, webinars, and hackathons. Get practical, hands-on experience with AI tools and techniques.
Our meetups will feature a blend of presentations, workshops, guest speaker sessions, and networking events, catering to all levels of AI knowledge and experience. We welcome everyone interested in exploring how AI can accelerate business growth, increase operational efficiency, and foster innovation.
Join "AI for Entrepreneurs and Business Leaders" today and step into the future of business and entrepreneurship, powered by AI. Let's navigate the AI revolution together!
| 2023-01-01T00:00:00 |
https://www.meetup.com/ai-for-entrepreneurs-and-business-leaders/
|
[
{
"date": "2023/01/01",
"position": 85,
"query": "AI business leaders"
},
{
"date": "2023/02/01",
"position": 99,
"query": "artificial intelligence business leaders"
},
{
"date": "2023/04/01",
"position": 83,
"query": "AI business leaders"
},
{
"date": "2023/05/01",
"position": 92,
"query": "artificial intelligence business leaders"
},
{
"date": "2023/06/01",
"position": 93,
"query": "artificial intelligence business leaders"
},
{
"date": "2023/11/01",
"position": 98,
"query": "artificial intelligence business leaders"
},
{
"date": "2023/12/01",
"position": 96,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/01/01",
"position": 93,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/02/01",
"position": 91,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/05/01",
"position": 97,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/07/01",
"position": 98,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/09/01",
"position": 63,
"query": "AI business leaders"
},
{
"date": "2024/09/01",
"position": 97,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/10/01",
"position": 97,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/11/01",
"position": 85,
"query": "AI business leaders"
},
{
"date": "2024/11/01",
"position": 97,
"query": "artificial intelligence business leaders"
},
{
"date": "2025/01/01",
"position": 98,
"query": "artificial intelligence business leaders"
}
] |
|
Artificial Intelligence (AI) for Business Leaders - SAIT
|
Artificial Intelligence (AI) for Business Leaders
|
https://www.sait.ca
|
[] |
this two-day course gives decision-makers at all levels a clear, practical foundation in AI—moving beyond the theory to focus on real-world applications ...
|
Overview
In today’s rapidly evolving technological landscape, business leaders need to understand how to strategically implement both machine learning (ML) and generative AI (GAI) within their organizations. Ready to build an AI-ready culture and harness AI to drive organizational growth?
Offered in partnership with Braintoy, this two-day course gives decision-makers at all levels a clear, practical foundation in AI—moving beyond the theory to focus on real-world applications, strategy development, and ethical considerations.
Experience a dynamic, collaborative learning environment led by knowledgeable AI solutions experts and an engaged group of peers. Have ideas you’re eager to implement at your workplace? This hands-on course blends real-world case studies with interactive exercises and equips you with practical templates, frameworks, and worksheets to begin crafting an AI strategy—either for a hypothetical scenario or tailored to your organization.
By the end of the course, you'll be equipped with the knowledge and skills to identify AI opportunities, lead AI-driven projects, and ensure responsible AI adoption, leveraging the full potential of both predictive and generative AI.
This course is ideal if you:
want to understand how AI can drive business growth and innovation
are looking to develop a strategic AI roadmap for your organization
need to create governance policies and ethical guidelines for AI adoption
aim to measure and maximize the ROI of AI investments.
Our partners
SAIT is proud to offer the Artificial Intelligence (AI) for Business Leaders course—developed and delivered by Braintoy, a Western Canadian AI/ML solutions company working with organizations worldwide. Braintoy is on a mission to make AI and machine learning accessible to everyone. Their low-code/no-code platform, mlOS, enables organizations across sectors like energy, finance, manufacturing, and telecommunications to deploy AI quickly and effectively. By partnering with educational institutions, Braintoy helps individuals gain the skills to apply AI for better decision-making, efficiency, and safety. At the core of their work is a commitment to breaking down barriers and empowering digital citizens to use AI for meaningful, human-centred innovation.
| 2023-01-01T00:00:00 |
https://www.sait.ca/continuing-education/courses-and-certificates/courses/artificial-intelligence-for-business-leaders
|
[
{
"date": "2023/01/01",
"position": 96,
"query": "AI business leaders"
},
{
"date": "2023/02/01",
"position": 83,
"query": "artificial intelligence business leaders"
},
{
"date": "2023/04/01",
"position": 100,
"query": "AI business leaders"
},
{
"date": "2023/05/01",
"position": 90,
"query": "artificial intelligence business leaders"
},
{
"date": "2023/06/01",
"position": 79,
"query": "artificial intelligence business leaders"
},
{
"date": "2023/11/01",
"position": 94,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/01/01",
"position": 79,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/02/01",
"position": 89,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/05/01",
"position": 82,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/07/01",
"position": 83,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/09/01",
"position": 82,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/10/01",
"position": 82,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/11/01",
"position": 100,
"query": "AI business leaders"
},
{
"date": "2024/11/01",
"position": 82,
"query": "artificial intelligence business leaders"
},
{
"date": "2025/01/01",
"position": 82,
"query": "artificial intelligence business leaders"
},
{
"date": "2025/05/01",
"position": 15,
"query": "AI business leaders"
},
{
"date": "2025/05/01",
"position": 14,
"query": "artificial intelligence business leaders"
}
] |
|
Applied Artificial Intelligence: A Handbook For Business Leaders ...
|
Applied Artificial Intelligence: A Handbook For Business Leaders
|
https://appliedaibook.com
|
[
"Rachel Thomas",
"Jack Chua",
"Stephen Strauss"
] |
Applied Artificial Intelligence is a practical guide for business leaders who are passionate about leveraging machine intelligence to enhance the productivity ...
|
Applied Artificial Intelligence
A Handbook For Business Leaders
Applied Artificial Intelligence is a practical guide for business leaders who are passionate about leveraging machine intelligence to enhance the productivity of their companies and the quality of life in their communities. If you love driving innovation by combining data, technology, design, and people to solve real problems at an enterprise scale, this is your playbook.
This book balances technical details and strategic insights targeted for executives and entrepreneurs. You’ll learn how to lead successful AI initiatives, identify the most promising applications, assemble diverse teams of experts, and adopt the most effective implementation approaches.
In this expanded 2nd edition, we explore how various enterprise functions can leverage both proven predictive AI and newer generative AI technologies such as large language models and image generation.
| 2023-01-01T00:00:00 |
https://appliedaibook.com/
|
[
{
"date": "2023/01/01",
"position": 98,
"query": "AI business leaders"
},
{
"date": "2023/02/01",
"position": 97,
"query": "artificial intelligence business leaders"
},
{
"date": "2023/05/01",
"position": 90,
"query": "AI business leaders"
},
{
"date": "2023/05/01",
"position": 91,
"query": "artificial intelligence business leaders"
},
{
"date": "2023/06/01",
"position": 92,
"query": "artificial intelligence business leaders"
},
{
"date": "2023/08/01",
"position": 90,
"query": "AI business leaders"
},
{
"date": "2023/11/01",
"position": 90,
"query": "AI business leaders"
},
{
"date": "2023/11/01",
"position": 95,
"query": "artificial intelligence business leaders"
},
{
"date": "2023/12/01",
"position": 95,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/01/01",
"position": 89,
"query": "AI business leaders"
},
{
"date": "2024/01/01",
"position": 91,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/02/09",
"position": 3,
"query": "AI business leaders"
},
{
"date": "2024/02/01",
"position": 90,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/05/01",
"position": 96,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/07/01",
"position": 90,
"query": "AI business leaders"
},
{
"date": "2024/07/01",
"position": 96,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/09/01",
"position": 96,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/10/01",
"position": 96,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/11/01",
"position": 96,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/12/01",
"position": 90,
"query": "AI business leaders"
},
{
"date": "2025/01/01",
"position": 73,
"query": "AI business leaders"
},
{
"date": "2025/01/01",
"position": 96,
"query": "artificial intelligence business leaders"
},
{
"date": "2025/02/01",
"position": 86,
"query": "artificial intelligence business leaders"
},
{
"date": "2025/06/01",
"position": 87,
"query": "artificial intelligence business leaders"
}
] |
|
AI in Talent Acquisition | IBM
|
AI in talent acquisition
|
https://www.ibm.com
|
[] |
AI in talent acquisition refers to the use of artificial intelligence in sourcing and hiring new employees.
|
Advancements in AI have created several powerful use cases for human resources departments to use the technology to improve their workflows. Organizations can use machine learning, generative AI, natural language processing (NLP) and other advanced automation and AI tools to improve the overall hiring experience. AI-powered tools can help organizations save money and find the best possible candidates.
Organizations that use AI will find more prospects also using AI to enhance their jobs. McKinsey found that 88% of respondents to a survey were using generative AI to enhance their jobs.1 As such, they might be more comfortable encountering it during their job search process.
AI-driven talent acquisition can improve an organization’s overall recruitment process by reducing the time it takes to find, assess and hire top prospects.
| 2023-01-01T00:00:00 |
https://www.ibm.com/think/topics/ai-talent-acquisition
|
[
{
"date": "2023/01/01",
"position": 7,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 7,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 11,
"query": "AI hiring"
},
{
"date": "2023/05/01",
"position": 47,
"query": "artificial intelligence hiring"
},
{
"date": "2023/06/01",
"position": 9,
"query": "AI hiring"
},
{
"date": "2023/08/01",
"position": 8,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 6,
"query": "AI hiring"
},
{
"date": "2023/10/01",
"position": 47,
"query": "artificial intelligence hiring"
},
{
"date": "2023/12/01",
"position": 7,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 7,
"query": "AI hiring"
},
{
"date": "2024/03/01",
"position": 40,
"query": "artificial intelligence hiring"
},
{
"date": "2024/04/01",
"position": 76,
"query": "artificial intelligence hiring"
},
{
"date": "2024/05/01",
"position": 81,
"query": "artificial intelligence hiring"
},
{
"date": "2024/06/01",
"position": 7,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 6,
"query": "AI hiring"
},
{
"date": "2024/11/01",
"position": 67,
"query": "artificial intelligence hiring"
},
{
"date": "2025/01/01",
"position": 6,
"query": "AI hiring"
},
{
"date": "2025/06/01",
"position": 30,
"query": "artificial intelligence hiring"
}
] |
|
Hirevue | AI-Powered Skill Validation, Video Interviewing ...
|
AI-Powered Skill Validation, Video Interviewing, Assessments and More
|
https://www.hirevue.com
|
[] |
Validate role-specific skills. Simplify hiring, reduce bias, and future-proof your hiring with Virtual Job Tryouts and AI-powered assessments.
|
Use Hirevue’s video interviewing or seamlessly integrate your own—our flexible platform adapts to your hiring needs. Whether you stick with your existing tools or leverage ours, we make the process effortless, efficient and tailored to you.
| 2023-01-01T00:00:00 |
https://www.hirevue.com/
|
[
{
"date": "2023/01/01",
"position": 14,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 20,
"query": "AI hiring"
},
{
"date": "2023/08/01",
"position": 16,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 21,
"query": "AI hiring"
},
{
"date": "2023/12/01",
"position": 21,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 19,
"query": "AI hiring"
},
{
"date": "2024/06/01",
"position": 15,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 16,
"query": "AI hiring"
},
{
"date": "2025/01/01",
"position": 17,
"query": "AI hiring"
},
{
"date": "2025/02/01",
"position": 72,
"query": "AI employment"
},
{
"date": "2025/02/01",
"position": 14,
"query": "AI hiring"
},
{
"date": "2025/03/01",
"position": 73,
"query": "AI employment"
},
{
"date": "2025/03/26",
"position": 15,
"query": "AI hiring"
},
{
"date": "2025/03/26",
"position": 48,
"query": "artificial intelligence hiring"
},
{
"date": "2025/04/01",
"position": 12,
"query": "AI hiring"
},
{
"date": "2025/05/01",
"position": 72,
"query": "AI employment"
},
{
"date": "2025/06/01",
"position": 74,
"query": "AI employment"
},
{
"date": "2025/06/01",
"position": 13,
"query": "AI hiring"
}
] |
|
Introducing the new Hiring Assistant for Recruiter & Jobs.
|
Introducing the new Hiring Assistant for Recruiter & Jobs.
|
https://business.linkedin.com
|
[] |
The first AI agent for Recruiter & Jobs that helps take on time-consuming tasks on your behalf.
|
First Name is a required field *
Last Name is a required field *
Company is a required field *
Title is a required field *
Your role is a required field * –– Select One –– Business Owner/Leader Head of Department - HR/Talent Head of Department - Other Director - HR/Talent Director - Other Manager - HR/Talent Manager - Other Social Media Manager Recruiter/Sourcer Student/Intern Job Seeker Other
Email is a required field *
Country/Region is a required field * –– Select One –– Afghanistan Aland Islands Albania Algeria American Samoa Andorra Angola Anguilla Antarctica Antigua and Barbuda Argentina Armenia Aruba Australia Austria Azerbaijan Bahamas, The Bahrain Bangladesh Barbados Belarus Belgium Belize Benin Bermuda Bhutan Bolivia Bosnia and Herzegovina Botswana Bouvet Island Brazil British Indian Ocean Territory Brunei Darussalam Bulgaria Burkina Faso Burundi Cambodia Cameroon Canada Cape Verde Cayman Islands Central African Republic Chad Chile China Christmas Island Cocos (Keeling) Islands Colombia Comoros Congo Congo, The Democratic Republic Of The Cook Islands Costa Rica Cote D'ivoire Croatia Cyprus Czech Republic Denmark Djibouti Dominica Dominican Republic Ecuador Egypt El Salvador Equatorial Guinea Eritrea Estonia Ethiopia Falkland Islands (Malvinas) Faroe Islands Fiji Finland France French Guiana French Polynesia French Southern Territories Gabon Gambia, The Georgia, Republic Of Germany Ghana Gibraltar Greece Greenland Grenada Guadeloupe Guam Guatemala Guernsey Guinea Guinea-Bissau Guyana Haiti Heard Island and the McDonald Islands Holy See (Vatican City State) Honduras Hong Kong Hungary Iceland India Indonesia Iraq Ireland Isle Of Man Israel Italy Jamaica Japan Jersey Jordan Kazakhstan Kenya Kiribati Korea, Republic Of Kuwait Kyrgyzstan Lao People's Democratic Republic Latvia Lebanon Lesotho Liberia Libya Liechtenstein Lithuania Luxembourg Macao Macedonia, The Former Yugoslav Republic Of Madagascar Malawi Malaysia Maldives Mali Malta Marshall Islands Martinique Mauritania Mauritius Mayotte Mexico Micronesia, Federated States Of Moldova, Republic Of Monaco Mongolia Montenegro Montserrat Morocco Mozambique Myanmar Namibia Nauru Nepal Netherlands Netherlands Antilles New Caledonia New Zealand Nicaragua Niger Nigeria Niue Norfolk Island Northern Mariana Islands Norway Oman Pakistan Palau Palestinian Territories Panama Papua New Guinea Paraguay Peru Philippines Pitcairn Poland Portugal Puerto Rico Qatar Reunion Romania Russian Federation Rwanda Saint Barthelemy Saint Helena Saint Kitts and Nevis Saint Lucia Saint Martin Saint Pierre and Miquelon Saint Vincent and the Grenadines Samoa San Marino Sao Tome and Principe Saudi Arabia Senegal Serbia Seychelles Sierra Leone Singapore Slovakia Slovenia Solomon Islands Somalia South Africa South Georgia and the South Sandwich Islands Spain Sri Lanka Sudan Suriname Svalbard and Jan Mayen Swaziland Sweden Switzerland Taiwan Tajikistan Tanzania, United Republic Of Thailand Timor-leste Togo Tokelau Tonga Trinidad and Tobago Tunisia Turkey Turkmenistan Turks and Caicos Islands Tuvalu Uganda Ukraine United Arab Emirates United Kingdom United States United States Minor Outlying Islands Uruguay Uzbekistan Vanuatu Venezuela Vietnam Virgin Islands, British Virgin Islands, U.S. Wallis and Futuna Western Sahara Yemen Zambia Zimbabwe
State/Province is a required field * –– Select One –– N/A Alabama Alaska Arizona Arkansas California Colorado Connecticut Delaware District of Columbia Florida Georgia Hawaii Idaho Illinois Indiana Iowa Kansas Kentucky Louisiana Maine Maryland Massachusetts Michigan Minnesota Mississippi Missouri Montana Nebraska Nevada New Hampshire New Jersey New Mexico New York North Carolina North Dakota Ohio Oklahoma Oregon Pennsylvania Rhode Island South Carolina South Dakota Tennessee Texas Utah Vermont Virginia Washington West Virginia Wisconsin Wyoming Alberta British Columbia Manitoba New Brunswick Newfoundland Nova Scotia Ontario Prince Edward Island Quebec Saskatchewan Australian Capital Territory New South Wales Northern Territory Queensland South Australia Tasmania Victoria Western Australia Beijing Shanghai Tianjin Chongqing Guangdong Jiangsu Zhejiang Anhui Fujian Gansu Guangxi Guizhou Hainan Hebei Heilongjiang Henan Hubei Hunan Jiangxi Jilin Liaoning Inner Mongolia (Neimenggu) Ningxia Qinghai Shandong Shanxi Shaanxi Sichuan Tibet (Xizang) Xinjiang Yunnan Andaman and Nicobar Andhra Pradesh Arunachal Pradesh Assam Bihar Chandigarh Chhattisgarh Dadra and Nagar Haveli Daman and Diu Delhi Goa Gujarat Haryana Himachal Pradesh Jammu and Kashmir Jharkhand Karnataka Kerala Lakshadweep Madhya Pradesh Maharashtra Manipur Meghalaya Mizoram Nagaland Odisha Puducherry Punjab Rajasthan Sikkim Tamil Nadu Telangana Tripura Uttar Pradesh Uttarakhand West Bengal
Is your company a customer of LinkedIn Recruiter and Jobs? is a required field * Yes No I'm not sure
By submitting this form, you agree that we may use the data you provide to contact you with information related to your request/submission and LinkedIn's products and services. You can unsubscribe from LinkedIn marketing and sales emails at any time by clicking the unsubscribe link in the email. If you are a LinkedIn member, you can control the marketing messages you receive from LinkedIn in your settings. Your data will be used subject to LinkedIn's Privacy Policy.
Required fields *
Submit
| 2023-01-01T00:00:00 |
https://business.linkedin.com/talent-solutions/hiring-assistant
|
[
{
"date": "2023/01/01",
"position": 23,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 20,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 21,
"query": "AI hiring"
},
{
"date": "2023/08/01",
"position": 19,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 22,
"query": "AI hiring"
},
{
"date": "2023/12/01",
"position": 22,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 16,
"query": "AI hiring"
},
{
"date": "2024/06/01",
"position": 21,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 21,
"query": "AI hiring"
},
{
"date": "2025/01/01",
"position": 19,
"query": "AI hiring"
},
{
"date": "2025/02/01",
"position": 29,
"query": "AI hiring"
},
{
"date": "2025/03/25",
"position": 20,
"query": "AI hiring"
},
{
"date": "2025/04/01",
"position": 22,
"query": "AI hiring"
},
{
"date": "2025/06/01",
"position": 26,
"query": "AI hiring"
}
] |
|
Companies That Tried to Save Money With AI Are Now Spending a ...
|
The heart of the internet
|
https://www.reddit.com
|
[] |
Companies That Tried to Save Money With AI Are Now Spending a Fortune Hiring People to Fix Its Mistakes. Article.
|
/r/jobs is the number one community for advice relating to your career. Head to our discord for live support: discord.gg/4nJztvj
Members Online
| 2023-01-01T00:00:00 |
https://www.reddit.com/r/jobs/comments/1lu9q6l/companies_that_tried_to_save_money_with_ai_are/
|
[
{
"date": "2023/01/01",
"position": 25,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 22,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 23,
"query": "AI hiring"
},
{
"date": "2023/08/01",
"position": 21,
"query": "AI hiring"
},
{
"date": "2023/12/01",
"position": 24,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 22,
"query": "AI hiring"
},
{
"date": "2024/03/01",
"position": 68,
"query": "artificial intelligence hiring"
},
{
"date": "2025/01/01",
"position": 89,
"query": "artificial intelligence hiring"
},
{
"date": "2025/02/01",
"position": 27,
"query": "AI hiring"
},
{
"date": "2025/04/01",
"position": 18,
"query": "AI hiring"
},
{
"date": "2025/06/01",
"position": 22,
"query": "AI hiring"
}
] |
|
AI Hiring Resource Center | Dice for Employers
|
AI Hiring Resource Center
|
https://www.dice.com
|
[] |
Stay ahead in AI hiring with Dice. Explore strategies to attract AI talent, trends shaping the field, and resources to future-proof your tech hiring ...
|
Machine learning has been shaping our world for decades, proving that AI is far from a passing trend. Just as we’ve done with every technological shift, we’ll adapt to a rapidly changing and brighter future.
Dice is your go-to resource for the latest insights in AI and AI hiring. Discover the best ways to stay ahead and secure top talent in the evolving AI landscape.
| 2023-01-01T00:00:00 |
https://www.dice.com/hiring/ai-hiring-trends
|
[
{
"date": "2023/01/01",
"position": 27,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 24,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 27,
"query": "AI hiring"
},
{
"date": "2023/05/01",
"position": 83,
"query": "artificial intelligence hiring"
},
{
"date": "2023/06/01",
"position": 89,
"query": "artificial intelligence hiring"
},
{
"date": "2023/08/01",
"position": 26,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 26,
"query": "AI hiring"
},
{
"date": "2023/10/01",
"position": 89,
"query": "artificial intelligence hiring"
},
{
"date": "2023/12/01",
"position": 27,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 23,
"query": "AI hiring"
},
{
"date": "2024/04/01",
"position": 85,
"query": "artificial intelligence hiring"
},
{
"date": "2024/05/01",
"position": 85,
"query": "artificial intelligence hiring"
},
{
"date": "2024/06/01",
"position": 25,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 25,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 86,
"query": "artificial intelligence hiring"
},
{
"date": "2025/01/01",
"position": 24,
"query": "AI hiring"
},
{
"date": "2025/01/01",
"position": 81,
"query": "artificial intelligence hiring"
}
] |
|
Sapia.ai | Conversational AI Hiring Platform
|
Conversational AI Hiring Platform
|
https://sapia.ai
|
[] |
Sapia.ai helps enterprises hire brilliant people faster, fairer, and at scale. Our AI chat interview enhances candidate experience, promotes inclusion, ...
|
The technical storage or access that is used exclusively for statistical purposes.
The technical storage or access that is used exclusively for anonymous statistical purposes. Without a subpoena, voluntary compliance on the part of your Internet Service Provider, or additional records from a third party, information stored or retrieved for this purpose alone cannot usually be used to identify you.
| 2023-01-01T00:00:00 |
https://sapia.ai/
|
[
{
"date": "2023/01/01",
"position": 30,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 26,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 29,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 27,
"query": "AI hiring"
},
{
"date": "2023/12/01",
"position": 25,
"query": "AI hiring"
},
{
"date": "2024/06/01",
"position": 26,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 24,
"query": "AI hiring"
},
{
"date": "2025/02/01",
"position": 30,
"query": "AI hiring"
},
{
"date": "2025/04/01",
"position": 24,
"query": "AI hiring"
},
{
"date": "2025/06/01",
"position": 27,
"query": "AI hiring"
}
] |
|
Careers - Sierra AI
|
Careers
|
https://sierra.ai
|
[] |
As an APX, you'll build AI agents directly with top global brands and gain access to comprehensive training opportunities, both as an Agent Engineer and Agent ...
|
Interviewing at Sierra
Our approach to hiring is grounded in the belief that excellence is about more than just functional expertise. During the interview process, we’ll evaluate not only your capabilities, but also how well you align with our values.
Since we work in person, interviews take place at one of our offices. You'll have the opportunity to experience our culture and what it'd be like to work at Sierra.
| 2023-01-01T00:00:00 |
https://sierra.ai/careers
|
[
{
"date": "2023/01/01",
"position": 39,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 38,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 41,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 33,
"query": "AI hiring"
},
{
"date": "2023/12/01",
"position": 40,
"query": "AI hiring"
},
{
"date": "2024/06/01",
"position": 38,
"query": "AI hiring"
},
{
"date": "2024/07/09",
"position": 77,
"query": "artificial intelligence hiring"
},
{
"date": "2024/10/01",
"position": 35,
"query": "AI hiring"
},
{
"date": "2025/02/01",
"position": 39,
"query": "AI hiring"
},
{
"date": "2025/04/01",
"position": 32,
"query": "AI hiring"
},
{
"date": "2025/06/01",
"position": 35,
"query": "AI hiring"
}
] |
|
Candidate Engagement & Text Recruiting Tools | HireVue
|
Candidate Engagement & Text Recruiting Tools
|
https://www.hirevue.com
|
[] |
AI-powered candidate engagement tools for hiring teams. Automate text recruiting, streamline scheduling and connect with talent faster. Try HireVue today.
|
Leading Agentic AI framework that goes beyond keyword searching. We guide the candidate to find all the roles they are a fit for not just the searched ones
| 2023-01-01T00:00:00 |
https://www.hirevue.com/platform/candidate-engagement-tools
|
[
{
"date": "2023/01/01",
"position": 44,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 30,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 45,
"query": "AI hiring"
},
{
"date": "2023/08/01",
"position": 38,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 40,
"query": "AI hiring"
},
{
"date": "2023/12/01",
"position": 41,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 38,
"query": "AI hiring"
},
{
"date": "2024/06/01",
"position": 37,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 34,
"query": "AI hiring"
},
{
"date": "2025/01/01",
"position": 34,
"query": "AI hiring"
},
{
"date": "2025/02/01",
"position": 41,
"query": "AI hiring"
},
{
"date": "2025/04/01",
"position": 38,
"query": "AI hiring"
},
{
"date": "2025/06/01",
"position": 37,
"query": "AI hiring"
}
] |
|
AI Interviewer for hiring - Sara - Teammates.ai
|
AI Interviewer for hiring
|
https://teammates.ai
|
[] |
Your autonomous AI Teammate for hiring. Conduct in-depth interviews with every single candidate in 50+ languages so you can cut screening cost by 85%.
|
Zero bias. Superhuman. Effortless in-depth interviews.
Sara engages every candidate with a consistent, human-like voice at any time, day or night. She asks tough, relevant questions so you don't have to, ensuring a fair and world-class experience for everyone.
| 2023-01-01T00:00:00 |
https://teammates.ai/ai-interviewer
|
[
{
"date": "2023/01/01",
"position": 48,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 52,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 61,
"query": "AI hiring"
},
{
"date": "2023/08/01",
"position": 46,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 54,
"query": "AI hiring"
},
{
"date": "2023/12/01",
"position": 52,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 49,
"query": "AI hiring"
},
{
"date": "2024/06/01",
"position": 50,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 47,
"query": "AI hiring"
},
{
"date": "2025/01/01",
"position": 49,
"query": "AI hiring"
}
] |
|
Hiring Managers Are Using AI, Here's Why Job Seekers Should Too
|
More Hiring Managers Are Using AI To Select Candidates, Here’s Why Job Seekers Should Too
|
https://www.blackenterprise.com
|
[
"Nahlah Abdur-Rahman"
] |
As more hiring managers use AI to screen candidates, job seekers can also use the software to their own advantage.
|
Technology by Nahlah Abdur-Rahman More Hiring Managers Are Using AI To Select Candidates, Here’s Why Job Seekers Should Too Striking a balanced use of AI can help one stand out best in the evolving job market.
As employers shift toward AI in their hiring processes, job seekers should take heed of the changes.
According to a study conducted by recruiting agency Kelly Services, the majority of hiring managers are implementing AI to screen candidates. The study found that 66% of employers are using the technology to fill new roles.
“They want to use AI to get things faster, look at resumes faster, interview faster, but I still want to make the decision,” explained Mark Saltrelli, the vice president of engineering and recruiting at Kelly Services.
With automated screenings becoming the norm, job seekers are finding it harder to stand out from the crowd. However, the use of AI can work both ways, with candidates also using the tool to overcome this barrier.
Understanding how AI weeds out candidates is the first step. Implementing key phrases that the software will pick up on remains a key, and tailoring one’s resume to suit this process can aid in getting the interview. For some, the job search has become its own game of cat and mouse. However, knowing how to play can make all the difference.
“It was how I was formatting it, and the terminology I was using,” explained one job seeker, Chelsea Jordan, about her resume tweaks to WXYZ. It looks good in general, but for this specific job, if it’s going to get through to a person, it has to say specific words. I guess it just opened my eyes up to, for lack of a better term, the job search can be a game that you have to play, and I think that AI has helped me do that.”
However, making it to the human side of the hiring process is just one part. Once there, job seekers must make sure they can actually speak to their expertise.
“To really differentiate yourself, you still need that people aspect,” added Saltrelli. “You still need to validate that you’ve done the job well, and others can refer you into it.”
On the other hand, too much reliance on AI can become detrimental to job seekers. Tech recruiter Tova Angsuwat explained to LinkedIn News that employers can see through the artificial cover letters.
“The biggest mistake that I’ll often see from candidates is they use AI to write their cover letter,” explained Angsuwat. “They’re so generic and jargony and may or may not even relate to the company or the role. And immediately, I think you didn’t really care enough to put your voice into this cover letter.”
Despite this, she encourages job seekers to use AI to ensure that a submitted resume matches the job description. She also encourages job applicants to practice their interview skills by getting AI to feed them possible questions. Overall, striking a balance with AI usage can lead to more interviews and potential offers in this evolving job market.
RELATED CONTENT: Jackson State University To Receive $1.3M For AI Development
| 2025-07-07T00:00:00 |
2025/07/07
|
https://www.blackenterprise.com/hiring-managers-using-ai-why-job-seekers-should-too/
|
[
{
"date": "2023/01/01",
"position": 50,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 54,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 59,
"query": "AI hiring"
},
{
"date": "2023/08/01",
"position": 44,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 57,
"query": "AI hiring"
},
{
"date": "2023/12/01",
"position": 49,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 46,
"query": "AI hiring"
},
{
"date": "2024/06/01",
"position": 48,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 46,
"query": "AI hiring"
},
{
"date": "2025/01/01",
"position": 47,
"query": "AI hiring"
},
{
"date": "2025/02/01",
"position": 87,
"query": "AI hiring"
},
{
"date": "2025/04/01",
"position": 88,
"query": "AI hiring"
},
{
"date": "2025/06/01",
"position": 88,
"query": "AI hiring"
},
{
"date": "2025/06/01",
"position": 99,
"query": "artificial intelligence hiring"
}
] |
comma.ai — jobs
|
comma.ai — jobs
|
https://comma.ai
|
[] |
We're Actively Hiring · Electronics Engineer Design + ship hardware like the comma 3X and comma body // challenge · Software Engineer (Web) · Software Engineer ( ...
|
comma.ai jobs
Come build the future
Solve self driving cars while delivering shippable intermediaries.
We're building the robotics stack that will solve self driving cars, then eventually scales to all of robotics. We own our stack from shipping state of the art machine learning models trained on our own infrastructure, building the operating system, designing the hardware, and manufacturing it.
Today, our fleet is the second largest after Tesla, and it's growing every month as more of the 10+ million compatible cars on the road come online. We will win by continuing to ship a better product and better driving to our users. No hype, just shipping constant incremental progress until your comma reliably drives you to Taco Bell.
comma is 25 people across three teams:
The autonomy team builds the autonomous agent software, along with all of the infrastructure needed for that.
The product team designs and manufactures the product, including the hardware, low-level software needed to run the agent software, as well the app.
The operations team builds and maintains company infrastructure, including money, people, and logistics.
The operations and product teams work together to ship you the comma 3X, and the autonomy and product teams ship openpilot to run on your comma 3X.
comma is a profitable consumer electronics business. For every dollar we make, half goes to building comma 3Xs and half goes to engineering to improve the product. No advertising, MBAs, or agenda beyond solving self-driving cars.
One meeting a week, two great meals a day, and people who have passed a very high bar to get hired. Perks: - Chef-prepared lunch and dinner - On-site gym and yoga studio - 24/7 access to the comma fleet of cars - Health, dental, and vision insurance - Flexible time off
Who we're looking for
We don't care where, or even if, you went to school. We don't care if you have a traditional background. We're just looking for people who can independently contribute to shipping openpilot. We love a great GitHub, open source contributors, good projects, and competition winners. Prove your skills with either of these: 1. Bounties: contribute to our open source projects while getting paid 2. Challenges: we made challenges for design, controls, hardware, and more.
We're Actively Hiring
Electronics Engineer Design + ship hardware like the comma 3X and comma body // challenge Software Engineer (Web) Own the comma web and mobile experience // challenge: get a web bounty merged Build an incredible companion app for openpilot Software Engineer (Systems) Work on systems and infrastructure for openpilot // challenge: get a bounty merged You'll work on things like mainlining our kernel, bringing up new hardware, and making the comma 3X boot up in 5s. Car Interface Engineer Work on growing openpilot's car compatibility alongside our community // challenge: get a bounty merged Functional safety experience is a plus Controls Engineer Work on steering, gas, and brake controls for the 300 different cars openpilot supports // challenge Autonomy Engineer Work on infrastructure to train autonomous agents // challenge Internship All teams accept interns year-round // challenge: get on the leaderboard or solve some bounties Pick & Place Operator Run the comma factory's circuit board line // Relevant experience required instead of a challenge Technician Maintain the comma compute cluster and comma fleet // Requirements: have built computers, good debugging skills, and detail orientedness Operations Engineer (comma shop) Own comma's daily operations around the comma shop, including supply chain, logistics, procurement, customer support, fulfillment, and more // challenge
Applying
1. Challenge Choose any of the challenges from the leaderboard or bounties, solve it, then reach into [email protected]. 2. Phone screen Typically, we do two phone calls. A quick intro and screen, then an in-depth technical interview with a division head. 3. Paid Micro-internship We'll fly you out to meet the team and work on a real problem for a few days. In most cases, the project will be scoped such that you'll ship it to real users by the end. If all goes well, we'll make you a full-time job offer.
FAQ
| 2023-01-01T00:00:00 |
https://comma.ai/jobs
|
[
{
"date": "2023/01/01",
"position": 53,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 55,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 62,
"query": "AI hiring"
},
{
"date": "2023/08/01",
"position": 48,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 56,
"query": "AI hiring"
},
{
"date": "2023/12/01",
"position": 51,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 47,
"query": "AI hiring"
},
{
"date": "2024/06/01",
"position": 53,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 49,
"query": "AI hiring"
},
{
"date": "2025/01/01",
"position": 52,
"query": "AI hiring"
}
] |
|
CTOs Reveal How AI Changed Software Developer Hiring in 2025
|
CTOs Reveal How AI Changed Software Developer Hiring in 2025
|
https://www.finalroundai.com
|
[] |
We asked 12 CTOs and CEOs what skill they now prioritize when hiring developers because of AI. Their answers validate what experienced ...
|
AI is turning every junior developer into a code factory and every senior developer into a janitor.
That's the brutal reality we are seeing across the industry right now. While AI evangelists promise that everyone will become a "10x developer," what's actually happening is that companies are drowning in AI-generated code that looks perfect but breaks in production.
So we asked the people who actually have to deal with this mess: CTOs and engineering leaders who are hiring developers in 2025.
What we found might surprise the AI hype machine.
We asked one simple question: "What skill do you now look for when hiring developers that you didn't care about as much before AI?"
Spoiler: "They're not hiring prompt engineers".
Here's what these leaders told us and why it proves that the most valuable developers aren't the ones churning out AI code, but the ones who can think their way out of the problems AI creates.
Critical Thinking Over Code Generation
Most engineering leaders said the same thing: they want developers who can look at AI-generated code and figure out what's wrong with it, not just accept whatever the AI spits out.
1. "AI Often Gives Confident But Wrong Answers"
For us, critical thinking and healthy skepticism are now a priority. AI often gives "confident but wrong" answers - the developer must doubt. The key to quality is the ability to test assumptions. Without critical thinking, a developer can believe false results.
At the interview, we demonstrate this skill as follows:
We add errors or ambiguities to the task condition. We monitor whether the candidate asks clarifying questions. We ask the candidate to evaluate the code in terms of risks, not just functionality.
The approach to hiring has changed:
We give more open-ended tasks without clear instructions. The way of thinking becomes more important than a template solution. We actively involve behavioral interviews to check resistance to "false confidence."
Taras Tymoshchuk, CEO, Co-Founder, Geniusee
2. "The Best Candidates Treat AI Like a Junior Teammate"
One skill I'm prioritizing now is "critical thinking in code validation". Essentially, the ability to question and verify what AI tools produce rather than assuming it's correct.
With AI assistants like Copilot or ChatGPT generating boilerplate and even complex code, developers are moving faster but the risk of subtle bugs, security holes, or performance issues creeping in has increased. What sets apart strong engineers now is their instinct to pause and ask,
Does this really do what I think it does?
Could there be an edge case?"
They're not just consuming AI outputs; they're auditing them.
I've adjusted interviews to include AI-assisted coding rounds. For example, I'll have the candidate use an AI tool to scaffold a solution, then ask them to explain potential failure points or suggest tests to validate it. I also like giving them slightly flawed AI-generated code and asking them to debug or refactor it on the spot. Those who can calmly dissect and improve on AI's output stand out.
Has AI changed how I hire? Yes. I'm less focused on speed typing or memorizing syntax and more on design, reasoning, and their ability to collaborate with AI tools. The best candidates treat AI like a junior teammate: helpful, but not infallible.
One great example: I hired a mid-level developer who impressed me by catching a subtle concurrency bug in code Copilot wrote. She sketched out how she'd test and refactor it and showing the exact mindset I now value.
Vipul Mehta, Co-Founder & CTO, WeblineGlobal
3. "That Moment of Scrutiny Saved Us From a Patient Safety Issue"
We recently interviewed a developer for a healthcare app project. During a test, we handed over AI-generated code that looked clean on the surface. Most candidates moved on. However, this particular candidate paused and flagged a subtle issue: the way the AI handled HL7 timestamps could delay remote patient vitals syncing. That mistake might have gone live and risked clinical alerts.
Thanks to that moment of scrutiny, we avoided what could have been a serious patient safety issue. We later found this fix would have prevented potential liability and saved us thousands in rework.
Now, I look for developers who challenge AI outputs, ask, "What if this breaks?" and think about how code behaves in the real world. It's not about knowing more; it's about thinking deeper.
If you're hiring in any field touched by AI, test how candidates respond when the machine is wrong. That's where the real talent shows up.
Riken Shah, Founder & CEO, OSP Labs
4. "We Need Developers Who Can Spot When AI Gets It Wrong"
One skill we've started prioritizing in hiring is how well developers can think critically about AI-generated code. With tools like GitHub Copilot and ChatGPT in the mix, it's easy for someone to accept whatever output they get without questioning it. That's risky.
We need people who can pause, review what the AI produced, and ask:
Does this actually fit our architecture?
Is it secure?
Could this break under certain conditions?
This ability to analyze and challenge AI suggestions is now just as important as writing clean code.
In the interview, we often show the candidates a code snippet from the AI tool and ask them to review it. The best candidates do not just point out syntax issues. They notice design flaws, security gaps, or ways to improve maintainability.
AI has not really changed who we hire, but it has changed how we evaluate. We now focus more on how candidates collaborate with AI, instead of treating AI as magic they can rely on blindly.
Vikrant Bhalodia, Head of Marketing & People Ops, WeblineIndia
Systems Thinking: The New Competitive Advantage
Multiple leaders emphasized that while AI can write individual functions, it cannot understand how systems work together at scale.
5. "AI Can Write Code, But It Can't Think About How Systems Scale"
As a CTO in 2025, one of the skills I am beginning to prioritize while hiring developers is system design. With AI eliminating much of the mundane coding, developers are now primarily called upon to design scalable, efficient, and flexible systems. While AI can write code, it cannot think critically about how different parts of a system will interact and scale in the future. This is where human judgment plays a crucial role.
When hiring now, I place more emphasis on candidates who can abstract complex problems and design architecture with the future in mind. During interviews, I like to ask them about specific real-world examples where they had to design a system from the ground up or optimize an existing one. I ask them to walk me through their "space of solutions" and the trade-offs they considered, how they addressed scaling issues, and what they learned in the process.
AI hasn't made hiring easier. It has actually altered how we evaluate developers. While technical knowledge remains important, I increasingly search for problem-solving and big-picture thinking skills. AI tools are just that tools. What truly matters is how developers utilize these tools to solve challenging problems that require a deep understanding of systems and design.
Jason Hishmeh, Author | CTO | Founder | Tech Investor, Varyence
6. "We've Seen Perfect Code Break Under Real-World Pressure"
One skill I now prioritize is systems thinking, the ability to understand how different parts of a solution work together and how to design for long-term performance and flexibility.
AI tools like GitHub Copilot and ChatGPT have boosted developer productivity by up to 55%, but this shift has moved the real value away from just writing code. Developers now spend more time debugging, integrating, and making architectural decisions. So, we look for people who think in systems.
We've seen cases where the code looked perfect but broke under real-world pressure due to overlooked issues like caching or database bottlenecks. That's why we don't rely solely on technical tests anymore.
In interviews, we focus on:
Real-world problem solving: "How would you scale a CRM module or reduce loading times during peak usage?" Design reviews: "We show a flawed system plan and ask candidates how they would fix or improve it."
The strongest candidates explain their thinking clearly and understand the trade-offs. We're also cautious with candidates who can only talk about tools or frameworks but struggle to explain the reasoning behind their decisions. That's a red flag, especially now.
Royal Rovshan, CTO & Product Manager, Vitanur
7. "AI Handles Basic Code Generation, Developers Create Structure"
One specific skill we now prioritize is systems thinking. We look for developers who understand how code connects to broader architecture, user experience, and operational impact. Writing functions is one piece of the work. Designing durable, scalable solutions is what drives long-term value.
Why it matters more now: AI handles basic code generation. Developers who think in systems create structure, reduce risk, and support growth. They make better decisions at every layer of the product.
How do we spot it? We give real-world scenarios and ask candidates how they would design, build, and scale a solution. We listen to how they reason through complexity, define priorities, and anticipate impact. This shows how they approach real work.
How AI has changed our hiring process: We focus on judgment, context, and tool fluency. Developers who understand how to integrate AI into their workflow move faster with precision.
We prioritize those who lead with structure and understand the business impact of their technical choices.
Alex Smereczniak, Co-Founder & CEO, Franzy
Understanding the Business Behind the Code
Several leaders noted that AI excels at writing technically correct code but completely misses business requirements.
8. "We Used to Hire People Who Could Code; Now We Hire People Who Can Think"
One specific skill being prioritized due to AI is Business Context Translation. the ability to understand complex client requirements and guide AI tools towards actual solutions, not just technically correct code. We have observed AI generate perfect authentication systems when clients only needed simple login bypasses. Our most valuable developers now bridge this gap between business needs and AI execution.
I present candidates with complex, real-world scenarios such as: "A restaurant owner claims their 'online ordering is broken' but customers are successfully placing orders." Strong candidates don't immediately resort to coding - they ask clarifying questions about customer complaints, payment issues, or interface problems.
Everything has changed. We used to hire people who could code; now we hire people who can think, then use AI to code their thoughts. We have replaced traditional coding tests with "problem-solving simulations" using real client scenarios and AI tools. We are hiring more "technical translators" - hybrids who bridge business needs and AI capabilities. Surprisingly, our best new hires often have less coding experience but stronger communication skills. Our interviews now include client role-playing and requirement gathering exercises. We're testing interpretation and AI collaboration skills, not algorithm memorization.
Cache Merrill, Founder, Zibtek
9. "AI Can Help With Implementation, But Only Humans Understand Business Needs"
While AI is now capable of writing code efficiently, it still lacks the ability to frame problems that need to be solved or determine exactly what to build. Because of this, the skill I prioritize most when hiring developers today, far more than before AI, is system design and architecture.
My clients want candidates who can design robust, scalable systems that directly address core business problems. AI can help with implementation, but only humans can deeply understand business needs and translate them into effective architectures. That's why system design has become such a critical differentiator in 2025.
To assess this capability, I use a blend of strategies during interviews. I ask open-ended system design questions and scenario prompts like, "How would you design for resiliency at scale?" I also incorporate whiteboard architecture problems to see how candidates structure their thinking. I listen for whether they approach the problem step by step, clarify assumptions, and thoughtfully consider trade-offs rather than jumping straight to code.
Archie Payne, Co-Founder & President, CalTek Staffing
10. "Engineers Who Integrate Business Insights Into Technical Decisions Thrive"
One skill that I've prioritized in hiring is product mindset. This is especially true for product engineers, who blend technical expertise with a deep understanding of business goals and user needs.
AI tools like Copilot and Cursor have automated many routine coding tasks, freeing engineers to focus on more strategic aspects of product development. This shift requires a broader perspective as they now need to not only write code but also understand the business implications and user value of their work. I believe that the ability to see the big picture and align technical solutions with business objectives has become essential.
When evaluating candidates, I look for their ability to understand and clearly articulate business goals and user needs, break down complex problems, define what actually needs to be done, and propose solutions from a product perspective rather than just a technical one. I want to see how they bridge the gap between business teams, designers, and analysts — connecting "what we want" with "how to achieve it" and how they engage meaningfully in planning, prioritization, and strategic decision-making.
In my experience, engineers who integrate business insights into technical decisions thrive in this environment. For example, one candidate I interviewed had collaborated with a Product Owner to assess market impact before developing a new feature, ensuring resources were invested wisely. I've also seen developers who focus solely on technical tasks without considering the broader business context struggle to adapt.
The integration of AI in development has elevated product mindset from a nice-to-have to an essential skill, fundamentally transforming how I approach hiring to prioritize candidates who can think strategically and collaborate across functions to drive product success.
Maxim Ivanov, Chief Executive Officer, Aimprosoft
Debugging AI Is the New Interview Test
Multiple leaders highlighted that debugging AI code requires different skills than debugging code you wrote yourself.
11. "We're Hiring AI Editors, Interpreters, and Sense-Makers"
One skill we now actively seek is contextual thinking in debugging AI-assisted code.
With tools like GitHub Copilot or ChatGPT helping generate substantial amounts of logic, many junior and even mid-level developers rely too heavily on suggestions without truly understanding why the code works or why it doesn't.
AI is fast, but it's not always correct. Consequently, debugging has become less about syntax errors and more about identifying logic gaps, edge cases, and side effects that AI might overlook.
We once had a strong candidate who excelled in all the Data Structures and Algorithms (DSA) rounds and built applications using AI tools. However, when we gave him a prompt to debug an AI-generated code that subtly misused asynchronous handling in Node.js, he couldn't discern what the code was attempting to do before trying to fix it. That's now considered a red flag.
To test this, we give candidates an AI-written function and ask: "What do you think this was supposed to do?" Then, "What could go wrong?" We're not just testing debugging skills; we're assessing how well they think like a human.
So yes, AI has indeed changed our hiring process. We're no longer just hiring developers; we're hiring AI editors, interpreters, and sense-makers.
Jigar Shah, Founder & CEO, WPWeb Infotech
12. "She Spent 15 Minutes Asking Smart Questions Before Writing Any Code"
AI has profoundly changed how we hire developers, though perhaps in subtle yet powerful ways. It's undeniably less about assessing raw coding speed or memorized algorithms and far more about evaluating strategic thinking and adaptability. Our coding challenges now very often start with a fully functional AI assistant at the candidate's disposal.
I actually remember one candidate who really impressed me recently, Ana, let's call her that. We'd given her this task to build a pretty specific data processing pipeline. Instead of just jumping straight into coding, she spent her first fifteen minutes, a full fifteen minutes - asking incredibly smart questions about data sources, expected volumes, how we'd handle errors, and even future scalability. Then, when she finally did use an AI tool, she made it quite clear she was concerned about a suggested for loop's efficiency for really large datasets. So, she intelligently re-prompted the AI, asking for a more optimized, vectorized approach.
We're definitely shifting our focus from just assessing pure coding ability to evaluating deep problem-solving acumen, keen architectural foresight, and that nuanced, uniquely human ability to question, reason effectively, and adapt swiftly. Developers who can critically assess and skillfully guide AI, rather than just be passively guided by it, are the ones who will truly drive meaningful innovation and provide lasting, invaluable contributions in 2025 and beyond.
André Ahlert, CEO and Managing Partner, AEX
The Bottom Line
While everyone's debating whether AI will replace developers, the people actually hiring them are looking for the opposite of what you'd expect. They don't want prompt engineers or AI evangelists. They want the developers who can clean up the mess AI creates.
The irony is perfect: AI was supposed to make coding easier, but it's actually making the thinking parts of development more valuable than ever.
Companies are learning the hard way that AI-generated code comes with hidden costs. The developers who can spot those costs upfront are going to be in high demand.
If you're worried about AI taking your job, stop.
The companies that figure this out first are going to need more developers, not fewer. They just want developers who can think, not just code.
| 2023-01-01T00:00:00 |
https://www.finalroundai.com/blog/software-developer-skills-ctos-want-in-2025
|
[
{
"date": "2023/01/01",
"position": 56,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 58,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 69,
"query": "AI hiring"
},
{
"date": "2023/08/01",
"position": 57,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 70,
"query": "AI hiring"
},
{
"date": "2023/12/01",
"position": 73,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 72,
"query": "AI hiring"
},
{
"date": "2024/06/01",
"position": 63,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 62,
"query": "AI hiring"
},
{
"date": "2025/01/01",
"position": 75,
"query": "AI hiring"
}
] |
|
HiredScore AI for Recruiting | Workday
|
AI For Recruiting
|
https://www.workday.com
|
[] |
Streamlined, data-driven processes and smart action alerts empower recruiters and hiring managers to hire faster and smarter. With a trusted, powerful AI coach, ...
|
See how we help you succeed.
With our 11+ years of delivering AI technology for talent acquisition, providing availability in over 150 countries, and supporting some of the most innovative organizations around the world—our leadership in AI for HR is unparalleled.
Remove hiring friction and bottlenecks by meeting hiring managers in the places they already work, such as Microsoft Teams, with a guided, streamlined hiring process.
Real-time diversity insights are seamlessly integrated into your recruiters’ workflow—giving them greater visibility and removing the constraints of retrospective metrics.
Receive AI-driven, timely notifications that help busy recruiters complete tasks quickly and spotlight moments that matter to maximize business outcomes.
Automatically uncover highly qualified, likely-to-apply leads from your existing databases and partner networks—delivered to recruiters in one unified view.
Prioritize the most qualified candidates and ensure fair and efficient talent practices through unbiased, AI-driven candidate grading.
Leveraging responsible AI, automation designed for HR, and deep integrations, HiredScore AI for Recruiting provides actionable insights in the flow of work for a seamless, focused approach to hiring.
Streamlined, data-driven processes and smart action alerts empower recruiters and hiring managers to hire faster and smarter. With a trusted, powerful AI coach, HiredScore AI for Recruiting elevates decision-making and optimizes outcomes from day one.
The talent landscape changes fast, and recruiting teams need to be faster. With HiredScore AI, teams boost productivity with minimum bottlenecks and maximum agility—all while tapping into your existing talent pools to deliver iconic outcomes.
To access your Workday account, please reach out to your HR or IT department for a link to your company's unique sign in page.
You have automatically signed in to workday.com with your Workday Community account.
Explore our resource library and learn how Workday sets you up for success.
Gain a flexible foundation that helps you move beyond the limitations of legacy ERP.
Improve your operational agility and meet the needs of your industry.
Take control of your contract data and drive results across your organization.
The planning system that integrates with any ERP/GL or data source.
Empower your people and adapt your workforce to the future of work.
Please accept cookies to continue.
This content is blocked due to your cookie preferences for this site. By clicking here, you accept YouTube's Terms of Service and Privacy Policy. Workday will save your choice in a session cookie.
Accept Cookies
| 2023-01-01T00:00:00 |
https://www.workday.com/en-us/products/talent-management/ai-recruiting.html
|
[
{
"date": "2023/01/01",
"position": 59,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 42,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 71,
"query": "AI hiring"
},
{
"date": "2023/06/01",
"position": 63,
"query": "artificial intelligence hiring"
},
{
"date": "2023/08/01",
"position": 55,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 66,
"query": "AI hiring"
},
{
"date": "2023/10/01",
"position": 64,
"query": "artificial intelligence hiring"
},
{
"date": "2023/12/01",
"position": 59,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 56,
"query": "AI hiring"
},
{
"date": "2024/06/01",
"position": 58,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 57,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 64,
"query": "artificial intelligence hiring"
},
{
"date": "2024/11/01",
"position": 61,
"query": "artificial intelligence hiring"
},
{
"date": "2025/01/01",
"position": 69,
"query": "AI hiring"
},
{
"date": "2025/02/01",
"position": 47,
"query": "AI hiring"
},
{
"date": "2025/04/01",
"position": 45,
"query": "AI hiring"
},
{
"date": "2025/06/01",
"position": 42,
"query": "AI hiring"
}
] |
|
Careers at Notion | We're Hiring!
|
Careers at Notion
|
https://www.notion.com
|
[] |
Run better meetings with AI Meeting Notes.Learn more→. Notion. Features ... Software Engineer, AI Product. San Francisco, California; New York, New York ...
|
Our story
Early computing pioneers envisioned a future where machines on our desks could amplify our imagination, extend our intellect, and help us model information in ways never before seen. This is the type of tool we want to build together at Notion — one that gives you the software you can mold and shape like clay to solve your problems your way.
We’ve heard Notion described many ways. It can be as simple as a blank piece of paper, making writing feel light and delightful. It can be as complex as a relational database that stores huge amounts of data. We sometimes compare it to a set of Legos (if Legos were designed by The New York Times). But at its core, Notion is a toolbox of software building blocks that let you manage your life and work however you find most useful.
To make this possible, we’ve brought together a diverse team of individuals passionate about computing, history, art, alternative programming languages, music, skateboarding, and craft. Today, we’re growing faster than ever across offices in San Francisco, New York, Dublin, Hyderabad, Tokyo, Seoul and Sydney 🇺🇸 🇮🇪 🇮🇳 🇯🇵 🇰🇷 🇦🇺
Browse open positions↓
| 2023-01-01T00:00:00 |
https://www.notion.com/careers
|
[
{
"date": "2023/01/01",
"position": 64,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 76,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 98,
"query": "AI employment"
},
{
"date": "2023/03/01",
"position": 80,
"query": "AI hiring"
},
{
"date": "2023/04/01",
"position": 97,
"query": "AI employment"
},
{
"date": "2023/05/01",
"position": 99,
"query": "AI employment"
},
{
"date": "2023/06/01",
"position": 98,
"query": "AI employment"
},
{
"date": "2023/08/01",
"position": 96,
"query": "AI employment"
},
{
"date": "2023/08/01",
"position": 61,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 74,
"query": "AI hiring"
},
{
"date": "2023/11/01",
"position": 97,
"query": "AI employment"
},
{
"date": "2023/12/01",
"position": 99,
"query": "AI employment"
},
{
"date": "2023/12/01",
"position": 78,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 74,
"query": "AI hiring"
},
{
"date": "2024/06/01",
"position": 97,
"query": "AI employment"
},
{
"date": "2024/06/01",
"position": 64,
"query": "AI hiring"
},
{
"date": "2024/07/01",
"position": 97,
"query": "AI employment"
},
{
"date": "2024/10/01",
"position": 63,
"query": "AI hiring"
},
{
"date": "2025/01/01",
"position": 97,
"query": "AI employment"
},
{
"date": "2025/01/01",
"position": 76,
"query": "AI hiring"
},
{
"date": "2025/02/01",
"position": 99,
"query": "AI employment"
},
{
"date": "2025/02/01",
"position": 56,
"query": "AI hiring"
},
{
"date": "2025/03/01",
"position": 98,
"query": "AI employment"
},
{
"date": "2025/04/01",
"position": 51,
"query": "AI hiring"
},
{
"date": "2025/05/01",
"position": 98,
"query": "AI employment"
},
{
"date": "2025/06/01",
"position": 97,
"query": "AI employment"
},
{
"date": "2025/06/01",
"position": 51,
"query": "AI hiring"
}
] |
|
AI Staffing | Find Artificial Intelligence Talent - Insight Global
|
Find Artificial Intelligence Talent
|
https://insightglobal.com
|
[
"Head Of Vendor Management",
"Bre G.",
"Shawn B.",
"Tim S.",
"Rayna W.",
"Cassie F.",
"Julia Koslowsky",
"Insight Global Staff",
"Alexandra Woodford"
] |
Insight Global is an AI staffing agency that provides hiring managers with access to the best talent in the IT industry.
|
Insight Global is one of the largest staffing agencies in the United States. We can match you with AI professionals across an array of specialties, from machine learning engineers to data scientists to AI researchers.
We know how hard it can be to find AI professionals. Our dedicated tech recruiters can find talent for your needs and have them start in as little as one week. We’re dedicated to helping you find talent who will help you drive innovation and success.
Are you an AI Professional looking for a job? Apply here
Questions about staffing? Call us toll-free: 855-485-8853
| 2023-01-01T00:00:00 |
https://insightglobal.com/industries/it/ai-professionals/
|
[
{
"date": "2023/01/01",
"position": 66,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 50,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 40,
"query": "AI hiring"
},
{
"date": "2023/08/01",
"position": 42,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 47,
"query": "AI hiring"
},
{
"date": "2023/12/01",
"position": 47,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 45,
"query": "AI hiring"
},
{
"date": "2024/03/01",
"position": 88,
"query": "artificial intelligence hiring"
},
{
"date": "2024/06/01",
"position": 42,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 39,
"query": "AI hiring"
},
{
"date": "2025/01/01",
"position": 44,
"query": "AI hiring"
},
{
"date": "2025/06/01",
"position": 60,
"query": "artificial intelligence hiring"
}
] |
|
How to Use AI Recruitment in Your Hiring Process | Monster.com
|
How to Use AI Recruitment in Your Hiring Process
|
https://hiring.monster.com
|
[] |
How to Use AI Recruitment in Your Hiring Process · 1. Focus on What AI Does Best · 2. Be Transparent About Your Use of AI · 3. Maintain Hiring Etiquette in AI ...
|
How to Use AI Recruitment in Your Hiring Process
Today’s recruiters and HR managers are expected to do more with less: fill openings faster, find stronger candidates, and do it all with fewer resources. Artificial intelligence (AI) recruitment tools have become accessible for even the smallest companies, and—although they can’t solve all your hiring challenges—AI can help you do your job more efficiently and effectively.
However, when used inappropriately, AI recruitment can make it even harder to address some of the biggest hiring challenges out there, from employee churn to ensuring a diverse, equitable, and inclusive workplace. Knowing how to properly deploy an AI system for your recruiting efforts is key.
AI hiring works best when it is deployed to support and optimize the aspects of talent acquisition that only a human hiring manager can do. These strategies can help you free up valuable time, spot talent you might otherwise overlook, and optimize the benefits of AI (while avoiding the pitfalls):
Focus on what AI does best Be transparent about your use of AI Maintain hiring etiquette Understand the limits of AI Be ready to test and readjust
Following these best practices can help recruiters reduce the cost per hire without increasing the danger that you’ll make a bad hire.
1. Focus on What AI Does Best
Unlike other forms of automation, AI (when supplemented with machine learning technology) is designed to adapt and develop based on how users interact with it. In other words, the more the technology is used the more it learns and, in theory, improves over time.
For example, you might use AI’s pattern recognition capabilities to pinpoint qualities that your best employees share, and then direct it to seek out those same qualities in the application materials provided by job seekers. But make sure that the comparative resumes and assessments you use from top performers correspond to a diverse range of employees to avoid inadvertently teaching your AI hiring software to look for only one type of employee.
AI recruitment technology can also assist in proactive talent sourcing. So, rather than scanning job boards in your sector in search of resumes with the qualities you’re seeking, AI software can search for you and alert you to any candidates that fit your criteria.
AI is particularly effective at streamlining mundane, time-consuming tasks, such as:
Scheduling using automated email, chat bot, or voice recognition software
Identifying skills gaps among your current employees
Assessing applicants’ materials to determine possible hires
Inputting criteria for applicant tracking systems (ATS)
2. Be Transparent About Your Use of AI
Make sure you comply with all the laws guiding the use of AI recruitment in your city or state. A growing number of states and local governments require employers to inform applicants when AI is used in the hiring process.
Many of these laws require recruiters to gain consent from applicants if they are going to use facial recognition software. Others grant candidates the right to have any data obtained using AI deleted at the end of your hiring process.
Even if no such laws yet exist in your locality, alerting candidates that AI will be used in your hiring process and assuring candidates that they will maintain control over their data can improve your employer brand.
3. Maintain Hiring Etiquette in AI Recruitment
One of the biggest complaints about AI recruitment is that it dehumanizes the hiring process. That’s why it’s essential to include automated responses into the early phases of the process. These may range from automated acknowledgements that application materials have been received to early round rejection emails.
It is okay to use AI’s capabilities to cut down on administrative tasks and generate automated correspondence during the early phases of a search that attracts a high volume of applicants. However, it’s never okay for employers to “ghost” applicants, especially at later phases of the hiring process.
Don’t lean on AI to interact with candidates at the later rounds of the hiring process. Think of every applicant as a potential customer, future hire, or brand ambassador, capable of damaging (or enhancing) your brand via social media. Don’t risk offending candidates who’ve invested considerable time into your company’s talent acquisition process by failing to extend the courtesy of a personal rejection.
4. Understand the Limits and Dangers of AI
When used properly, AI can help to make your filtering process more objective since AI does not have any preconceived bias for or against applicants’ names or schools. It simply looks for skills.
In theory, this should mean that using AI will make your hiring process more equitable. In fact, the opposite has been proven true. In many cases, AI tends to exclude women, members of the LGBTQ community, and racially and culturally diverse candidates from applicant pools at a higher rate than traditional recruiting.
It turns out that when algorithms are designed to learn to anticipate the desired outcomes of the humans that use them they do an excellent job of picking up on even the unconscious biases that can guide hiring decisions. For this reason, it is imperative that you conduct frequent quality control tests to measure outcomes against your company’s DEI goals.
5. Be Ready to Test and Readjust Your Algorithms
If your AI recruitment software fails to find candidates with the skills you need, don’t assume the quality of job seekers in your field has suddenly taken a nosedive. Instead, your AI processes may need some adjustment.
Even if you are finding decent candidates to fill your open roles, you still need to conduct control tests at least 2-3 times per year. To make sure your AI is working as intended, perform a human review of a randomized set of resumes for a recently filled role. If you spot qualified candidates whose resumes were filtered out early in your hiring process, you know you need to adjust how you’re using AI.
Make the Most of AI Recruitment to Find and Manage Top-Quality Candidates
Staying up to date with talent acquisition and employee management best practices is the most effective way to make the most of your company’s most valuable asset—your workforce. Learn about innovative tech tools and get the latest hiring tips, expert advice, and how-to guides.
| 2023-01-01T00:00:00 |
https://hiring.monster.com/resources/recruiting-strategies/talent-acquisition/future-of-ai-recruiting/
|
[
{
"date": "2023/01/01",
"position": 68,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 63,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 53,
"query": "AI hiring"
},
{
"date": "2023/05/01",
"position": 58,
"query": "artificial intelligence hiring"
},
{
"date": "2023/06/01",
"position": 60,
"query": "artificial intelligence hiring"
},
{
"date": "2023/08/01",
"position": 62,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 77,
"query": "AI hiring"
},
{
"date": "2023/10/01",
"position": 59,
"query": "artificial intelligence hiring"
},
{
"date": "2023/12/01",
"position": 63,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 63,
"query": "AI hiring"
},
{
"date": "2024/03/01",
"position": 51,
"query": "artificial intelligence hiring"
},
{
"date": "2024/04/01",
"position": 58,
"query": "artificial intelligence hiring"
},
{
"date": "2024/05/01",
"position": 59,
"query": "artificial intelligence hiring"
},
{
"date": "2024/06/01",
"position": 66,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 66,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 59,
"query": "artificial intelligence hiring"
},
{
"date": "2024/11/01",
"position": 58,
"query": "artificial intelligence hiring"
},
{
"date": "2025/01/01",
"position": 61,
"query": "AI hiring"
},
{
"date": "2025/01/01",
"position": 58,
"query": "artificial intelligence hiring"
}
] |
|
AI Hiring Tools - GoHire
|
AI Hiring Tools
|
https://gohire.io
|
[] |
Get various cutting-edge AI hiring tools designed to streamline & optimise your hiring process. Identify the most qualified candidates for your business!
|
LinkedIn message generator
Create compelling outreach messages that capture the attention of top talent on LinkedIn. Say goodbye to generic and impersonal messages and hello to highly targeted and effective outreach.
| 2023-01-01T00:00:00 |
https://gohire.io/ai-hiring-tools
|
[
{
"date": "2023/01/01",
"position": 70,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 62,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 52,
"query": "AI hiring"
},
{
"date": "2023/03/19",
"position": 15,
"query": "artificial intelligence hiring"
},
{
"date": "2023/09/01",
"position": 76,
"query": "AI hiring"
},
{
"date": "2023/12/01",
"position": 64,
"query": "AI hiring"
},
{
"date": "2024/06/01",
"position": 67,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 67,
"query": "AI hiring"
},
{
"date": "2025/02/01",
"position": 21,
"query": "AI hiring"
},
{
"date": "2025/04/01",
"position": 53,
"query": "AI hiring"
},
{
"date": "2025/06/01",
"position": 56,
"query": "AI hiring"
}
] |
|
hireEZ: AI-First, People-Centric Recruiting Platform
|
AI-First, People-Centric Recruiting Platform
|
https://hireez.com
|
[] |
Streamline hiring with an all-in-one recruitment platform featuring AI sourcing, automated resume screening, analytics, and more powered by agentic AI.
|
AI that works with you EZ Agent instantly sources talent and reviews every resume with AI precision. It identifies best-fit candidates and guides hiring teams with an intuitive interface.
Agent Mode: AI that scales with you Activate Agent Mode to engage more candidates without added effort. EZ Agent automates outreach, schedules interviews, and manages responses to help teams scale hiring across roles and regions.
Multi-step AI that becomes smarter EZ Agent adapts with each search. It learns from hiring inputs, candidate data, and outcomes to deliver better matches and stronger talent pools faster than any team could alone.
| 2023-01-01T00:00:00 |
https://hireez.com/
|
[
{
"date": "2023/01/01",
"position": 75,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 68,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 64,
"query": "AI hiring"
},
{
"date": "2023/08/01",
"position": 68,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 83,
"query": "AI hiring"
},
{
"date": "2023/12/01",
"position": 69,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 70,
"query": "AI hiring"
},
{
"date": "2024/06/01",
"position": 72,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 72,
"query": "AI hiring"
},
{
"date": "2025/01/01",
"position": 66,
"query": "AI hiring"
},
{
"date": "2025/02/01",
"position": 8,
"query": "AI hiring"
},
{
"date": "2025/04/01",
"position": 61,
"query": "AI hiring"
},
{
"date": "2025/06/01",
"position": 11,
"query": "AI hiring"
}
] |
|
Hiring with AI for small business · Zoom - Luma
|
Hiring with AI for small business · Zoom · Luma
|
https://lu.ma
|
[] |
Join us, Janet and Ali, founders of Workcraft.ai and winners of Dubai Police's Innovation Award—for a fast-paced, no-fluff session on how small businesses ...
|
Event Full If you’d like, you can join the waitlist.
Please click on the button below to join the waitlist. You will be notified if additional spots become available.
| 2023-01-01T00:00:00 |
https://lu.ma/z7knepn4
|
[
{
"date": "2023/01/01",
"position": 86,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 86,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 86,
"query": "AI hiring"
}
] |
|
AIApply | AI-Powered Job Search Tools
|
AI-Powered Job Search Tools
|
https://aiapply.co
|
[] |
AIApply helps job seekers land more jobs quicker with the power of AI. Our Job Application Kit Generator is one of our tools that creates custom cover ...
|
Leverage AI to showcase your value, position yourself for senior roles, and stay ahead in a shifting market.
AI provides everything you need
Hi John, Hope you're doing well. Just following up on my application—I wanted to check in and see if there's an opportunity to chat. I've spent my career building products that don't just work but change the way people live. From the Macintosh to the iPhone, I've always believed that technology should be seamless, intuitive, and, most importantly, human. AIApply has the potential to redefine how people navigate their careers, and I'd love to explore how I can help shape that future. Let me know if there's a good time to connect. Looking forward to it. Cheers, Steve
Dear HR Manager I'm reaching out about the role at AIApply. You're looking for someone who challenges conventions and builds products that redefine industries—well, that's been the foundation of my career. I co-founded Apple with the belief that technology should be intuitive, beautifully designed, and deeply integrated into people's lives. The Macintosh changed personal computing, the iPod revolutionized music, and the iPhone redefined how the world communicates. At Pixar, we didn't just create animated films—we pioneered an entirely new way to tell stories, blending art and technology seamlessly. My focus has always been on crafting experiences that don't just function but inspire. I thrive at the intersection of technology and humanity, designing products that feel inevitable in hindsight but revolutionary at launch. AIApply has the potential to reshape how people navigate their careers, and I'd love to help shape that future. Let's talk. Best, Steve
See what your score looks like
Upload your resume to get a detailed score and insights on what's working—and what's not.
Automatically translate your resume to increase your chances of getting hired.
Get real-time interview help and answers to interview questions.
Practice with AI-generated interviews to gain valuable insights and confidence.
Let AI apply to thousands of jobs for you automatically. Save time and get hired faster.
AI generates cover letters for each job application, increasing your chances of getting hired.
AI generates resumes for each job application, based on your skills and experience.
Alex R Recent College Graduate ★★★★★ AIApply was a lifeline . Their tools helped me identify key skills I needed to develop and connected me with the right opportunities. I landed my dream job within a month! Dec 17, 2024
Jess G ★★★★★ SO GLAD I SUBSCRIBED!! Got a job in a week using the application kit and interview help. Jan 4, 2025
Jordan M Job Seeker in Tech ★★★★★ AIApply's AI-driven resume builder helped me craft a resume that really stood out. I got callbacks from companies I've been eyeing for years. This tool is a game-changer for anyone job hunting in the tech industry! Jan 12, 2025
Liam S Experienced Professional ★★★★★ With AIApply, I took my career to the next level. The AI resume builder and direct access to the HR manager opened doors to opportunities I didn't know existed. It's a must-have for anyone serious about career growth Sep 18, 2024
Roman ★★★★★ I must say I'm very impressed . I used the tool to generate a new resume and relevant cover letter to a number of jobs and I heard back from every single one. Oct 1, 2024
Carlos D. Mid-Career Professional ★★★★★ The interview prep tool from AIApply was phenomenal. It used AI to analyze my speech patterns and provided personalized feedback, making me much more confident and articulate in my interviews. It really made a difference! Jan 10, 2025
Maria G Career Changer ★★★★★ Switching careers was daunting, but AIApply made it seamless . Their tailored resumes and job recommendations helped me transition smoothly into a new field . I've never felt more confident in my professional journey! Dec 15, 2024
Janee ★★★★★ Felt so alone, applying to hundreds of jobs and not hearing back. Finally used AIApply for cover letters and to revamp my resume and like magic starting getting invited to interviews! Jan 5, 2025
Poppy B ★★★★★ The resume builder and interview prep is like magic! I got a job in a week after applying for months. Aug 17, 2024
Rohit ★★★★★ Finally starting getting interviews at Apple and Google and nailed the interviews with the help of AIApply. Thank you. Nov 23, 2024
Gab ★★★★★ OMG. Game changer Nov 24, 2024
Tim Kägy ★★★★★ I used to dread writing cover letters, but this AI tool has made it a breeze . It's like it reads my mind and knows exactly what to say. Highly recommend! May 24, 2024
Nivi ★★★★★ Never thought I'd find a tool that makes job applications quite fun ! Nov 29, 2024
Sally ★★★★★ AIApply's cover letter generator is a life-saver! It helped me create a professional and personalized cover letter that caught employers' attention. Dec 3, 2024
Riz Ahmed ★★★★★ i got $100K/year job at google with AIApply's cover letter! Jan 20, 2025
Sandra Q ★★★★★ Goodbye generic cover letters, hello job offers ! Life saver. Sep 17, 2024
Kathhhy ★★★★★ AIApply was excellent and really helped my job hunt - thank you! Mar 22, 2024
Mia P ★★★★★ Landed a $100k/year job after prepping with AIApply. Finally, a smart tool that understands my job search needs! Jul 22, 2024
Ali K ★★★★★ Was job hunting for months until I found you guys on TikTok. Finally, a tool that does the tedious work for me. Thanks AIApply. Jun 23, 2024
Liam T ★★★★★ Transformed my job hunt. Seriously, it's like having a personal career coach ! Oct 14, 2024
| 2023-01-01T00:00:00 |
https://aiapply.co/
|
[
{
"date": "2023/01/01",
"position": 91,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 91,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 93,
"query": "AI hiring"
},
{
"date": "2023/08/01",
"position": 86,
"query": "AI hiring"
},
{
"date": "2023/09/01",
"position": 95,
"query": "AI hiring"
},
{
"date": "2023/12/01",
"position": 87,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 87,
"query": "AI hiring"
},
{
"date": "2024/02/01",
"position": 42,
"query": "AI employment"
},
{
"date": "2024/06/01",
"position": 90,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 88,
"query": "AI hiring"
},
{
"date": "2025/01/01",
"position": 89,
"query": "AI hiring"
}
] |
|
Apple Loses Key AI Executive to Meta's Multimillion-Dollar Hiring ...
|
Apple Loses Key AI Executive to Meta's Multimillion-Dollar Hiring Spree
|
https://www.macrumors.com
|
[
"Juli Clover",
"Tim Hardwick",
"Joe Rossignol",
"Hartley Charlton"
] |
Meta CEO Mark Zuckerberg has been offering AI engineers massive pay packages to poach them from other companies, and a key Apple engineering ...
|
Meta CEO Mark Zuckerberg has been offering AI engineers massive pay packages to poach them from other companies, and a key Apple engineering manager has decided to take the deal, according to Bloomberg.
Ruoming Pang, who manages Apple's foundation models team, is moving from Apple to Meta. He was in charge of a team with approximately 100 employees that work on Apple's large language models. Models developed by Pang's team are used for Apple Intelligence features like email summaries, Priority Notifications, and Genmoji.
Meta lured Pang with a deal worth tens of millions of dollars per year. Meta has also scooped up AI experts from OpenAI, Anthropic, and Scale AI.
Rumors suggest that Apple has been considering relying on technology from Anthropic or OpenAI for a future LLM version of Siri, rather than using the models it has been working on. Those discussions have reportedly impacted the morale of the foundation models team that Pang is leaving. Other engineers on the team are also mulling offers from other companies.
Apple is struggling to catch up to competitors that have more advanced AI features, including Google and Samsung. Earlier this year, Apple delayed the Apple Intelligence Siri features that it had promised at WWDC 2024, and the delay led to a restructuring of its AI teams. Apple's AI efforts are now being overseen by Apple's software chief Craig Federighi and Mike Rockwell, who led Vision Pro development.
| 2025-07-07T00:00:00 |
2025/07/07
|
https://www.macrumors.com/2025/07/07/apple-ai-executive-leaves-for-meta/
|
[
{
"date": "2023/01/01",
"position": 93,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 95,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 98,
"query": "AI hiring"
},
{
"date": "2023/08/01",
"position": 95,
"query": "AI hiring"
},
{
"date": "2023/12/01",
"position": 95,
"query": "AI hiring"
},
{
"date": "2024/01/01",
"position": 94,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 93,
"query": "AI hiring"
}
] |
Pre-Employment Assessments Surging in Hiring to Screen AI ...
|
Pre-Employment Assessments Surging in Hiring to Screen AI Applications
|
https://www.businessinsider.com
|
[
"Jennifer Sor"
] |
Hiring managers are leaning on pre-employment assessments that test applicants' soft skills in order to see beyond their AI-enhanced ...
|
This story is available exclusively to Business Insider subscribers. Become an Insider and start reading now.
Are you happy? Do you sleep well? Do you have many friends? Are you a workaholic?
Those are some of the questions Katelin Eagan, 27, said she had to answer recently when she was applying for a job.
She agreed to take a cognitive and personality assessment as part of the hiring process, but was a bit bewildered. Many of the questions had nothing to do with the engineering position, which, after completing the tests and going through several months of silence, she was eventually rejected for.
Eagan says she's been applying for jobs full-time since the start of the year. Her efforts haven't panned out yet, which she attributes partly to how competitive her field has become and employers having room to be picky.
"I think there's definitely a lower amount than I thought there would be," she said of available roles.
But that may be only part of the story. Employers are growing increasingly selective, partly because many are seeing a flood of seemingly perfect candidates, many of whom are suspected of using AI to finesse their applications, according to recruiters and hiring assessment providers who spoke to BI.
The solution many companies have come to?
Make everyone take a test — and see who candidates really are, irrespective of what ChatGPT suggested they put on their résumés.
According to surveys conducted by TestGorilla, one firm that administers talent assessments for employers, 76% of companies that had hired in the 12 months leading up to April said they were using skills tests to determine if a candidate was a right fit, up from 55% who said they were using role-specific skills tests in 2022.
Employers seem most interested in testing for soft skills — amorphous qualities like communicativeness and leadership — as well as administering general aptitude and personality tests, Wouter Durville, the CEO of TestGorilla, told Business Insider.
Related stories Business Insider tells the innovative stories you want to know Business Insider tells the innovative stories you want to know
TestGorilla's Critical Thinking test was completed more than 100,000 times in the first quarter of this year, a 61% increase compared to the same quarter in 2024.
The firm also offers a Big 5 personality assessment, which was completed more than 127,000 times in the first quarter — a 69% increase compared to last year.
Demand among US employers in particular has been "massive," Durville said, adding that many firms have turned to tests as a result of being overwhelmed with job applications. The US is the largest market for the firm, which is based in the Netherlands.
"The biggest thing is people just want to hire the best people. It's very selfish and it's fine," Durville said.
Canditech, another firm that offers hiring assessments, says it's also seen rapid growth in the last year. In 2024, the assessment usage grew 135% compared to the prior year, CEO Guy Barel told BI. He estimates that assessment usage is on track to soar 242% year-over-year.
Barel says the surge is partly due to the job market tipping more in favor of employers. In many cases, companies he works with are flooded with "tons of candidates" and looking to "move forward as fast as possible," he said.
Criteria, another skills-based assessment provider, says test usage has more than doubled in recent years.
"AI is kind of creating this authenticity crisis in talent acquisition, because everyone can and is putting their résumé into ChatGPT." Criteria CEO Josh Millet told BI. "It's all about demonstrating your ability or your skill or your personality in an objective way that's a little bit harder to fake."
The AI job market
Jeff Hyman, a veteran recruiter and the CEO of Recruit Rockstars, estimates that demand for testing among his clients has increased by around 50% over the last 18 months.
That's due to a handful of different reasons, he said — but companies being inundated by job applications is near the top, thanks to candidates leaning more on AI to gain an edge and send out résumés en masse, he says.
Hyman says a typical job he tries to fill for a client has around 300 to 500 applicants, though he's spoken to companies trying to fill roles with more than 1,000 candidates within several days of being posted online.
The number of job applications in the US grew at more than four times the pace of job requisitions in the first half of 2024, according to a report from WorkDay.
Companies also want to test candidates' soft skills as remote work grows more common, Hyman adds — and they want to be sure they're getting the right person. Depending on the size of the organization, a bad hire can cost a company anywhere from $11,000 to $24,000, a survey conducted by CareerBuilder in 2016 found.
According to TestGorilla, 69% of employers who issued tests this year said they were interested in assessing soft skills, while 50% said they were interested in assessing a candidate's cognitive ability. A separate survey by Criteria ranked emotional intelligence as the most sought-after skill among employers, followed by analytical thinking.
"It's about their personality and to see if they are a good fit to the organization, if they share the same DNA," Durville said, though he noted that, in many cases, companies find the results of the tests to be shaky as a sole evaluation metric.
TestGorilla, Canditech, and Criteria told BI that employers say they're enjoying the time and cost savings of administering tests.
According to TestGorilla, 82% of employers who said they used skills-based hiring — a catch-all term for hiring based on proven skills — said they were satisfied with new hires, compared to 73% of US employers on average.
Canditech, meanwhile, claims its assessments can help employers cut down on hiring time by as much as 50%, and reduce "unnecessary interviews" by as much as 80%, according to its website.
But Hyman thinks there are some issues with hiring tests. For one, he says employers turn down candidates who don't score well "all the time," despite them being otherwise qualified for the job.
The trend also appears to be turning off job candidates. Hyman estimates around 10%-20% of applicants will outright refuse to take a test if employers introduce it as a first step in the hiring process, though that's a practice Canditech's Barel says is becoming increasingly common.
Hyman says he frequently has conversations with employers urging them not to put so much weight on test results, due to the potential for a mis-hire.
"That's lazy hiring, to be honest. I think that's not the right way to go about it," he said.
| 2023-01-01T00:00:00 |
https://www.businessinsider.com/pre-employment-assessments-hiring-tests-ai-job-applications-2025-7
|
[
{
"date": "2023/01/01",
"position": 95,
"query": "AI hiring"
},
{
"date": "2023/02/01",
"position": 98,
"query": "AI hiring"
},
{
"date": "2023/03/01",
"position": 94,
"query": "AI hiring"
},
{
"date": "2024/10/01",
"position": 97,
"query": "AI hiring"
}
] |
|
Meta's 'superintelligence' hiring spree adds an AI leader from Apple.
|
Meta’s ‘superintelligence’ hiring spree adds an AI leader from Apple.
|
https://www.theverge.com
|
[
"Richard Lawler"
] |
... AI Models Executive to Meta's Hiring Spree | https://www.bloomberg.com/news/articles/2025-07-07/apple-loses-its-top-ai-models-executive-to ...
|
Meta’s ‘superintelligence’ hiring spree adds an AI leader from Apple.
Bloomberg reports that Mark Zuckerberg’s latest high-priced AI hire is Apple’s foundation AI model leader, Ruoming Pang, based on an offer worth “tens of millions of dollars per year,” plus Yuanzhi Li from OpenAI and Anton Bakhtin from Anthropic.
Last week, former Apple AI lead Daniel Gross confirmed his departure from the startup Safe Superintelligence Inc., reportedly also to join Meta’s team. Bloomberg’s sources said Pang’s departure “...could be the start of a string of exits.”
| 2025-07-08T00:00:00 |
2025/07/08
|
https://www.theverge.com/news/700196/meta-apple-openai-ai-talent-war
|
[
{
"date": "2023/01/01",
"position": 98,
"query": "AI hiring"
}
] |
Affected by layoffs? How generative AI can help you ...
|
Affected by layoffs? How generative AI can help you prepare to land your next job
|
https://www.linkedin.com
|
[
"Ripudaman Singh",
"Ashley Richmond",
"Elite Health Consultant For Former Athletes Turned Executives",
"Helping Men",
"Fix Their Metabolism To Drop With Systems That Fit Demanding Work",
"Travel Schedules",
"Clients Served",
"Rep Athlete",
"Gregory Heller",
"Gallup Certified Strengths Coach"
] |
Affected by layoffs? How generative AI can help you prepare to land your next job. I'm Ryan Dickerson, an Executive Career Coach. I work with Directors, ...
|
Affected by layoffs? How generative AI can help you prepare to land your next job
I’m Ryan Dickerson, an Executive Career Coach. I work with Directors, VPs, and C-level professionals preparing to make their next career move.
Over the last few months, well over 200k people have been laid off at large companies including Google, Amazon, Twitter, and Microsoft. For many, the news came as a terrible surprise.
Most of the folks I work with have not had to interview with a new company in several years. They have decades of fascinating and relevant stories to tell, but limited recent practice telling those stories in a competitive interview setting.
Practicing your response to a simple prompt like “tell me about yourself” in front of a mirror can be demoralizing and unnerving, especially during a difficult economic time.
However, I’m thrilled to see how advances in generative AI are helping people improve their communication skills, specifically their interview skills. With platforms like Yoodli, candidates can practice mock interviews and receive private, personalized, and actionable feedback on the content and delivery of their answers. Yoodli’s free platform is a powerful resource for people who might be rusty at interviewing and want to get back into interview shape quickly.
What is generative AI and how can it enable interview practice?
Generative AI is a relatively new field of artificial intelligence that’s capable of creating human-like free form output based on specific inputs. In the past, candidates could practice speeches or interviews on platforms such as Yoodli, and they’d get metrics on their filler words, eye contact, pacing, etc. Feel free to check out my previous post about how generative AI is transforming my coaching business.
Using generative AI, Yoodli’s technology is able to generate contextual recommendations on how candidates can stop rambling, be more concise, or even use proven interview training frameworks such as the STAR method (for instance, if you’re asked about a time you led a team or a project, consider using STAR: Situation, Task at hand, the Action you took, and the Results you achieved). This is an efficient and effective way for candidates to get private feedback without the pressure of feeling judged. What’s more, Yoodli provides you with follow up questions, based on your answer, for you to finetune your response so you can simulate the impromptu back and forth with your interviewer.
But I’m an expert! Why should I practice for interviews?
For better or worse, how you communicate your ideas is often a primary determinant of whether you earn a job offer. Let’s say that you’ve updated your resume, applied to a few jobs, and you’ve landed your first interview. What happens when you join the Zoom meeting and the interviewer asks, “tell me about yourself?
Perhaps you think that you can just wing it. You know your story like the back of your hand, right?
An introductory interview or a screening call usually lasts under 25 minutes. In that brief period, the recruiter will evaluate your fit for the role and the company, check a few must-have boxes, and make sure that your compensation expectations line up with their budget. A 7-minute rambling introduction not only demonstrates that you’re unprepared, it also burns through more than 25% of the time allotted for the entire interview. Unprepared candidates don’t tend to advance through the interview process and land job offers.
How you can make the most of Yoodli for interview practice:
Go to Yoodli, select the interview practice module and choose the kind of job you’re applying for (product management, marketing, consulting etc.). You can choose questions from a pre-generated question bank or add your own! I’ve listed 5 frequently asked questions for you to try:
Tell me about yourself
What do you want next in your career?
Tell me about your favorite project from the last 6 months?
Why are you looking for a new role?
What are your compensation expectations?
At the end of your recording, Yoodli will provide you a report summarizing analytics across your word choice (filler words, non inclusive language), delivery (pacing, centering, gesturing) generative AI comments that include rephrasing suggestions and follow up questions!
While AI has come a long way, it cannot give you feedback on human connection - your empathy, passion, authenticity (not yet!). I highly recommend sharing your Yoodli interview with a colleague or interview coach - they can leave you feedback synced with specific parts of the video to help you improve - all asynchronously!
| 2023-01-01T00:00:00 |
https://www.linkedin.com/pulse/affected-layoffs-how-generative-ai-can-help-you-land-your-dickerson
|
[
{
"date": "2023/01/01",
"position": 17,
"query": "AI layoffs"
}
] |
|
Steps to take when you get laid off - AI insights from ChatGPT
|
Steps to take when you get laid off - AI insights from ChatGPT
|
https://www.linkedin.com
|
[
"Textkernel Bullhorn",
"Al Shalloway",
"Centizen",
"Jack Quigley",
"Trudy Lagan",
"Satya B.",
"Information Technology Leader - System Architect"
] |
After a layoff, register for benefits and insurance, update your resume, develop job skills, access free resources, network, and search for jobs.
|
I recently came across this incredible new artificial intelligence tool called ChatGPT created by the OpenAI team. If you have not heard of it, check it out ASAP. Do not pass go...do not collect (or pay) $200 because as of now it is free... Check it out!
To date, I've already used it for a variety of tasks and have not been disappointed:
Lesson plan ideas for establishing organizational data literacy
Sample Data Quality and Metadata Governance policies
Writing poems, short children's stories, and even songs (I'll publish those later)..
Today my company is laying off some of our workforce. Yesterday I heard about Salesforce laying off 8,000 people. So I asked ChatGPT for advice. Because I too am at risk of a layoff, I customized my inquiry to my situation. You prompt the tool with various parameters. And apparently, you can get better results when you ask the tool to imagine or act in a specific role or persona. The recommendations were spot on. Though I did notice some missing advice that I subsequently requested. My edits/additions to the ChatGPT responses are in italics. (Update: As of 2/9 I was laid off and am now following the advice below!)
Prompt : Imagine you are a Professional Recruiter specializing in the area of data, data governance and data management. One of your clients was just laid off from his job as a Manager of Data Governance. What are the critical recommendations you would make to him to help him get a new job as soon as possible?
Answer: As a professional recruiter specializing in the area of data, data governance, and data management, some critical recommendations I would make to a client who was just laid off from his job as a Manager of Data Governance to help him secure a new job as soon as possible include:
Update your resume and LinkedIn profile: Make sure your resume and LinkedIn profile are up-to-date and highlight your relevant experience in data governance, data management, and any other relevant skills. Be sure to include any accomplishments or successes you had in your previous role as a Manager of Data Governance. (When you are ready...turn on "open to work" on your profile! Also - Review the desired skills for roles you want, then make sure YOUR profile has those skills identified. It should help you with receiving better job listings from the LinkedIn search and matching algorithm job recommendations) Network: Leverage your professional network to let people know that you are looking for a new opportunity. (POST a note to your network. This is similar to sending up a flare when you are lost at sea. You may be very pleasantly surprised by the number of repostings, likes and comments you receive). Consider reaching out to former colleagues, classmates, and professionals in the industry. Attend networking events and join industry groups to expand your network. (SEARCH LinkedIn for groups that focus on your areas of interest or professional experience. PARTICIPATE in the discussions. Increase awareness of YOU and your skills/knowledge). Highlight your transferable skills: While data governance and data management are specific skills, you likely have transferable skills that can be applied to other roles and industries. Make sure to highlight your leadership, project management, communication, and problem-solving skills in your resume and LinkedIn profile. (If you are unaware of which of your skills might be transferable, work with a friend to help identify some.) Showcase your expertise: Consider writing articles, blog posts, or white papers about data governance and management topics. This will help to demonstrate your expertise in the field and will make you more attractive to potential employers. (ChatGPT can also assist in this regard, though I do recommend that you put any output into your own words or style. Add your own value.) Stay current with industry trends: The field of data governance and data management is constantly evolving, so it's important to stay current with industry trends and developments. Read industry publications and attend industry conferences to learn about new technologies and best practices. Tailor your job search: Make sure to tailor your job search to the specific roles and industries that interest you. Don't just apply to any job that is remotely related to data governance or data management, make sure it's a good fit for your skills, experience, and career goals. (The current job market is pretty hot considering a 3-4% rate of unemployment. Try not to "settle".) Consider contract work or freelancing: If you're having trouble finding a full-time role, consider taking on contract work or freelancing to keep your skills sharp and build your network. (Some challenges with contract work: Many "body shops" want you to work C2C [corp to corp] which means you'd need to create a corporation, you are completely on your own with respect to employment taxes, unemployment risk and benefits. You may want to try for a W-2 working for the "body shop". That way they deal with the paperwork. Just keep in mind that a contract role may have higher risk regarding longevity). Keep a positive attitude: Job searching can be a frustrating and time-consuming process, but it's important to keep a positive attitude and not get discouraged. Remember that it often takes time to find the right opportunity, and that every interview and networking opportunity is an opportunity to learn and grow.
I hope these recommendations help you in your job search. Remember, data governance and data management is a hot field and a great skill to have, so you should be able to find a new role soon.
Additional Prompt: Please provide additional recommendations , taking into consideration factors such as the need to register for unemployment benefits and healthcare insurance coverage
Of course, here are some additional recommendations I would make to someone who has been laid off, specifically taking into consideration factors such as the need to register for unemployment benefits and healthcare insurance coverage:
Register for unemployment benefits: AS SOON as you are laid off, be sure to register for unemployment benefits. These benefits can provide some financial support while you're looking for a new job, and they can also help you to maintain your healthcare coverage, as some states offer healthcare through the unemployment system. Review your healthcare options: If your healthcare coverage was provided by your previous employer, you will need to find new coverage. Look into your options for individual healthcare plans, as well as options for COBRA coverage. Look for networking opportunities with people in similar situations: See if your previous employer has an outplacement service, or look for professional or social groups which might have support for people who have recently been laid off. This can give you a great opportunity to network with people who are in similar situations, which may lead to new job opportunities or useful advice. (Also make sure you network with the people who were NOT laid off. Often these are friends and colleagues who care about you. Don't hesitate to reach out to them for recommendations on LinkedIn, job ideas or contacts at other companies). Seek out career counseling: if you need additional support, consider reaching out to a career counselor or coach. They can help you with your job search, develop a plan to achieve your career goals, and provide you with advice on how to market your skills effectively to potential employers. Explore online learning: While you're looking for a new job, use this time to develop new skills or expand your knowledge in the field. Look into online courses or certifications, especially ones that will make you stand out in your job search. (I know from experience that the NJ unemployment claims process includes an offer of free online learning - other states may too.
Online Learning Resources:
If you have a library card, you may also be able to access LinkedIn learning for free: https://www.makeuseof.com/tag/lynda-com-free-library/
A few other training sites include:
Free College Courses: https://www.openculture.com/freeonlinecourses.
Coursera - Coursera offers a wide range of online courses from top universities and institutions, including courses in IT, data, AI, and machine learning.:
edX - edX is a non-profit online learning platform that offers courses from top universities and institutions around the world. It has a range of courses in IT, data, AI, and machine learning.
MIT OpenCourseWare - MIT OpenCourseWare is a free online platform that provides access to MIT course materials, including lecture notes, assignments, and exams. There are several courses in IT, data, AI, and machine learning available.
Some good Free Tutorials can also be found here (there are also NOT free courses): https://www.educba.com/ and Learn to code: https://www.freecodecamp.org/
Of course no list of resources is complete without mentioning Udemy: an online learning platform that offers a large selection of courses in a variety of subjects, including IT, data, AI, and machine learning. Many courses are inexpensive, but many can also be found for free. I have a list of about 1500 courses I've "enrolled" in and for which I keep trying to find the time. Secret site with coupons for free Udemy Courses: https://coursefolder.net/live-free-udemy-coupon.php
Please note: These are NOT a complete list of resources. Just some that I'm aware of off the top of my head.
Be creative in job search: Don’t limit yourself to only applying to posted job openings. Look for ways to create job opportunities where none existed before. Research companies or organizations that align with your interests and skills, and then see if you can find an opportunity for them to benefit from what you can offer.
I hope these additional recommendations are helpful. Remember that being laid off can be a difficult and stressful experience, but there are many resources available to help you find a new job and maintain your healthcare coverage. It's important to take advantage of these resources and stay positive during your job search.
Layoffs are challenging. They are very emotional. And they feel very, very personal. The reality is they are generally not "personal". So, DO NOT allow yourself to internalize any feelings of inadequacy that you think may have caused your layoff. Too many factors play into the decisions that identify those who are laid off. They might include age, gender, lifestyle, stage of life, seniority, skills, perception of an ability to change/grow, politics, salary, and/or perception of attitude. They may be random choice.
Don't bother trying to figure out the WHY...just start figuring out what to do next.
Look forward, not backward.
Use everything you learned in the most recent and previous jobs and find a new one.
Or start a side hustle that you can turn into a full time gig and work for yourself instead of a company.
As ChatGPT recommended: stay positive during your job search.
Good luck!
| 2023-01-01T00:00:00 |
https://www.linkedin.com/pulse/steps-take-when-you-get-laid-off-ai-insights-from-chatgpt-smith
|
[
{
"date": "2023/01/01",
"position": 27,
"query": "AI layoffs"
}
] |
|
Big Tech Is Going to Regret All These Layoffs : r/technology
|
The heart of the internet
|
https://www.reddit.com
|
[] |
The only way they're going to regret it is that employees are finally starting to see the wisdom of unions in tech - these 10,000 person layoffs to placate Wall ...
|
Subreddit dedicated to the news and discussions about the creation and use of technology and its surrounding issues.
Members Online
| 2023-01-01T00:00:00 |
https://www.reddit.com/r/technology/comments/10kdgie/big_tech_is_going_to_regret_all_these_layoffs/
|
[
{
"date": "2023/01/01",
"position": 35,
"query": "AI layoffs"
}
] |
|
Layoffs for Data Engineers : r/dataengineering
|
The heart of the internet
|
https://www.reddit.com
|
[] |
Layoffs for Data Engineers. Discussion. Its been a blood bath of layoffs for tech companies as of late ... AI / ML scaling. You guy. Upvote 1. Downvote Award
|
Its been a blood bath of layoffs for tech companies as of late and it clear we are headed towards a recession.
I'm curious to hear various thoughts and the subreddits observations as it pertains to Data Engineers / Data Engineering. Have you been affected by the recent layoffs? Have you observed DE teams being affected? My first instinct is that Data Engineers are such an important role to any company that they are largely insulated from these types of events but then again, you honestly never know.
Please share your experiences
| 2023-01-01T00:00:00 |
https://www.reddit.com/r/dataengineering/comments/10iq2pk/layoffs_for_data_engineers/
|
[
{
"date": "2023/01/01",
"position": 43,
"query": "AI layoffs"
}
] |
|
Imposter syndrome is a tool of the patriarchy - Christa Avampato
|
Imposter syndrome is a tool of the patriarchy
|
https://christaavampato.medium.com
|
[
"Christa Avampato"
] |
The layoffs in the tech sector have left many people blind-sided ... Amazon's AI Layoff Wave: CEO's Email Sparks Outrage — Why SVPs Stay Safe While Workers.
|
Imposter syndrome is a tool of the patriarchy Christa Avampato Jan 24, 2023 -- Listen Share
Imposter syndrome is a tool of the patriarchy
It’s re-evaluation season. The layoffs in the tech sector have left many people blind-sided, deeply and urgently considering their next career move. It’s also graduate school application season where many people start questioning whether or not they’re good enough as compared to their peers.
This is your reminder that imposter syndrome is a tool of the patriarchy. Many in power in various aspects of society are interested in making sure you keep doubting yourself. It allows them to pay you less and to make yourself smaller so they can maintain their influence. It does not serve you. It serves them.
Do not fall for this, ever. You are a talented, radiant, and intelligent person with heart. Don’t let anyone tell you otherwise. Go out into the world like a lantern and shine.
| 2023-01-24T00:00:00 |
2023/01/24
|
https://christaavampato.medium.com/imposter-syndrome-is-a-tool-of-the-patriarchy-21483f12dce0
|
[
{
"date": "2023/01/01",
"position": 88,
"query": "AI layoffs"
}
] |
How to Leverage Artificial Intelligence for HR & Beyond
|
Artificial Intelligence in the Workplace: Equipping Leaders for the Rise of AI
|
https://www.lifelabslearning.com
|
[] |
This blog explores the growing impact of AI in the workplace, from automating time-consuming HR tasks to transforming hiring, onboarding, employee training, ...
|
Summary: Curious about how artificial intelligence is reshaping the way we work? This blog explores the growing impact of AI in the workplace, from automating time-consuming HR tasks to transforming hiring, onboarding, employee training, and workforce planning. Backed by fresh data and insights from our ‘Leveraging AI in People Operations’ webinar, you’ll learn how to use AI tools to boost productivity, personalize learning, simplify performance reviews, and improve the employee experience. Plus, get practical pro tips to build your AI fluency and confidently lead through change.
Everybody’s talking about Artificial Intelligence (AI). In today’s workplace, it’s no longer just a buzzword. From automating repetitive tasks to transforming hiring and onboarding, AI is redefining how we work. According to PwC’s 2024 Global Workforce Hopes & Fears Survey, 62% of workers globally use generative AI daily to enhance their job performance.
At LifeLabs Learning, we like to think of the workplace as a lab — a space for ongoing experimentation and growth. Well, now’s the perfect time to put AI under your microscope and explore how you and your team can use it to improve efficiency, engagement, and employee development.
In this blog, you’ll explore AI in HR and employee experience, learn how AI is used in training, recruitment, and wellness, and gain practical strategies from our webinar, ’Leveraging AI in People Operations’, to build your AI fluency at work.
Why AI in the Workplace Matters
Despite fears about AI replacing jobs, the data tells a different story:
Think of AI as a super flexible assistant that helps in countless ways. With many managers today feeling like they lack the capacity to do their job well, AI offers a solution. It boosts productivity and unlocks time for leaders to focus on high-impact priorities like growth, collaboration, and feedback.
“AI may be the steam engine of the mind.” — Reid Hoffman, LinkedIn co-founder and early investor in AI
How AI is Used in HR and Workforce Management
AI is fundamentally reshaping HR processes, making it easier, faster, and smarter to support employees and lead high-performing teams. According to Gartner, 81% of HR leaders have explored or implemented AI tools, and more than half are already experimenting with generative AI to improve operations.
Here are some of the top ways AI is being used in HR today, with practical applications across recruitment, onboarding, performance, and retention.
Automating Time-Consuming HR Tasks with AI Tools
One of the most common questions in HR today is: What AI tools are used in HR and how do they help? The short answer is: AI helps automate repetitive tasks so people can focus on strategic work. From calendar coordination and meeting summaries to drafting policies and internal memos, AI tools take administrative pressure off HR professionals.
This shift is especially useful for managers overwhelmed by growing to-do lists and limited bandwidth. When used effectively, AI frees you to focus on people, not paperwork.
Find a list of expert-recommended AI tools for HR in the AI for HR Playbook.
How AI Is Used in Employee Training and Upskilling
With rising pressure to deliver fast, relevant, and personalized training, HR leaders are turning to AI-powered platforms. Wondering how AI is used in employee training or what AI tools support skill gap analysis? Modern L&D platforms now use AI to recommend courses, tailor content to role-specific needs, and offer real-time feedback.
These tools don’t just make training more efficient, they also help reinforce high-impact leadership skills like communication, collaboration, and adaptability. At LifeLabs, we call these irreplaceable human abilities Tipping Point Skills™, and they’re the perfect complement to AI-driven learning.
Dive deeper! Read Why People Skills are the Future of Work
“As more and more artificial intelligence is entering into the world, more and more emotional intelligence must enter into leadership” — Amit Ray, AI scientist and author of Compassionate Artificial Intelligence
Leveraging AI to Simplify Performance Management
AI is also helping HR teams reimagine performance reviews. Instead of manually compiling feedback and data, managers can now rely on AI to generate first-draft performance summaries using inputs like 360° reviews, self-assessments, and KPIs.
This approach reduces time spent on documentation and creates more consistency across the organization. Managers still need to personalize and humanize these drafts, but AI gives them a valuable head start and helps ensure no key insights are missed.
Improving Workforce Planning and Retention with AI
AI is increasingly used in predictive analytics for workforce planning, helping HR teams make smarter decisions about staffing, engagement, and growth. These tools can identify warning signs of attrition, spot performance trends, and surface insights that support more proactive leadership.
Looking to retain your top talent? AI can help you detect what’s working, and what’s not, across teams, so you can course-correct and grow more intentionally.
Using AI in Hiring and Recruitment
AI is transforming the recruiting process, from job description creation to resume screening and candidate evaluation. Tools that use machine learning can quickly sift through applications, flag promising candidates, and suggest interview questions that align with core competencies.
That said, it’s important to note that AI in hiring must be used ethically. Many organizations are addressing key questions like: What is AI bias in the hiring process? and How do we reduce bias in AI hiring? To ensure fairness, companies are reviewing AI-generated outputs and using audits to avoid reinforcing systemic biases, especially in jurisdictions where AI hiring tools are now regulated, like New York City.
Dive deeper! Read: Practical Strategies for Ethical, Fair, and Impactful Implementation
How AI Is Used in Employee Onboarding and Experience
Many HR teams are now asking: Can onboarding be automated? and How is AI used in onboarding?
The answer is yes! AI can dramatically improve the new hire experience. With AI-powered onboarding software, companies can automate training sequences, share tailored resources, answer common questions via chatbot, and help employees navigate benefits and policies from day one.
By streamlining onboarding, AI increases productivity and confidence for new hires while saving HR teams hours of manual setup.
Get skilled up in AI – 8 helpful tips Are you ready to equip yourself and your team for the rise of Artificial intelligence in the workplace? Explore these tips we gathered from seasoned leaders who shared their strategies for navigating AI at work in our ‘Leveraging AI in People Operations’ webinar and be sure to pass them along to your team! Always be learning: This is one of our core values at LifeLabs Learning and it applies well to technology in the workplace. Take time to understand the basics of AI: what it can do, where it can be useful, and how it’s changing the way we work. Stay up to date with the latest AI developments by following thought leaders in the field. Poll your peers: Talk to colleagues and friends to learn how they use AI tools in their work and everyday life. AI in the workplace is a hot topic among folks in our POPs United community on Slack where over 5,000 POPs, L&D, and HR professionals come together to network, ask questions, and share best practices. Join in! Get a demo: Schedule a demonstration of an AI-powered platform to deepen your knowledge and provide practical insights into AI functionality. Take a course: Enroll in an introductory course like Google’s Introduction to Generative AI to learn fundamental concepts and important terminology. This will equip you to engage in informed discussions about AI and its role in the workplace. Get hands-on experience: Give yourself and your employees a safe space to play with the capabilities of AI. Experiment with AI tools in non-critical settings to build familiarity and better understand AI’s potential. Try it out: Draft an email or another piece of communication using a tool like Chat GPT to grasp the immediate applications of generative AI and discover how it can enhance everyday tasks. Explore further: Extend your experimentation beyond Chat GPT to AI-integrated platforms like G-Suite, Google Sheets, and Microsoft’s suite of tools. Exploring a variety of AI applications broadens your understanding of AI’s versatility. Be critical: Be skeptical and critically evaluate the results AI gives you. Don’t just trust the machine blindly, as it can make mistakes, like being biased or giving you false information.
Navigating AI with Curiosity
As you venture further into the world of AI in your workplace laboratory, stay focused on uncovering the ways it can best serve you and your team. Discover its potential as a supportive tool to make tasks quicker and better. And maintain a sense of curiosity, for AI’s role and value within your organization are sure to keep evolving.
Want more? Download our AI for HR Playbook
Watch ‘AI Meets HR: Leveraging AI in People Operations’ On-Demand!
FAQs:
| 2023-01-01T00:00:00 |
https://www.lifelabslearning.com/blog/artificial-intelligence-in-the-workplace-equipping-leaders-for-the-rise-of-ai
|
[
{
"date": "2023/01/01",
"position": 70,
"query": "AI employment"
}
] |
|
Synthesia Jobs | See Current Openings - Hiring Now
|
See Current Openings - Hiring Now
|
https://www.synthesia.io
|
[] |
Work with awesome people at a top AI video SaaS company. See job openings and career opportunities.
|
Things need to get done. But for the most part it is up to you to schedule your day, so that it works for you.
| 2023-01-01T00:00:00 |
https://www.synthesia.io/careers
|
[
{
"date": "2023/01/01",
"position": 81,
"query": "AI employment"
},
{
"date": "2023/02/01",
"position": 36,
"query": "generative AI jobs"
},
{
"date": "2023/02/01",
"position": 96,
"query": "AI employment"
},
{
"date": "2025/02/01",
"position": 44,
"query": "generative AI jobs"
},
{
"date": "2025/03/01",
"position": 43,
"query": "generative AI jobs"
},
{
"date": "2025/04/01",
"position": 45,
"query": "generative AI jobs"
},
{
"date": "2025/06/01",
"position": 43,
"query": "generative AI jobs"
}
] |
|
Careers - Google DeepMind
|
Careers
|
https://deepmind.google
|
[] |
Research. Our research teams focus on pushing the boundaries of artificial intelligence theory and practice, scientific discoveries, and AI-powered ...
|
Flexible collaboration
At the heart of Google DeepMind’s mission is our commitment to act as responsible pioneers in the field of AI, in service of society’s needs and expectations.
This requires us to ensure our technology is built by and for those who represent the world we live in. It’s a responsibility we can only take by continuing to cultivate an internal culture that recognizes how our diversity of experience, knowledge, backgrounds, and perspectives enables us to find connections that solve real world problems.
Collaboration is at the heart of everything we do, but we know it may look different every day. That’s why we have a working model that allows for the flexibility of in-office and remote working optimized across the organization.
| 2023-01-01T00:00:00 |
https://deepmind.google/about/careers/
|
[
{
"date": "2023/01/01",
"position": 84,
"query": "AI employment"
},
{
"date": "2023/02/01",
"position": 37,
"query": "generative AI jobs"
},
{
"date": "2023/04/01",
"position": 36,
"query": "generative AI jobs"
},
{
"date": "2023/05/01",
"position": 35,
"query": "generative AI jobs"
},
{
"date": "2023/06/01",
"position": 34,
"query": "generative AI jobs"
},
{
"date": "2023/07/01",
"position": 37,
"query": "generative AI jobs"
},
{
"date": "2023/09/01",
"position": 36,
"query": "generative AI jobs"
},
{
"date": "2023/10/01",
"position": 38,
"query": "generative AI jobs"
},
{
"date": "2023/11/01",
"position": 37,
"query": "generative AI jobs"
},
{
"date": "2023/12/01",
"position": 36,
"query": "generative AI jobs"
},
{
"date": "2024/01/01",
"position": 37,
"query": "generative AI jobs"
},
{
"date": "2024/02/01",
"position": 37,
"query": "generative AI jobs"
},
{
"date": "2024/03/01",
"position": 33,
"query": "generative AI jobs"
},
{
"date": "2024/07/01",
"position": 35,
"query": "generative AI jobs"
},
{
"date": "2024/08/01",
"position": 36,
"query": "generative AI jobs"
},
{
"date": "2024/09/01",
"position": 34,
"query": "generative AI jobs"
},
{
"date": "2024/11/01",
"position": 35,
"query": "generative AI jobs"
},
{
"date": "2025/01/01",
"position": 35,
"query": "generative AI jobs"
},
{
"date": "2025/02/01",
"position": 89,
"query": "AI employment"
},
{
"date": "2025/02/01",
"position": 38,
"query": "generative AI jobs"
},
{
"date": "2025/03/01",
"position": 87,
"query": "AI employment"
},
{
"date": "2025/03/01",
"position": 36,
"query": "generative AI jobs"
},
{
"date": "2025/04/01",
"position": 38,
"query": "generative AI jobs"
},
{
"date": "2025/05/01",
"position": 88,
"query": "AI employment"
},
{
"date": "2025/06/01",
"position": 87,
"query": "AI employment"
},
{
"date": "2025/06/01",
"position": 36,
"query": "generative AI jobs"
}
] |
|
AI Software Engineer - Seattle, Washington, United States
|
AI Software Engineer
|
https://careers.zoom.us
|
[] |
We're Hiring! Zoom offers a structured hybrid working environment for our employees. Open roles in Engineering, Marketing, Legal, IT, ...
|
AI Software Engineer
What you can expect
As an AI Engineer, you will collaborate to design, implement, and optimize AI algorithms and software applications. You will ensure AI training, inference, deployment, and operation are functional, reliable, and scalable in your role.
About the Team
Zoom is seeking a highly passionate AI Software Engineer to join our AI infrastructure team. This AI Software Engineer plays a pivotal role in developing and enhancing AI-powered software solutions.
Responsibilities
Collaborating with multidisciplinary teams to understand project requirements and objectives.
Implementing AI solutions solves complex problems in computer vision, natural language processing and recommendation systems.
Designing, developing, and maintaining AI algorithms, models, and software applications.
Ensuring software reliability and quality by participating in code reviews, testing, and debugging.
Documenting code, algorithms, and technical processes for internal and external reference.
What we’re looking for
Possess a Bachelor's Degree in Computer Science, AI, Machine learning or a related field.
Minimum 3+ years of industry experience or relevant work in a related field.
Demonstrate deep understanding and skill in software engineering, AI, ASR or machine learning through experience.
Be proficient in programming languages such as C++ programming; fluent Python programming; algorithm experience.
Have experience with deep learning, neural networks, and data preprocessing.
Have a solid comprehension of AI concepts, algorithms, and frameworks (e.g. TensorFlow, PyTorch).
Be knowledgeable about software development best practices and version control systems (e.g. Git).
Salary Range or On Target Earnings:
Minimum:
$143,000.00
Maximum:
$312,800.00
In addition to the base salary and/or OTE listed Zoom has a Total Direct Compensation philosophy that takes into consideration; base salary, bonus and equity value.
Note: Starting pay will be based on a number of factors and commensurate with qualifications & experience.
We also have a location based compensation structure; there may be a different range for candidates in this and other locations.
Ways of Working
Our structured hybrid approach is centered around our offices and remote work environments. The work style of each role, Hybrid, Remote, or In-Person is indicated in the job description/posting.
Benefits
As part of our award-winning workplace culture and commitment to delivering happiness, our benefits program offers a variety of perks, benefits, and options to help employees maintain their physical, mental, emotional, and financial health; support work-life balance; and contribute to their community in meaningful ways. Click Learn for more information.
About Us
Zoomies help people stay connected so they can get more done together. We set out to build the best collaboration platform for the enterprise, and today help people communicate better with products like Zoom Contact Center, Zoom Phone, Zoom Events, Zoom Apps, Zoom Rooms, and Zoom Webinars.
We’re problem-solvers, working at a fast pace to design solutions with our customers and users in mind. Find room to grow with opportunities to stretch your skills and advance your career in a collaborative, growth-focused environment.
Our Commitment
At Zoom, we believe great work happens when people feel supported and empowered. We’re committed to fair hiring practices that ensure every candidate is evaluated based on skills, experience, and potential. If you require an accommodation during the hiring process, let us know—we’re here to support you at every step.
We welcome people of different backgrounds, experiences, abilities and perspectives including qualified applicants with arrest and conviction records and any qualified applicants requiring reasonable accommodations in accordance with the law.
If you need assistance navigating the interview process due to a medical disability, please submit an Accommodations Request Form and someone from our team will reach out soon. This form is solely for applicants who require an accommodation due to a qualifying medical disability. Non-accommodation-related requests, such as application follow-ups or technical issues, will not be addressed.
Think of this opportunity as a marathon, not a sprint! We're building a strong team at Zoom, and we're looking for talented individuals to join us for the long haul. No need to rush your application – take your time to ensure it's a good fit for your career goals. We continuously review applications, so submit yours whenever you're ready to take the next step.
| 2023-01-01T00:00:00 |
https://careers.zoom.us/jobs/ai-software-engineer-seattle-washington-united-states-3cd7453c-746d-4805-b645-e13118edaaa8
|
[
{
"date": "2023/01/01",
"position": 92,
"query": "AI employment"
}
] |
|
Meta Pay
|
Meta Pay
|
https://www.meta.com
|
[] |
Apps. Facebook · Messenger · Instagram · WhatsApp · Meta Horizon ; Services. Meta AI · AI Studio · Llama · Meta Pay ; Community. About Meta · Businesses.
|
Meta Pay is an easy, secure way to pay on the apps you already use.
Not in the US? Check availability
| 2023-01-01T00:00:00 |
https://www.meta.com/meta-pay/?srsltid=AfmBOooJyX0WFXxm1Bk8DydX36qm73f0u-Ejihgv-H_4yiFudagcLvHG
|
[
{
"date": "2023/01/01",
"position": 99,
"query": "AI wages"
}
] |
|
AI in Education: The Good, the Bad, and the Downright ...
|
AI in Education: The Good, the Bad, and the Downright Confusing
|
https://domesticdatastreamers.medium.com
|
[
"Domestic Data Streamers"
] |
It is clear that AI is a valuable tool you could use to finish assignments more quickly, but what would be lost in that process?
|
AI in Education: The Good, the Bad, and the Downright Confusing Domestic Data Streamers 11 min read · Jan 16, 2023 -- 1 Listen Share
Words by Pau Aleikum & Marta Handenawer
This article started as a discussion between friends, sparked by the release of ChatGPT last December. Instantly, our minds were racing with the massive amount of tremendously stupid and not-so-stupid applications it could have for our work at Domestic Data Streamers. It is clear that AI is a valuable tool you could use to finish assignments more quickly, but what would be lost in that process? Using ChatGPT feels like cheating; using a shortcut to finish your work, it’s so easy that it can feel as if you are not working at all. This obviously comes with a cost. If you don’t write those words, you are less likely to remember them and less likely to internalize knowledge or connect it to other fields of knowledge you already have. And that, friends, is a problem for education. The Atlantic recently declared that “The College Essay Is Dead,” and although I disagree, this calls for further exploration.
Are generative algorithms like performance-enhancing drugs?
The use of ChatGPT to write academic projects has been a source of significant concern in academia. Three of the four universities we work with have already sent out emails asking that teachers acknowledge the existence of this technology and prepare for it. This is the next phase in our journey from manual calculation to technology-aided information recall, just as we evolved from adding up numbers in our minds to calculators and from basic orientation to Google Maps.
What, then, is the key issue in this controversy? Returning to the feeling of cheating, the key is the effort we put in. How much effort should learning something take?
As Abby Seneor (CTO of Citibeats) put it:
The effort heuristic is a phenomenon investigated by Kruger in 2004 and suggests that people tend to use the amount of effort that has been put into something as a heuristic or shortcut for determining its quality. The main focus of this theory is on “other-generated effort” rather than “self-generated effort”.
Let’s take an analogy from the sport world: the use of performance-enhancing drugs is generally seen as cheating because it gives athletes an unfair advantage, while the use of advanced gear is generally seen as a legitimate way to improve performance. So is the use of AI in academia similar to using illegal substances or more like using performance-enhancing gear?
Drugs are ‘other-generated effort’, they can produce internal changes and alter the body in various ways, while gear generally is external and only enhances the self-generated efforts one puts in. Following this logic, using AI falls into the other-generated effort, and therefore seems unethical and is considered cheating.
Those in favour will argue that the education system is results-oriented rather than education or effort oriented.
If the goal was education the student wouldn’t feel the need to do this; unless it actually made them learn better. So if students have come up with a creative way to get the result that was asked for, they aren’t cheating.
Whilst this isn’t black or white, in the end, it is all about the purpose intended and the end goal.
#Education is not just about acquiring information, It is a way of learning how to think, organize thoughts, refine ideas, express and conceptualize them clearly.
If AI is used as a tool to facilitate learning these types of skills, then it can be a valuable resource. However, it is crucial to ensure transparency and #fairness about the use of it, and also #accessibility to all students so we level the playing field.
“The invention of writing will produce forgetfulness in the minds of those who learn to use it because they will not practice their memory. Their trust in writing, produced by external characters who are no part of themselves, will discourage the use of their own memory within them. You offer your pupils the appearance of wisdom, not true wisdom.” #Socrates clearly didn’t see this coming.
GPTChat, when used as a shortcut to speed up expression mechanics, can simultaneously be very helpful and harmful.
HOW CAN WE DETECT THE USE OF THIS TECH?
Every law has a loophole, and every loophole has a loophole detector. You can detect the use of GPTChat thanks to computer science student Edward Tian who built GPTZero. This application can detect AI-generated text by looking at two concepts, PERPLEXITY, and BURSTINESS.
His website explains these as follows:
PERPLEXITY: the randomness of the text is a measurement of how well a language model like ChatGPT can predict a sample text. Simply put, it measures how much the computer model likes the text. Texts with lower perplexities are more likely to be generated by language models.
Human written language exhibits properties of BURSTINESS: non-common items appear in random clusters that will certainly appear over time. Recent research has extended this property to natural language processing. Some human-written sentences can have low perplexities, but they are bound to spike as the human continues writing. Contrastingly, perplexity is uniformly distributed and constantly low for machine-generated texts.
His site is still very slow and often gives a time-out error, and my test was by no means thorough. I’m curious to learn what full-on AI scientists think of it.
We are starting a new cat-and-mouse game. As AI gets better at generating human-like written text, other tools (normally also using AI) get better at assessing if a human or an AI wrote it.
If you are a scared teacher and want another quicker tool, here you have a tool to detect the use of ChatGPT, and some other simple ideas to apply in class for your peace of mind.
THE INVISIBLE SIDES OF AI
Another aspect of this software to keep in mind is that, as with most technological advances, there is a certain level of alienation. AI may seem like an ethereal, otherworldly force, but it’s made up of natural resources, fuel, human labor, and massive infrastructures. Tools like ChatGPT can give the impression of being weightless and detached from any material reality, but in fact, they require massive amounts of computing power and extractive resources to operate (if you are interested in this idea, I recommend reading Atlas of AI by Kate Crawford).
Still, the biggest mystery of AI is how it actually works, as even the top experts don’t understand how these algorithms operate. We understand the pieces and logic but not the dynamics. My goddaughter breaks things all the time, but I’ve come to realize that most of the time, she is trying to understand how things work, and by breaking them, she can see the interior of the toy and also understand its logic. In the case of AI, this doesn’t work because we can’t break this technology in any way that a human could recognize. If we look inside, the process is too complex for a human mind, which means you can build a hypothesis of what is going on inside, but you can’t be certain that that’s actually happening.
This fact makes this technology a black box, and as most of the things we don’t understand, we refer to magic to explain them. You can find headlines all over the internet talking about “The AI new god,” an “AI oracle”, or “the ultra-intelligent AI” as if it were some entity that “knows.” The truth is that it doesn’t know; it is just a mathematical formula. A very complex one, but a formula with statistical results nevertheless, and this black box idea will keep feeding naive headlines in the media and building fantasy narratives about the actual limitations of this technology.
AI AS AN ASSISTANT
In our case, as a research and design studio, we are using it. If we have to describe something that 1,000,000 people have already described, then maybe there is no added value in rewriting it again. But, if the goal is for you to internalize and acquire this knowledge, then we will write it 1,000,000 times over if necessary.
Using this tool for internal documentation is impressive. We’ve done it, and we’ll keep doing it to speed up reporting and give more team members the opportunity to be informed and communicate critical ideas. It also works well when playing with formats (you can explore our latest article on ChatGPT uses here), and if you use the right prompts, you have a fantastic brainstorming assistant on hand.
Problems start appearing when one uses AI to generate new ideas or perspectives without human input or filtering. In these cases, the work’s authorship becomes unclear, and the value of being a human using AI tools is lost. Instead of using these tools to enhance our capabilities, we become reliant on them. If we wanted to be polemic, we could even say that if you are not using the AI correctly, then the AI is using you, but seeing as there isn’t anything like a sentient AI we only can state that the company that owns this technology would be using you.
We delegate specific responsibilities to different technologies. We use Google and Wikipedia to look up historical facts and information, calculators to perform complex mathematical equations, and calendars to keep track of our appointments and errands. These technologies can be incredibly convenient and time-saving, but it is essential to recognize that they are not always foolproof. Google Maps has been known to lead us to incorrect destinations or take a less-than-optimal route. Similarly, information found on the internet may not always be accurate or complete. We must use these technologies as tools to assist us in our work rather than relying on them entirely, and it’s essential to clearly understand that their use is not bulletproof.
THE CASE OF UNIVERSAL VOICE
We had similar concerns about Google voice assistant. Even if it’s a fantastically useful technology for the visually impaired, and speeds up some processes, it creates a new problem when opening it up to a broader audience. It is that it gives just, and only one answer to any query. This somehow implies that a choice has been made, so you no longer get to choose which is the best result. This creates what we call the Universal Voice, an entity that talks like a human to you, and gives answers to most of your questions, but only one, which is, therefore, the best one, the one that is true by default. What happens to all the other options? Who is speaking? Who decides what this voice can answer? What values does this voice follow? To whom does it give more visibility? If we already have problems navigating through Google with all the advertisements, then what will happen if OpenAI decides to integrate advertisements as a business revenue source? These questions will become vital if ChatGPT starts to be used as a search engine.
CAN WE BYPASS THE UNIVERSAL VOICE?
There are ways. The good thing about chatGPT is its immense database so that you can trigger different voices and perspectives. Imagine that you want to hear an account of the Vietnam War by Noam Chomsky or Richard Nixon. Well, you’d soon see it’s the same facts but two different stories. AI generative tools can help us enrich the diversity of opinions and find spaces where we can agree with divergent perspectives expeditiously. Just prompt it so that it brings a specific perspective into play.
This idea brings us to the fantastic world of epistemologies, specifically the possibility of an Epistemology of AI.
Since these technologies contribute to the general production of knowledge, it might be smart to look at the big challenges they pose. One big issue is that AIs often use unclear references extracted from different sources that, when combined, can be perceived as a solid form of universal knowledge. The moment you type in a question, the AI gives you one cohesive response that feels very much like the truth. But is it the truth? And is it really creating new knowledge?
In that sense, it is helpful to keep in mind that an AI will never speak as Nixon or as Chomsky, even if it looks like it. And here’s the takeaway: AIs have their own epistemic limitations that can condition the ways we produce and process information if we use them as our only source of knowledge.
De Araujo, de Almeida and Nunez explore this in the abstract of their paper:
“The more we rely on digital assistants, online search engines, and AI systems to revise our system of beliefs and increase our body of knowledge, the less we are able to resort to some independent criterion, unrelated to further digital tools, in order to asses the epistemic quality of the outputs delivered by digital systems. This raises some important questions to epistemology in general, and pressing questions to be applied to epistemology in particular. “
In this context, it is important to resurface the work of feminist epistemologies such as Donna Haraway’s Situated Knowledges. A concept used to emphasise that absolute, universal knowledge is impossible and demands a practice of positioning that carefully attends to power relations at play in the processes of knowledge production.
Today AIs could be performing what Haraway calls “the god trick,” enabling “a perverse capacity […] to distance the knowing subject from everybody and everything in the interests of unfettered power”. So if we’re concerned about AI and knowledge production, we should probably think of ways of creating epistemologies that move away from “a conquering gaze from nowhere.”
— > Here more about Haraway and Situated Knowledge
WHAT’S NEXT?
Looking at the meteoric evolution of AI tools over the past year, we can already say with some certainty that 2023 will bring an incredible number of new tools and applications that will most likely perform much more specific, purpose-driven functions than we have seen so far with image generation and ChatGPT. Yet will need to remain aware of some of the emerging problems that come with the broader integration of these tools into society.
As Dan Shipper says: Sadly, it’s sort of like the tendency of politicians and business leaders to say less meaningful and more vague things as they get more powerful and have a larger constituency. The same happens with technology, and the more prominent and popular ChatGPT gets, the bigger the incentive will be to limit what it says so that it doesn’t cause PR backlash, harm users, or create massive legal risk for OpenAI. It is to OpenAI’s credit that they care about this deeply, and are trying to mitigate these risks to the extent that they can. Still, it is evident that by doing so, they are limiting the software’s capacity in both directions. Prompts that I was using a month ago are blocked today, and the conversation feels generally less fluid than in the beginning. Still, the good news is that it is probably much more secure.
Looking forward, we should ask ourselves what role these tools play in our schools, workplaces, and even in our homes whilst considering the new narratives they will build and how we can secure a constant fight and surveillance over the imperant monolithic voice that AI could become.
| 2024-03-29T00:00:00 |
2024/03/29
|
https://domesticdatastreamers.medium.com/ai-in-education-the-good-the-bad-and-the-downright-confusing-baea640913b0
|
[
{
"date": "2023/01/01",
"position": 5,
"query": "AI education"
},
{
"date": "2023/01/01",
"position": 7,
"query": "artificial intelligence education"
}
] |
Health - Google AI
|
Google AI
|
https://ai.google
|
[] |
AI has the potential to help save lives by transforming healthcare and medicine through the creation of more personalized, accessible and effective solutions.
|
Breast cancer is the most common form of cancer globally, and early detection through breast cancer screening can lead to better chances of survival. Working with healthcare partners like Northwestern Medicine, we developed an AI system that integrates into breast cancer screening workflows to help radiologists identify breast cancer earlier and more consistently. Our published research shows that our technology can identify signs of breast cancer as well as trained radiologists. We are now bringing this research to reality by partnering with iCAD to embed this technology in clinical settings.
| 2023-01-01T00:00:00 |
https://ai.google/health/
|
[
{
"date": "2023/01/01",
"position": 6,
"query": "AI healthcare"
},
{
"date": "2023/02/01",
"position": 6,
"query": "AI healthcare"
},
{
"date": "2023/06/01",
"position": 5,
"query": "AI healthcare"
},
{
"date": "2023/07/01",
"position": 7,
"query": "AI healthcare"
},
{
"date": "2023/08/01",
"position": 7,
"query": "AI healthcare"
},
{
"date": "2023/11/01",
"position": 9,
"query": "AI healthcare"
},
{
"date": "2023/12/01",
"position": 9,
"query": "AI healthcare"
},
{
"date": "2024/01/01",
"position": 9,
"query": "AI healthcare"
},
{
"date": "2024/03/01",
"position": 9,
"query": "AI healthcare"
},
{
"date": "2024/09/01",
"position": 9,
"query": "AI healthcare"
},
{
"date": "2024/11/01",
"position": 9,
"query": "AI healthcare"
},
{
"date": "2025/02/01",
"position": 6,
"query": "AI healthcare"
},
{
"date": "2025/02/01",
"position": 27,
"query": "artificial intelligence healthcare"
},
{
"date": "2025/03/01",
"position": 28,
"query": "artificial intelligence healthcare"
},
{
"date": "2025/04/01",
"position": 5,
"query": "AI healthcare"
},
{
"date": "2025/04/01",
"position": 29,
"query": "artificial intelligence healthcare"
},
{
"date": "2025/06/01",
"position": 5,
"query": "AI healthcare"
}
] |
|
Economics of Artificial Intelligence in Healthcare: Diagnosis vs ...
|
Economics of Artificial Intelligence in Healthcare: Diagnosis vs. Treatment
|
https://pmc.ncbi.nlm.nih.gov
|
[
"Narendra N Khanna",
"Department Of Cardiology",
"Indraprastha Apollo Hospitals",
"New Delhi",
"Mahesh A Maindarkar",
"Stroke Monitoring",
"Diagnostic Division",
"Atheropoint",
"Roseville",
"Ca"
] |
AI reduces healthcare costs as compared to conventional methods. It has been shown before the cost saving due to AI in treatment is more effective as compared ...
|
Abstract Motivation: The price of medical treatment continues to rise due to (i) an increasing population; (ii) an aging human growth; (iii) disease prevalence; (iv) a rise in the frequency of patients that utilize health care services; and (v) increase in the price. Objective: Artificial Intelligence (AI) is already well-known for its superiority in various healthcare applications, including the segmentation of lesions in images, speech recognition, smartphone personal assistants, navigation, ride-sharing apps, and many more. Our study is based on two hypotheses: (i) AI offers more economic solutions compared to conventional methods; (ii) AI treatment offers stronger economics compared to AI diagnosis. This novel study aims to evaluate AI technology in the context of healthcare costs, namely in the areas of diagnosis and treatment, and then compare it to the traditional or non-AI-based approaches. Methodology: PRISMA was used to select the best 200 studies for AI in healthcare with a primary focus on cost reduction, especially towards diagnosis and treatment. We defined the diagnosis and treatment architectures, investigated their characteristics, and categorized the roles that AI plays in the diagnostic and therapeutic paradigms. We experimented with various combinations of different assumptions by integrating AI and then comparing it against conventional costs. Lastly, we dwell on three powerful future concepts of AI, namely, pruning, bias, explainability, and regulatory approvals of AI systems. Conclusions: The model shows tremendous cost savings using AI tools in diagnosis and treatment. The economics of AI can be improved by incorporating pruning, reduction in AI bias, explainability, and regulatory approvals. Keywords: artificial intelligence, deep learning, machine learning, diagnosis, treatment, cost-effectiveness, health economics, AI pruning, AI explainability, AI bias, recommendations
1. Introduction The United States is the leading nation in cutting-edge medical training, research, and technology, notably in the healthcare industry. However, with the lowest health results and subpar public services when contrasted to the top ten nations, healthcare expenditure in the United States stands out as being the highest (when compared to Canada, Germany, United Kingdom, Australia, Japan, Denmark, France, the Netherlands, Switzerland, and Sweden). Between 1960 and 2022, healthcare spending in the United States increased from 5.0 to 17.9 percent of GDP (or USD 3.5 trillion), with an average increase of USD 146 to USD 10,739 per person. Almost a quarter of all healthcare dollars spent in the United States were wasted [1]. The leading causes of this expenditure include avoidable and correctable system drawbacks, such as subpar vigilance delivery, overtreatment, and improper health care delivery. This is more serious than it seems [2,3,4]. Artificial Intelligence (AI) based systems, in contrast, can dramatically reduce such inefficiencies, resulting in a considerably more efficient and cost-effective health ecosystem [5]. The incorporation of technology into healthcare has altered how we think about patient safety, hospital administration, producing new and better drugs, and, finally, making treatment decisions exclusively on data [6]. Technology has beneficial aspects for healthcare, particularly in both diagnosis and treatment [7,8]. By enabling real-time patient information to be accessed with only a few taps on a screen, technology is now paving the way for fast care management that will, in an emergency, reduce casualties. The Internet of Medical Technology (IoMT), artificial intelligence (AI), machine learning (ML), and deep learning (DL) are currently the primary drivers [8,9]. Innovation is becoming the centerpiece [10,11,12,13]. AI technological development improves existing systems, especially medical imaging [9,14] and coronary artery disease diagnosis [15,16], reducing human error, increasing patient care overall, and making doctors’ responsibilities easier [17]. The healthcare information technology (IT) sector has been driven to provide better treatments using big data, virtual reality, mobile technology, wearable medical devices, telehealth, and more, simply out of a desire to perform better [18,19,20]. The ability to reduce workflow and refocus most of a doctor’s attention on providing outstanding patient care has been made possible by systems that use AI and better data management [21]. It is impossible to overstate the value of technology in healthcare. Technical advancements has changed the face of the healthcare sector [22], and in particular, AI has changed the healthcare sector scenario. Medical applications have made extensive use of ML and DL algorithms [23,24]. AI-based solutions use databases to make decisions and are data-driven. It discovers non-linear correlations between the cardiovascular outcomes and the input predictors [25]. ML-based algorithms have the potential to simultaneously employ complicated, non-linear correlations among several input risk predictors (or qualities), in contrast to conventional statistical risk prediction methods [25,26]. For example, wall tissue characterization of atherosclerotic carotid [27,28,29,30,31,32], image segmentation [33,34,35,36,37], and cardiovascular disease (CVD) risk stratification [38] are features that DL algorithms directly extract from the input data to make predictions [9]. It has also been shown that convolution neural network (CNN) DL algorithms can extract features, followed by the training and testing of an ML-based classifier to produce a superior classification [39,40]. Recently, CVD risk and coronary artery calcium scores have been predicted using retinal images [41,42]. Predictions of diabetic retinopathy (DR) have been made using ML and DL-based systems [43,44,45,46]. Therefore, AI-based systems make it possible to examine the risk of stroke and CVD diseases and the need for human intervention [47]. The use of AI-based algorithms in specific carotid ultrasonography applications has shown promise [48,49]. Therefore, these AI-based models may be used in patient risk evaluation to jointly treat diabetic retinopathy (DR) and CVD illnesses [50]. The positive economic effect is a critical decision element in determining whether to invest in an AI solution in the healthcare business [51]. The healthcare provider and insurance businesses, in addition to the medical and pharmaceutical technology sectors, are significantly affected [52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69]. However, the broad economic impact of digital health solutions, in general, has been extensively studied in the presented paper. The saving of time in diagnosis and treatment procedures results in a direct saving of money. Using this hypothesis, an AI-based economic model for diagnosis and treatment is presented.
2. Background Literature AI-enabled devices, such as advanced computed tomography (CT) scans, magnetic resonance imaging (MRIs), and ultrasounds, can carry out repetitive, simple tasks more accurately, reducing medical errors, reducing cost, and promoting early diagnosis and intervention before serious situations arise [1,2]. For instance, an Israeli start-up has created AI algorithms for diagnosing conditions including osteoporosis, brain hemorrhage, malignant tissue in breast mammography, and coronary aneurysms that are equally accurate or more accurate than humans [3]. These are powerful paradigms for preventing manual and time-consuming procedures, thereby reducing costs. According to a recent Newsweek article, AI has demonstrated 99% accuracy and is substantially faster than humans in evaluating and analyzing mammograms. This has made it possible to diagnose breast cancer more quickly, improving the cost of diagnosis [4,5]. In today’s time, the ability to precisely and successfully utilize the potential of data has authorized more effective decision making across the majority of businesses [6]. The same is true for healthcare, where massive data collection is made available for AI-enabled algorithms that can examine pattern-based outcomes, leading to improved time analysis for decision making [7,8]. Healthcare professionals are beginning to move toward AI-based solutions for predicting outcomes which can help in optimal medications based on patient profiles, thereby lowering long-term costs [9,10]. By ensuring that the appropriate actions and treatments are tailored to each patient, AI enhances clinical decision-making and provides customized care [11]. The results will be significantly improved immediately, lowering expenses related to post-treatment problems, which are a significant cost factor in most healthcare ecosystems worldwide [12]. AI has the potential to speed up the creation of life-saving medications, thereby saving billions of dollars that could be invested in maintaining healthy ecosystems [13]. A start-up supported by the University of Toronto recently created a supercomputer-based algorithm that resembles and evaluates millions of potential medications that help in forecasting their effectiveness against the Ebola virus. This directly helps in cutting costs, reducing time, and, more importantly, saving lives by reconfiguring the existing treatments [14]. Advancements in gene-based biomarkers, where billions of patient information points can be analyzed in a short amount of time from a blood sample using at-home devices, can improve AI-based drug research for clinical trials, directly affecting drug costs [15]. People can be empowered by AI to make wiser health choices. All across the world, numerous people already utilize wearable devices to collect everyday data, including heart rate and sleep habits [16]. With the help of this AI data, people at risk of particular diseases could be risk stratified well before the threat becomes acute, thereby eventually reducing cost [17]. Already, AI-based smartphone apps provide fine-grained patient profile details, which could help patients with certain chronic conditions to manage their sickness, leading to healthier lives [18]. This has a direct bearing on the economics of healthcare. It is vital to investigate if the economic models truly meet the quality requirements that have been established to enable the decision-making for the deployment of AI in healthcare. Based on this economic analysis, our study will provide the knowledge necessary to decide in favor of or against the application of AI in hospitals, industry, and payer situations. In other words, it can be said how AI technology transforms in terms of costs, specifically the AI-based diagnosis and treatment paradigms in healthcare, and compare it against the current conventional (non-AI-based) approaches. This is exactly the aim of our study.
3. Search Strategy The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) paradigm were used to select the 200 best AI studies for diagnosis and therapy (Figure 1) and served as the foundation for the search strategy. The usage of repositories such as PubMed, Google Scholar, and IEEE are three important databases that were utilized in the process of locating and screening relevant publications through the usage of keywords such as: “AI-based cost-effective therapy,” “AI and cost-effective treatment,” “cost-effective treatment,” “cost-effective health ecosystem,” “cost-effective AI analysis in healthcare,” “cost-effective solution in healthcare,” “AI-based cost-effective diagnosis,” “cost-effective treatment diagnosis and artificial intelligence,” “cost-effective treatment diagnosis and treatment,” “artificial intelligence,” Economics using AI,” “preventive screen using AI,” “AI-based decision making in health care,” “machine learning in health care,” and “deep learning in health care.“ Healthcare were used to exclude studies: (i) insufficient data in research, (ii) unrelated studies, and (iii) articles that were irrelevant to the topic at hand. This led to the elimination of 78, 52, and 14 studies, which were each designated by the symbols E1, E2, and E3, respectively. As a result, the final pool of research consisted of 200 different cases. Either the costs of AI-based healthcare resources are ignored in this research, or they are compared to more traditional cost models. There will be 78 studies that were not chosen to move on to the next stage of the selection process; these are denoted by the letter E1 in the PRISMA model. (i) They are not focusing most of their efforts on the economics of healthcare. For the sake of this investigation, we are only interested in works that examine the connection between AI and the economics, diagnosis, and treatment of healthcare (ii) If studies show a link between AI and cardiovascular disease, diabetes, renal disease, or any other condition, we will not consider it because there has been no cost analysis. This category, which in the PRISMA model is denoted by the letter E2 and included 52 studies, had a total of participants. The research with incomplete evidence were the ones that did not give us sufficient data to include them in our analysis. The results of these analyses indicate there is no proof to support a link between cost and healthcare resources for AI. No attempts were made to conduct such interactions. The interaction between cost analyses was not considered. Figure 1. Open in a new tab PRISMA model for selection of studies. Studies on the diagnosis and treatment of numerous disorders, including dentistry, oncology, dermatology, kidney, ophthalmology, COVID-19, and CVD, are shown in Figure 2. Every study was subjected to a feasibility analysis before being cross-checked with scientific validation to ensure that it closely matched our objectives. Most of the papers demonstrated the role of AI in disease diagnosis with an explanation of the cost-effective technique that were available. The proposed study includes articles from various healthcare fields such as dentistry (9), oncology (14), dermatology (16), neurology (21), nephrology (23), ophthalmology focused on diabetic retinopathy (28), and immunology investigations focusing on the severity of COVID-19, which includes pulmonary. Acute Respiratory Distress Syndrome (ARDS) was shown in 32 investigations, and the studies explaining CVD, stroke severity, and risk stratification numbered 41. Figure 2. Open in a new tab Statistical distribution of various diseases. The research on cost-effective AI-based diagnosis and therapy for multiple fields of view, which covers dental treatments (such as digital X-ray imaging modalities in cavity treatment, amongst other dental procedures), and several studies conclude that image-based focused radiation on lesions, targeted drug delivery, and other uses are cost-effective strategies to treat cancer [70]. The cost-effective treatment of skin illnesses such as psoriasis [71], skin cancer [72], wound care, and other similar conditions are the primary focus of a significant portion of the ongoing research. Using fog AI, it is possible to test for a wide variety of diseases at a reduced cost, including Parkinson’s [73,74,75,76], COVID-19 [77,78], and CVD [79,80]. The number of studies that demonstrate cost-effectiveness in treatment is significantly lower compared to the number of studies that demonstrate cost-effectiveness in terms of diagnosis.
6. Recent Advances in Artificial Intelligence and Its Relationship to Economics Three major advancements in the field of AI that cannot be neglected are, namely, (a) pruning of AI (PAI) models, (b) explainability of AI (XAI) models, and (c) Risk of Bias (RoB) in AI models. These are vital for improving AI performance and comfort level of integrating the AI models in AI-based products in diagnosis and treatments. 6.1. Pruned Artificial Intelligence Systems and Its Effect on Economics ML and DL techniques have been widely used for various disease detection and classification due to their powerful ability to build training models which can be used for prediction on unseen or seen data sets [36,126,151,152,153,154,155]. Utilizing GPUs or supercomputers is one method for resolving the processing challenge [156,157,158]. Even though they are costly and challenging to maintain over time, LeCun et al. [159] were the first to introduce the idea of pruning to the field of deep learning in their 1989 publication, “Optimal Brain Damage.” Pruning is the process of eliminating extra weights from a model or query region to eliminate unnecessary or unimportant areas [160]. By selecting the appropriate and correct hyperparameters during model training, this pruning approach was expanded to optimize storage [161] and speed up model development [29]. Agarwal et al. [35] implemented eight pruning deep learning models for COVID-19 computed CT lung segmentation and heat map localization images. Four evolution algorithm (EA) approaches, namely Differential Evolution (DE), Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Whale Optimization (WO) were used to optimize two basic DL networks, fully connected network (FCN)/segmentation network (SegNet), to solve the storage and speed issue (Figure 17). The eight pruning procedures are thus four times two (i) FCN-DE, (ii) FCN-GA, (iii) FCN-PSO, and (iv) FCN-WO, with FCN and (v) SegNet-DE, (vi) SegNet-GA, (vii) SegNet-PSO, and (viii) SegNet-WO in DL framework. These pruning methods need more evaluation in terms of the tradeoff between parameter size vs. real-time usage vs. performance of AI pruning models. If the performance of the pruned AI model is superior to conventional AI models, this will further improve the economics in diagnosis and treatment paradigms. Figure 17. Open in a new tab Eight systems were created using four pruning approaches (DE, GA, PSO, and WO): FCN-DE, FCN-GA, FCN-PSO, FCN-WO and SegNet-DE, SegNet-GA, SegNet-PSO, and SegNet-WO [35]. 6.2. Explainable Artificial Intelligence Systems and Its Effect on Economics DL techniques have drawn a lot of attention, since they frequently outperform humans in tasks such as recommendation systems, speech and image recognition, and many others. However, these applications are not reliable or comprehensible. A common misconception about DL models is that they are opaque, challenging-to-understand black boxes with complex underlying mechanisms. However, depending on the application, mistakes made by AI systems could be catastrophic. In the medical industry, the lives of the patients depend on these decisions, whereas an unmanned vehicle’s vision-based system error could result in a crash. Explainable AI (XAI), is used to solve the aforementioned challenges. Recently, scientific validation was also evaluated with the help of XAI [37,98,162,163,164]. The role of justice, privacy, openness, and explainability in the DL paradigm has been further developed by the European General Data Protection Regulation (GDPR) [165]. Figure 18 shows the seven customizable processes of DL, which are DL training, quality assurance (QA), installation/deployment, prediction, cross-validation-based testing (A/B test), monitoring, and debugging. This is possible because XAI incorporates a feedback loop. The usability of the AI system improves if XAI is incorporated into the AI system. The demand for such an XAI system grows automatically, hence more considerable revenue. Further, it provides more stability to the AI system, giving longer life to the product design. Figure 18. Open in a new tab Eight aspects of Explainable AI [165]. 6.3. Bias in Artificial Intelligence Systems and Its Economics AI systems were recommended as a potential substitute for existing diagnosis and treatment approaches [166,167]. AI systems, on the other hand, confront several challenges, one of which is a tendency to prioritize accuracy over scientific validation and clinical evaluation [168,169]. Due to a lack of robust ground truth selection such as CVE, coronary CT score, or angiography stenosis, the disease severity ratio is typically approximated and not accurate. It places a significant emphasis on the AI system’s resilience while only a slight emphasis is placed on its authenticity [170]. It introduces bias into the AI system [13,16,155,168,169,171]. It is also important to note that the database contains specific regional patient characteristics; as a result, the model may under or overestimate diagnosis and treatment findings for different ethnicities or comorbidities [164]. Therefore, identifying risk-of-bias in artificial intelligence systems (RoB) [166,167] and adjusting the diagnosis and treatment are essential steps in the process of enhancing risk stratification in emergency department patients. By combining elements such as mobile, cloud, and e-health infrastructure, the performance of AI-based risk classification and therapy can be considerably improved.
7. Regulations and Artificial Intelligence-Based Systems 7.1. Motivation for Building AI-Based Products for a Successful Regulatory Market Approval The challenge in today’s world of biomedical engineering system design is that the focus is on the accuracy and performance of the system, but not on the reliability, stability, safety, failure mode, robustness, sensitivity analysis, mitigation during the failure mode, ability to perform risk analysis and risk mitigation, building the contradictions, and solid user manuals. This causes the system to become unreliable and eventually die out over a little course of time. To sustain AI products, one needs time-to-time regulatory approvals and memo-to-file (MTF). Most of the diagnosis products fall in the Class II category by the FDA 510 (K) regulations. They do not require clinical trials, while most therapeutic products (especially invasive) fall in the Class III category and require clinical trials. Thus, understanding AI-based products and their link to food and drug regulation (FDA) are of vital importance. 7.2. What Should an AI-Based Product Undergo for a Successful FDA 510 (K) Approval? During the AI-based system design, the following points are to be kept in mind for regulatory 510 (K) approval. This is not limited to these, but can be summarized as follows: (i) customer requirements should be clearly laid out; (ii) engineering specifications should be planned well; (iii) used cases must be established; (iv) engineering design should be carefully designed ensuring proper use of 3rd party systems, such as gold standard if the system is a supervised AI-based system; (v) solid verification and validations systems designs; (vi) user-manuals should show under what conditions the system works, the noise conditions, under what bounds the system will malfunction, and what are the mitigations under failure conditions, what are the alternatives for the clinicians (users); (vi) failure mode effective analysis (FMEA) must be duly performed along with risk analysis and risk mitigations; (vii) traceability analysis which links the customer requirements, engineering specification, engineering design, and mitigations; (viii) thorough design of contraindication and predicate designs for the 510 (K) approvals [172]. In AI-based design, AI explainability is of vital importance since most AI-based systems are black boxes; therefore one must show the explanations and justification of the results, such as where the lesions are by color codes (say heatmaps) or show which AI-based features are crucial and why, such as usage of LIME or SHAP by showing, graphically, the positive or negative side of the feature strength [173,174]. The parent firm should submit medical hardware or software for FDA review before it may be sold legally in the US market [175,176]. The regulatory body has three levels of clearance for medically focused AI/ML-based algorithms, including 510 (k), premarket approval, and the de novo pathway, each of which comes with unique requirements that must be met (Table 1). Table 1. Types of Food and drug administration (FDA) approvals for AI/ML-based healthcare technology are described [177]. SN FDA Approval Stages Description 1 510 (k) clearance A 510 (k) authorization is granted to an algorithm if it is at least as secure and effective as another equivalent, commercially available algorithm. Alongside the claim, the applicant for this clearance must provide substantial proof of equivalence. It is illegal to commercialize the algorithm that is awaiting approval until it has been determined to be reasonably comparable to the other algorithm. 2 Premarket approval For Class III medical devices, algorithms receive premarket approval. The safety and efficacy of the latter are assessed through more comprehensive scientific and regulatory processes since they can have a significant impact on human health. The FDA must find sufficient scientific evidence supporting the device’s usefulness and safety before approving an application. The applicant can move further with product marketing after receiving approval. 3 de novo pathway The de novo category is used to categorize novel medical devices with sufficient safety and efficacy and with broad controls, but in which there are no lawfully marketed equivalents. Before approving and permitting the devices to be marketed, the FDA conducts a risk-based evaluation of the device. Open in a new tab 7.3. A Short Note on the Influence of the Changing Technology and Economics Technologies are constantly evolving and volatile; in the case of AI-based systems, the vulnerability is even higher. It is hard to see engineering knowledge stay in one place due to its demand, and thus the reliability of the human capital is at stake. This affects the engineering design and its reliability. The company management should incentivize the engineering resources to stabilize by ensuring a win-win situation for the long-term objectives of the industries, leading to successful regulatory 510 (K) approval and regular MTF. Thus, the factors such as changes in technology, retaining human capital, long-term goals of the companies, and FDA regulation, all are tandemly connected and cannot be ignored for a successful business model. The FDA’s approach to dealing with repetitive revisions primarily relies on manufacturers to uphold GMLP, which stipulates that data from training and testing must be kept separate, algorithms must be evaluated for relevance, and execution and reporting by the manufacturer must be genuine and straightforward. Thus, as long as it accepts continuous advancements, this platform will provide patients with timely access to the most recent technology. However, it is crucial to consider carefully the details that manufacturers provide regarding an algorithm’s design, the intended use for which it is intended, and the effects of changes on local performance [178]. When attempting to evaluate algorithm performance reliability and consistency, there are numerous obstacles [179]. Since each company must purchase its training and testing images, the lack of uniform test sets hinders development and makes it more challenging to evaluate the data modality [180]. This can be a considerable time and expense drain, which might result in an accidental bias in the test sets favoring particular equipment manufacturers, patient groups, or the methods used by technicians to gather the scans. Itis also crucial to realize that the maker bears the responsibility for verification and integrity, which could lead to dishonest use of the technique for financial gain [181].
8. Discussion 8.1. Principal Findings This is the first study in the field of AI economics, as well as an investigation into the cost analysis of AI models for diagnosis and treatment. The review explains how to save costs and time by adopting AI-based solutions in diagnosis and treatment. In a progressively sequential task, we analyze the cost parameter and time for diagnosis and treatment. Further, our study explains the motivation for building AI-based products for successful regulatory market approval, and further to undergo successful FDA 510 (K) approval. We demonstrated that AI lowers healthcare costs when compared to traditional methods. The cost savings from AI in treatment are more effective than the cost savings from AI in diagnosis. When compared to traditional methods, AI saves time in diagnosis and therapy. High accuracy in diagnosis and treatment can be accomplished in a short period. AI-assisted diagnosis improves diagnostic accuracy by removing bias and subjectivity. AI-based medical diagnosis decreases the possibility of incorrect examination. Because of AI technology, patients may feel more at ease when visiting a doctor. AI examines enormous volumes of data to determine which treatments will produce the best outcomes. Implementing AI technology in the healthcare sector can help firms maximize their returns on investments while also reducing costs. The biggest challenge facing AI in many healthcare disciplines is not whether the technologies will be advanced enough to be useful, but rather ensuring their acceptance in routine clinical practice. For AI systems to be widely adopted, they must be certified by regulatory bodies, connected with EHR systems, standardized to the point that similar products perform similarly, taught to physicians, paid for by public or commercial payer groups, and maintained over time. 8.2. Benchmarking An analysis of the information shows that a few studies using different imaging modalities such as MRI, CT, X-ray, US, and ECG have been linked with AI models for the various disease diagnosis and treatment of renal, pulmonary, carotid artery disease, coronary artery disease, DR, and COVID-19. There is very little discussion of AI’s economic modeling seen in the literature. Only a few studies highlight AI models’ economic consequences and operating costs. The benchmarking Table 2 is shown for a few specific studies. Smetherman et al. [182] explained in detail AI products in radiology, and numerous novel uses for these technologies in breast imaging. In addition to outlining potential future payment channels, the article describes the current situation of reimbursement for breast radiography AI algorithms under the conventional fee-for-service model employed by Medicare and private insurers. Additionally, the reader is given a full explanation of the inherent difficulties associated with using the current American payment system for AI radiology systems. To effectively integrate these cutting-edge technologies into their practices and increase patient care and workflow efficiency, breast radiologists are looking for a better grasp of how AI will be compensated. Challen et al. [183] focused on the development of AI in health through the use of ML as a promising area of research, but it is challenging to determine how accurate these systems might be in clinical practice or how reproducible they are in various clinical contexts due to the rapid pace of change, diversity of different techniques, and multiplicity of tuning parameters. This is made worse by the lack of agreement over the best way to disclose a potential bias in ML studies. For this, the authors think that the Standards for Reporting of Diagnostic Accuracy effort could be a good place to start. Additionally, researchers must think about how ML models, such as scientific data sets, can be licensed and distributed to enable the replication of research findings in other contexts. Yuan et al. [184] proposed that the evolution of medical practice from empirical medicine to evidence-based medicine, intelligent diagnosis, and AI-directed medicine is something we are currently witnessing. Although AI in medicine is still in its infancy, there is no doubt that by utilizing the diversity and complexity of real-world data, AI will generate prediction algorithms suitable for routine clinical use shortly. The discussion of future medical evidence may be sparked by the findings presented in the studies, which go beyond the investigation of the first targets for data analysis and interpretation, which are potentially expensive, lengthy clinical trials with a constrained patient population that may eventually supplement or even entirely replace real-world data-driven risk assessments. Solanki et al. [185] presented go-beyond approaches that provide guidelines based on principles such as adherence to “fairness” and adopting a framework based on solutions that AI programmers can use to operationalize ethics in AI for healthcare across all phases of the AI lifecycle, including data management, model development, deployment, and monitoring. The authors strongly emphasize actionable, technical, or quasi-solutions that AI developers can use. The study presented by Biswas et al. [102] uses an AtheroEdgeTM device from AtheroPointTM to deliver a unique, reliable, and clinically-viable solution to cIMT measurements. The DL approach is used by the system to partition lumen-intima LI-far and MA-far to measure cIMT according to an intelligence-based paradigm. For the distant wall of the carotid artery’s final border extraction, the system applies an ML-based joint coefficient approach to fine-tune this. Data preparation employs a multiresolution paradigm to lighten the computational load. All measurements use an adjusted version of the industry standard polyline distance method. Compared to earlier research, the system performs better. Aijaz et al. [71] proposed a study that employed a deep-learning classification strategy to categorize the five types of psoriasis and healthy skin. Five different types of psoriasis can develop: plaque, guttate, inverted, pustular, and erythroderma. After the features of color, texture, and form have been extracted, the convolution neural network (CNN) and long short-term memory (LSTM) have been employed. An accuracy rate of 84.2% was shown when CNN and LSTM were employed. Siy et al. [186] introduced a model consisting of a CNN algorithm with different softmax layers to be deployed to obtain higher accuracy. The results obtained show how dependable and efficient the suggested deep learning application is. The consequences of future action investigation into the proposed and current deep learning application could result in the improvement of conventional techniques in biomedical imaging [187]. Moreover, studies on the psoriasis area and severity index in the future will also be possible to score (PASI). Ali et al. [188] presented study of renal medicine will change as a result of the applications of regenerative medicine, nanotechnology, genomics, artificial intelligence, 3D organ bioprinting, and smartphone applications. Undoubtedly, this will benefit patients’ results and the healthcare system. These improvements are on the way, but they will also bring new difficulties, such as excessive expenses and numerous ethical dilemmas. Viswanathan et al. [189] explained diabetes exacerbated the development of atherosclerotic plaque. Risk evaluation includes several factors in addition to the degree of vascular stenosis. Plaque vulnerability is influenced by its form, kind, composition, location, TPA, and TPV. The potential for better risk assessment and illness treatment is increased when imaging modalities are added to conventional risk variables. To assist doctors to choose the best interventions for their diabetic patients, screening may thus prove to be crucial. Compared to conventional risk calculators, the 10-year integrated risk calculators and image-based phenotypes produce more accurate risk projections, necessitating more research in the reduction of overall morbidity and death. A deep learning-based approach is suggested for PD identification that uses voice patterns. The dynamic articulation transition features and the bidirectional LSTM model are creatively combined in the proposed method to record the time-series properties of continuous speech signals. The experimental results demonstrated that the proposed approach significantly outperforms conventional machine learning models using static features in terms of the accuracy of PD detection under the two evaluation methods of 10-fold cross-validation (CV) and splitting the dataset without sample overlap of one individual [190]. Kamble et al. [191] indicated that when four ML models are used in a dataset that has undergone mathematical processing, three different types of digitalized spiral drawing tests have a significant impact on the classification of PD patients versus healthy controls. Results are based on a 40-patient, tiny, unbalanced dataset. The work presented a data set of spiral drawing images with features. Four ML algorithms were used, and an accuracy rate of 98.1% was achieved. Therefore, future PD diagnosis can be carried out with the support of an extended dataset and an extended computational model to help healthcare research on other neurodegenerative disorders. Our review had several studies that explored the AI model’s relationship with the diagnosis and treatment of various diseases. However, no such article was located that addressed all of the components in our analysis. 8.3. A View for the Future A lot of people are concerned that AI may lead to the automation of jobs and a considerable loss of labor, and this concern has garnered a lot of attention. According to research conducted jointly by Deloitte and the Oxford Martin Institute, AI may be responsible for the loss of 35% of jobs in the United Kingdom within the next 10 to 20 years [192]. The loss of employment may be mitigated by several external factors other than technology. These factors include the price of automation technologies, the size and cost of the labor market, the advantages of automation beyond basic labor substitution, and legislative and social acceptance. These factors may keep the actual number of jobs lost to 5% or fewer [193]. To the best of our knowledge, no employment in health care has been eliminated by AI. The limited penetration of AI into the sector thus far, as well as the difficulties of integrating AI into clinical workflows and EHR systems, has contributed to the lack of job impact [194]. It appears that the healthcare positions most likely to be automated are those involving digital information, such as radiography and pathology, rather than those involving direct patient interaction. However, even in positions such as radiologist and pathologist, AI adoption is likely to be delayed. Even though, as we have shown, technologies such as deep learning are making strides into the ability to analyze and classify images, there are many reasons why radiology professions, for example, will not go away anytime soon [195]. For automated image analysis to gain popularity, significant medical regulation and health insurance changes will be required. Pathology and other digitally related elements of medicine have similar causes [196]. As a result, we are unlikely to witness significant changes in healthcare employment as a result of AI during the next 20 years or so. There is also the chance of new employment being established to work with and improve AI technologies. However, static or increasing human employment means that AI technologies are unlikely to significantly cut the costs of medical diagnosis and treatment throughout that timeframe [197]. It also appears increasingly evident that AI systems will not wholly replace human clinicians, but will supplement their efforts to care for patients. Human therapists may eventually shift toward activities and job designs that require distinctly human skills, such as empathy, persuasion, and big-picture integration. Those healthcare professionals that refuse to collaborate with artificial intelligence may be the only ones who lose their employment over time. 8.4. Strength, Weakness, and Extensions Several benefits have been found from doing this review. Our two practical and cost-effective economic models for diagnosis and therapy are our primary strengths. We looked at the benefits and drawbacks of several implementation strategies and the amount of time they would take to figure out which would be the most cost-effective. When both the diagnostic and therapeutic models are evaluated, the latter offers greater savings. Policymakers in the AI industry will find the results valid, and the method can be applied elsewhere if the results are comparable. A cost-benefit analysis, however, is warranted if results vary significantly between demographics. Our research adequately clarified why it is essential to develop AI-based devices to gain regulatory market approval and the steps required to obtain FDA 510 (K) clearance for AI-based products. Our work has several constraints, the most important of which is its limited generality. Variations in the number of people who undergo screening and the cost of employing human graders and specialists will likely provide varying results across countries. On the other hand, our decision tree may be readily modified to represent these alternative possibilities. Second, we may have underestimated the cost savings from the fully automated model due to fewer false referral instances, due to a lack of relevant literature on the corresponding prevalence; we only examined diagnosis and treatment and overlooked other factors. Lastly, this study can be extended for meta-analysis [171]. We anticipate that AI will be an integral part of emerging medical technologies. It is the central capability propelling the growth of precision medicine, which is widely recognized as a welcome improvement in treatment. We expect AI will eventually master the domain of providing diagnosis and treatment suggestions, notwithstanding the difficulty of early attempts. It is conceivable that most radiology and pathology images will be examined by a machine in the future, thanks to the rapid development of artificial intelligence for imaging processing. The use of speech and text recognition for common healthcare tasks, including patient communication and note-taking, is expected to increase. Table 2. Benchmarking of studies. C1 C2 C3 C4 C5 C6 C7 C8 C9 C10 C11 SN Author Country Journal Study Type FoV Objective PS Cli-Val Diagnosis (Invasive/Noninvasive) Treatment (Invasive/Noninvasive) 1 Smetherman et al. [182] (2021) USA Breast Imaging P.R. Cancer Improving the quality of care and/or reducing healthcare costs by using AI 1012 No Noninvasive NR 2 Challen et al. [183] (2019) UK Artificial intelligence, bias and clinical safety R. Clinical safety To set short and medium ML clinical safety goals NR No Noninvasive NR 3 Almazán et al. [82] (2019) Italy Clinical Pharmacy P.R. Renal Evaluate the effectiveness, safety, and economic cost of nivolumab in real-world clinical practice 221 No Noninvasive NR 4 Yuan et al. [184] (2020) China Medical Sciences P.R. Renal Challenges in kidney diagnosis and treatment NR No Noninvasive NR 5 Solanki et al. [185] (2022) Australia Operational ethics in AI framework R NA NR NR No Noninvasive NR 6 Biswas et al. [102] (2018) India DL-based strategy for accurate Carotid Intima-Media Measurement R Heart The carotid intima-media thickness (cIMT) is an important biomarker for monitoring cardiovascular disease and stroke 204 No Noninvasive NR 7 Siy et al. [186] (2018) Taiwan IEEE Conference R Skin DL-based psoriasis detection 5700 No Noninvasive NR 8 Aijaz et al. [71] (2022) Pakistan Journal of Healthcare Engineering R Skin Effective classification of different psoriasis types using deep learning applications 473 No Noninvasive NR 9 Ali et al. [188] (2022) Iraq Kidney Diseases Transplantation P. Renal Renal medicine NR No NR NR 10 Viswanathan et al. [189] (2020) India Preventive health check in patients with diabetes R. Diabetes Cost-effective carotid ultrasound screening for diabetes patients NR NR Noninvasive NR 11 Sarki et al. [198] (2020) USA Health Information Science and Systems P.R. Diabetes Retinopathy Deep learning-based automated identification of multiple classes of diabetic eye disorders 1748 NR Noninvasive NR 12 Quan et al. [199] (2021) Japan IEEE Access P.R. Parkinson’s Using dynamic speech features, a deep learning-based approach for Parkinson’s disease detection 45 NR Noninvasive NR 13 Kamble et al. [191] (2021) India Measurement and Sensor P.R. Parkinson’s Parkinson’s disease classification using digital spiral drawings 25 NR Noninvasive NR C12 C13 C14 SN Author AI Type Cost Analysis Parameter Outcome of study AI Type ACC SEN SPE AUC MCC F1 Cost Analysis Parameter Input Modality Model Analysis Screening cost Maintain Cost Cost Savings (USD) Per. Sample 1 Smetherman et al. [182] (2021) NR NR NR NR NR NR NR NR Image Yes Yes NR 318 AI could assess individual situations, make appropriate decisions, and aid in the management of renal disease. 2 Challen et al. [183] (2019) NR NR NR NR NR NR NR NR NR NR NR NR NR ML DSS deployment will most likely concentrate on diagnostic decision support. ML Diagnostic decision assistance should be assessed with the same rigors as a novel laboratory screening test. 3 Almazán et al. [82] (2019) NR NR NR NR NR NR NR NR Point Data Yes Yes NR 61 AI for improved clinical benefit from nivolumab therapy. 4 Yuan et al. [184] (2020) NR NR NR NR NR NR NR NR Point Data Yes Yes NR 62 Artificial intelligence can consider individual situations, make appropriate decisions, and make significant advancements in the management of renal disease. 5 Solanki et al. [185] (2022) NR NR NR NR NR NR NR NR NR Yes Yes Yes Yes Guidelines, frameworks, and advancement of technologies for ethical AI that reflect human values, such as self-direction, in healthcare. 6 Biswas et al. [102] (2018) DL 86.78 0.76 NR 0.86 NR NR NR Image NR NR NR NR High-level features are extracted from the CCA US photos using CNN’s 13 layers. To produce clear and crisp segmented images, these features were upsampled using FCN upsampling layers, and the skipping operation was carried out. 7 Siy et al. [186] (2018) DL 91.5 NR NR NR NR NR NR Image NR NR NR NR A DNN-based psoriasis detection presented having 91.5% accuracy. 8 Aijaz et al. [71] (2022) DL 84.2 0.81 0.71 NR NR NR NR Image NR NR NR NR This study employed a CNN-based deep learning classification strategy to categorize the five types of psoriasis. 9 Ali et al. [188] (2022) NR NR NR NR NR NR NR NR NR NR NR NR NR Machine learning and artificial intelligence have ushered in a new era in medicine and nephrology. 10 Viswanathan et al. [189] (2020) NR NR NR NR NR NR NR NR Image NR NR NR 14 Diabetes exacerbated the deposition of atherosclerotic plaque. Risk assessment includes other factors in addition to the degree of vessel stenosis. 11 Sarki et al. [198] (2020) DL 84.88 0.87 NR NR NR NR NR Image NR NR NR NR The development of moderate and multi-class DL algorithms for the automatic detection of DED, according to the British Diabetic Association (BDA) criteria. 12 Quan et al. [199] (2021) DL 80.90 0.87 0.92 0.83 0.53 NR NR Speech NR NR NR NR The dynamic articulation transition features and the bidirectional LSTM model are combined ingeniously in the proposed method to record the time-series properties of continuous speech data. 13 Kamble et al. [191] (2021) ML 91.6 NR NR NR NR 0.8 NR Image NR NR NR NR Digitalized spiral drawing tests significantly affect how PD patients and healthy controls are classified. Open in a new tab
9. Conclusions Current research examines the impact of AI in health care moderately, and reveals qualitative flaws in methodology. This study provides a clear explanation of the diagnostic and therapeutic paradigm needed for future cost-effectiveness analyses. The presented study delineated the motivation for building AI-based products for successful regulatory market approval and the necessary element for AI-based products to undergo successful FDA 510 (K) approval. They should contain the original expenditure, ongoing costs, and a comparison to alternative technology. This way, a complete and segmented cost-benefit analysis may be offered, which will serve as a solid basis for making decisions about AI installations. From a strategic point of view, cost-effectiveness studies were assessed using a quality criteria catalog. Because decisions are not solely based on medical improvement rates, the business management decision making basis has been identified as critical for favorable implementation decisions and subsequent wide-scale applications. The integration of the business management perspective encompasses not only the conventional cost considerations, such as one-time and continuing costs, but also the options for delivering cutting-edge healthcare solutions in various ways.
Appendix A Table A1. Cost Effective analysis for the diagnosis. Categories Count Years 1 2 3 4 5 6 7 8 9 10 Patient Size per hospital per year 3650 7300 9125 10,950 12,775 14,600 16,425 18,250 20,075 21,900 23,725 No. of Hospital 20 20 22 24 26 28 30 32 34 36 38 Per day Patient Per hospital 20 20 25 30 35 40 45 50 55 60 65 Total patient 73,000 2,920,000 5,018,750 7,884,000 1,162,5250 1,635,2000 22,173,750 29,200,000 37,540,250 47,304,000 58,600,750 Conventional Method Physician charges per hour 500 500 550 605 665.5 732.05 805.255 885.7805 974.3586 1071.794 1178.974 Conventional method time (minutes) per day 60 1200 1500 1800 2100 2400 2700 3000 3300 3600 3900 Conventional method time (hours) per day 1 20 25 30 35 40 45 50 55 60 65 Physician charges per day in USD 10,000 13,750 18,150 23,292.5 29,282 36,236.48 44,289.03 53,589.72 64,307.66 76,633.3 Physician Charges per year per hospital 3,650,000 5,018,750 6,624,750 8,501,763 10,687,930 13,226,313 16,165,494 19,560,248 23,472,297 27,971,154 AI-based Method Physician charges per hour in USD 500 500 550 605 665.5 732.05 805.255 885.7805 974.3586 1071.794 1178.974 AI-based system time (minutes) per day 60 1000 1225 1440 1645 1840 2070 2300 2530 2760 2990 AI-based system time in (hours) per day 1 16.66667 20.41667 24 27.41667 30.66667 34.5 38.33333 42.16667 46 49.83333 Physician charges per day in USD 8333.333 11,229.17 14,520 18,245.79 22,449.53 27,781.3 33,954.92 41,085.45 49,302.54 58,752.2 Physician charges per year per hospital in USD 3,041,667 4,098,646 52,99,800 6,659,714 8,194,080 10,140,174 12,393,545 14,996,190 17,995,428 21,444,552 Difference (Conventional–AI) Saving in time (minutes) per day 200 275 360 455 560 630 700 770 840 910 Saving in time (hours) per day 3.333333 4.583333 6 7.583333 9.333333 10.5 11.66667 12.83333 14 15.16667 Saving in Physician charges per day in USD 1666.667 2520.833 3630 5046.708 6832.467 8455.178 10,334.11 12,504.27 15,005.12 17,881.1 Saving in Physician charges per year per hospital in USD 608,333.3 920,104.2 1,324,950 1,842,049 2,493,850 3,086,140 3,771,949 4,564,058 5,476,869 6,526,603 Open in a new tab Table A2. Cost Effective analysis for the treatment. Categories Count Year 1 2 3 4 5 6 7 8 9 10 Patient Size per hospital per year 3650 3650 5475 7300 9125 10,950 12,775 14,600 16,425 18,250 20,075 No. of Hospital 20 15 17 16 18 17 19 18 20 19 21 Per day Patient Per hospital 20 10 15 20 25 30 35 40 45 50 55 Total patient 73,000 547,500 1,396,125 2,336,000 4,106,250 5,584,500 8,495,375 10,512,000 14,782,500 17,337,500 23,186,625 Conventional Method Physician charges per hour 1000 1000 1100 1210 1331 1464.1 1610.51 1771.561 1948.7171 2143.58881 2357.947691 Conventional method time (minutes) per day 180 1800 2700 3600 4500 5400 6300 7200 8100 9000 9900 Conventional method time (hours) per day 3 30 45 60 75 90 105 120 135 150 165 Physician charges per day in USD 30,000 49,500 72,600 99,825 131,769 169,103.55 212,587.32 263,076.80 321,538.32 389,061.36 Physician Charges per year per hospital 10,950,000 18,067,500 26,499,000 36,436,125 48,095,685 61,722,795.75 77,594,371.8 96,023,035.1 117,361,487.3 142,007,399.7 AI-based Method Physician charges per hour in USD 1000 1000 1100 1210 1331 1464.1 1610.51 1771.56 1948.71 2143.58 2357.94 AI-based system time (minutes) per day 90 500 735 960 1175 1380 1610 1840 2070 2300 2530 AI-based system time in (hours) per day 1.3 8.33 12.25 16 19.58 23 26.83 30.66666667 34.5 38.33 42.16 Physician charges per day in USD 8333.33 13,475 19,360 26,065.41 33,674.3 43,215.35 54,327.87067 67,230.73 82,170.90438 99,426.79 Physician charges per year per hospital in USD 3,041,666.66 4,918,375 7,066,400 9,513,877.08 1,229,1119.5 1,577,3603.36 19,829,672.79 24,539,220.08 29,992,380.1 36,290,779.92 Difference (Conventional–AI) Saving in time (minutes) per day 1300 1965 2640 3325 4020 4690 5360 6030 6700 7370 Saving in time (hours) per day 21.66 32.75 44 55.41 67 78.16 89.33 100.5 111.66 122.83 Saving in Physician charges per day in USD 21,666.66 36,025 53,240 73,759.58 98,094.7 125,888.19 158,259.44 195,846.068 239,367.41 289,634.57 Saving in Physician charges per year per hospital in USD 7,908,333.33 131,49,125 19,432,600 26,922,247.92 35,804,565.5 45,949,192.39 57,764,699.01 71,483,815.02 87,369,107.25 105,716,619.8 Open in a new tab Table A3. AI content considered for cost analysis. SN Category Content X1 Data collection Patient size per hospital Enrollment cost per patient X2 Engineering R&D cost Data verification Data validation Scientific algorithms Graphical user interface (design) Cloud/storage Software technology updation Hardware technology updation Prototype testing Maintenance and support X3 Human resource cost ML scientist DL scientist Verification and validation scientist Clinical scientist Database engineer Graphical user interface engineer System administrator Cloud engineer Marketing professional Secretary X4 Commercialization cost FDA 5K approval Regulatory costs of various countries Release cost X5 Marketing cost Marketing Technical marketing Installation X6 Infrastructure cost Office space Furniture Hardware Software Electricity Open in a new tab
Author Contributions Conceptualization, J.S.S., M.M. (Mahesh Maindarkar), M.A.-M. and. S.P.; Methodology and software, J.S.S., M.M. (Mahesh Maindarkar), L.S., M.B. and M.T. Validation, A.M.J., A.A., M.T., V.V., P.A., I.M.S. and N.N.K., Investigation, K.V., J.R.L., I.M.S., M.T., M.M. (Martin Miner), G.T., D.W.S., K.L. and J.S.S.; Resources, S.P.; Data curation, M.M. (Mahesh Maindarkar), L.S., S.P., L.M., G.D.K. and J.S.S.; Writing—original draft preparation, S.P., M.M. (Mahesh Maindarkar), L.S., M.A.M., M.K.K., D.W.S., M.M.F., S.N. and J.S.S.; Writing—review and editing, S.P., M.M. (Mahesh Maindarkar), L.S., M.T., I.M.S., A.S., V.A. and J.S.S.; Visualization, J.F.E.F., K.V., R.K., J.S.T., A.S. (Aditya Sharma), G.T., Z.R., A.D.P. and J.S.S.; Supervision, A.S. (Aman Sharma), V.R., V.A., M.F., S.C. and J.S.S.; Project administration, S.P., N.N.K., J.S.T. and J.S.S. All authors have read and agreed to the published version of the manuscript.
Institutional Review Board Statement Not applicable.
Informed Consent Statement Suri and Maindarkar is with AtheroPoint™ LLC, Roseville, CA, USA, which does cardiovascular and stroke imaging.
Data Availability Statement No data availability.
Conflicts of Interest The authors declare no conflict of interest.
Funding Statement This research received no external funding.
Footnotes Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.
| 2022-12-09T00:00:00 |
2022/12/09
|
https://pmc.ncbi.nlm.nih.gov/articles/PMC9777836/
|
[
{
"date": "2023/01/01",
"position": 16,
"query": "AI healthcare"
},
{
"date": "2023/02/01",
"position": 17,
"query": "AI healthcare"
},
{
"date": "2023/07/01",
"position": 18,
"query": "AI healthcare"
},
{
"date": "2023/08/01",
"position": 19,
"query": "AI healthcare"
},
{
"date": "2023/12/01",
"position": 16,
"query": "AI healthcare"
},
{
"date": "2024/01/01",
"position": 19,
"query": "AI healthcare"
},
{
"date": "2024/03/01",
"position": 18,
"query": "AI healthcare"
},
{
"date": "2024/11/01",
"position": 18,
"query": "AI healthcare"
},
{
"date": "2025/02/01",
"position": 12,
"query": "AI healthcare"
},
{
"date": "2025/04/01",
"position": 12,
"query": "AI healthcare"
},
{
"date": "2025/06/01",
"position": 12,
"query": "AI healthcare"
}
] |
AI in Healthcare and Life Sciences - Intel
|
AI in Healthcare and Life Sciences – Intel
|
https://www.intel.com
|
[] |
AI in healthcare and life sciences can help improve patient outcomes and experiences, accelerate research and discovery, and increase operational efficiency.
|
What Is AI in Healthcare?
AI in healthcare uses machine learning, deep learning, and other technologies to process vast datasets, benefiting patients, providers, research, and operations within the healthcare industry.
From research to patient care, healthcare generates massive amounts of data. To some extent, delivering appropriate and efficient care depends on making sense of all that information. Artificial intelligence, which encompasses machine learning, deep learning, generative AI (GenAI), and other algorithmic methods, is designed to analyze vast amounts of disparate data to find and act on patterns at a speed and scale beyond human abilities.
When applied to healthcare, AI offers myriad data-driven benefits for patients, clinical and nursing staff, and administrators. Outcomes such as improved diagnostic speed and accuracy, remote patient monitoring, and virtual assistants augment patient support. Streamlined workflows, automated administrative tasks, and improved inventory tracking reduce costs and free staff for higher-value personal interactions. In the lab, AI is automating laboratory instruments to deliver precise, accurate test results at scale; accelerate diagnosis and drug discovery; and enable precision medicine.
AI-augmented security solutions and AI PCs help healthcare organizations remain compliant and protect their systems and data, and that of their patients, from cyber threats.
| 2023-01-01T00:00:00 |
https://www.intel.com/content/www/us/en/learn/ai-in-healthcare.html
|
[
{
"date": "2023/01/01",
"position": 24,
"query": "AI healthcare"
},
{
"date": "2023/02/01",
"position": 24,
"query": "AI healthcare"
},
{
"date": "2023/07/01",
"position": 25,
"query": "AI healthcare"
},
{
"date": "2023/08/01",
"position": 26,
"query": "AI healthcare"
},
{
"date": "2023/11/01",
"position": 23,
"query": "AI healthcare"
},
{
"date": "2023/12/01",
"position": 29,
"query": "AI healthcare"
},
{
"date": "2024/01/01",
"position": 24,
"query": "AI healthcare"
},
{
"date": "2024/03/01",
"position": 24,
"query": "AI healthcare"
},
{
"date": "2024/09/01",
"position": 22,
"query": "AI healthcare"
},
{
"date": "2024/11/01",
"position": 21,
"query": "AI healthcare"
},
{
"date": "2025/02/01",
"position": 26,
"query": "AI healthcare"
},
{
"date": "2025/04/01",
"position": 26,
"query": "AI healthcare"
},
{
"date": "2025/06/01",
"position": 26,
"query": "AI healthcare"
}
] |
|
AI In Healthcare Market Size, Share | Industry Report, 2030
|
AI In Healthcare Market Size, Share
|
https://www.grandviewresearch.com
|
[] |
The global AI in healthcare market size was estimated at USD 26.57 billion in 2024 and is projected to reach USD 187.69 billion by 2030, growing at a CAGR of ...
|
"The quality of research they have done for us has been excellent."
Brian Moore, VP, NICCA USA, Inc.
testimonials
| 2023-01-01T00:00:00 |
https://www.grandviewresearch.com/industry-analysis/artificial-intelligence-ai-healthcare-market
|
[
{
"date": "2023/01/01",
"position": 32,
"query": "AI healthcare"
},
{
"date": "2023/02/01",
"position": 34,
"query": "AI healthcare"
},
{
"date": "2023/07/01",
"position": 38,
"query": "AI healthcare"
},
{
"date": "2023/08/01",
"position": 37,
"query": "AI healthcare"
},
{
"date": "2023/09/01",
"position": 49,
"query": "artificial intelligence healthcare"
},
{
"date": "2023/11/01",
"position": 33,
"query": "AI healthcare"
},
{
"date": "2023/12/01",
"position": 46,
"query": "AI healthcare"
},
{
"date": "2024/01/01",
"position": 36,
"query": "AI healthcare"
},
{
"date": "2024/03/01",
"position": 30,
"query": "AI healthcare"
},
{
"date": "2024/05/01",
"position": 48,
"query": "artificial intelligence healthcare"
},
{
"date": "2024/06/01",
"position": 46,
"query": "artificial intelligence healthcare"
},
{
"date": "2024/09/01",
"position": 36,
"query": "AI healthcare"
},
{
"date": "2024/10/01",
"position": 48,
"query": "artificial intelligence healthcare"
},
{
"date": "2024/11/01",
"position": 32,
"query": "AI healthcare"
},
{
"date": "2025/01/01",
"position": 46,
"query": "artificial intelligence healthcare"
},
{
"date": "2025/02/01",
"position": 32,
"query": "AI healthcare"
},
{
"date": "2025/04/01",
"position": 34,
"query": "AI healthcare"
},
{
"date": "2025/06/01",
"position": 33,
"query": "AI healthcare"
}
] |
|
The Evolution of AI in Healthcare - Xsolis
|
The Evolution of AI in Healthcare
|
https://www.xsolis.com
|
[] |
AI in healthcare will help detect patterns and connect systems. This will allow for a network of seamless sharing of data, to anywhere, from anywhere. This ...
|
Artificial intelligence (AI) in healthcare is not a new concept. In the 1970s, AI applications were first used to help with biomedical problems. From there, AI-powered applications have expanded and adapted to transform the healthcare industry by reducing spend, improving patient outcomes, and increasing efficiencies overall.
How AI Works
Before we get into the evolution of AI in healthcare, it is beneficial to understand how artificial intelligence works.
Essentially, AI describes computer models and programs that imitate human-level intelligence to perform cognitive functions, like complex problem solving and experience gathering.
Most current AI tools are considered “Narrow AI,” which means the technology can outperform humans in a narrowly defined task. Many current approaches are powered by machine learning algorithms. Machine learning enables computers to learn, perform tasks and adapt without human intervention.
The Origins of AI in Healthcare
The phrase “artificial intelligence” was first coined in a Dartmouth College conference proposal in 1955. But the AI applications did not enter the healthcare field until the early 1970s when research produced MYCIN, an AI program that helped identify blood infections treatments. The proliferation of AI research continued, and in 1979 the American Association for Artificial Intelligence was formed (currently the Association for the Advancement of Artificial Intelligence, AAAI).
Throughout the 1980s and 1990s, the design of new AI systems helped achieve medical advancements such as:
Producing faster data collection and processing
Assisting in more precise surgical procedures
In – depth DBA research and mapping
More comprehensive implementation of electronic health records
Where AI is Today
AI technology and machine learning have evolved to influence how healthcare is delivered profoundly. This advanced technology has evolved beyond biological sciences, where it began and now applies to medical specialties, including:
Radiology
Screening
Psychiatry
Primary Care
Disease Diagnosis
Telemedicine
While AI in healthcare has become prevalent, its introduction to utilization review did not happen until recently.
AI for Utilization Review
Administrative burden, subjective data, and lack of payer-provider connectivity have always plagued utilization review, mostly due to a lack of technology that provided access and analysis. “Until a few years ago, a patient’s previous medical history wasn’t even considered in the utilization review process,” says Michelle Wyatt, Director of Clinical Best Practices at XSOLIS.
Because of that, Michelle says so much complex patient information was missed. Artificial intelligence, such as XSOLIS’ CORTEX platform, provides utilization review nurses the opportunity to understand patients better so their care can be managed appropriately to each specific case. Indeed, CORTEX was the first artificial intelligence-driven technology created specifically for the utilization review process.
How does it work? The CORTEX platform extracts data from the electronic medical record then applies natural language processing (which “reads” written documentation) and machine learning (which learns new patterns across millions of patients) so that UR teams can see a continuously updated and predictive view of each patient’s clinical picture. This allows for prioritization of patients, which results in improved efficiencies.
Through CORTEX, UR staff can share a comprehensive clinical picture of the patient with the payer, allowing both sides to see the exact same information at the same time. This shared data has helped to solve the contentious relationship that has plagued UR for so long.
Hospitals and health systems across the nation are taking advantage of the benefits AI provides specifically to utilization review. Implementing this type of change is transformative and whether a barrier is fear of change, financial worries, or concern about outcomes, XSOLIS helps clients overcome these concerns and realize significant benefits.
“Case managers often ask if AI will replace them in the future,” says Michelle. “I explain that artificial intelligence is a tool that allows us to understand the holistic nature of each patient better, but it doesn’t replace the expertise of a nurse or physician reviewer.”
Artificial intelligence like CORTEX allows UR nurses to automate all the manual data gathering that takes up so much time. That results in more time to manage patient care and put their clinical training to work.
Looking to the Future
According to the World Economic Forum (WEF), the future of AI in healthcare will dramatically change between now and 2030 in the following three ways:
1. Connected care
AI in healthcare will help detect patterns and connect systems. This will allow for a network of seamless sharing of data, to anywhere, from anywhere. This shared data and information will create life-saving connectivity across the globe.
2. Better AI-powered predictive care
Improved data will evaluate the probability and risk of an individual developing a disease in the future.
3. Improved patient and staff experiences
As AI evolves, it will continue to improve patient and provider experiences, including reducing wait times for patients and improved overall efficiency in hospitals and health systems.
With CORTEX, hospitals are harnessing AI to do work uniquely suited to automation – and making time for humans to do the work they are uniquely suited to: providing exceptional patient care.
If you want to transform the future of utilization review at your healthcare system or hospital, contact XSOLIS today to set up a demo of the CORTEX platform.
| 2021-02-02T00:00:00 |
2021/02/02
|
https://www.xsolis.com/blog/the-evolution-of-ai-in-healthcare/
|
[
{
"date": "2023/01/01",
"position": 33,
"query": "AI healthcare"
},
{
"date": "2023/02/01",
"position": 31,
"query": "AI healthcare"
},
{
"date": "2023/07/01",
"position": 32,
"query": "AI healthcare"
},
{
"date": "2023/08/01",
"position": 32,
"query": "AI healthcare"
},
{
"date": "2023/11/01",
"position": 21,
"query": "AI healthcare"
},
{
"date": "2023/12/01",
"position": 35,
"query": "AI healthcare"
},
{
"date": "2024/01/01",
"position": 25,
"query": "AI healthcare"
},
{
"date": "2024/03/01",
"position": 26,
"query": "AI healthcare"
},
{
"date": "2024/09/01",
"position": 21,
"query": "AI healthcare"
},
{
"date": "2024/11/01",
"position": 24,
"query": "AI healthcare"
},
{
"date": "2025/02/01",
"position": 34,
"query": "AI healthcare"
},
{
"date": "2025/04/01",
"position": 35,
"query": "AI healthcare"
},
{
"date": "2025/06/01",
"position": 34,
"query": "AI healthcare"
}
] |
Microsoft's "Path to Medical Superintelligence": A Glimpse into AI's ...
|
The heart of the internet
|
https://www.reddit.com
|
[] |
Could this truly be a "path to medical superintelligence" as Microsoft suggests, leading to vastly more accurate and accessible healthcare ...
|
Hey r/Singularity,
Just came across this fascinating article from Microsoft AI: "The Path to Medical Superintelligence". It details their work on the Microsoft AI Diagnostic Orchestrator (MAI-DxO) and the Sequential Diagnosis Benchmark (SDBench). Essentially, they're developing an AI system that aims to mimic the step-by-step diagnostic process of human clinicians, iteratively asking questions, ordering tests, and refining hypotheses.
Some key takeaways that jumped out at me:
Impressive Accuracy: The article claims MAI-DxO, when paired with OpenAI's o3 model, achieved up to 85.5% diagnostic accuracy on complex NEJM case proceedings, significantly outperforming a group of experienced physicians (who averaged around 20%).
Cost Efficiency: Beyond accuracy, the system reportedly achieved diagnoses at a reduced cost compared to human physicians.
Sequential Reasoning: Unlike many AI evaluations that rely on multiple-choice questions, SDBench focuses on sequential diagnosis, which is a much closer approximation of real-world clinical reasoning.
"Orchestration" of AI Agents: They highlight the concept of "orchestration" where multiple AI agents work together in a "chain-of-debate style" to arrive at a diagnosis. This multi-agent approach is presented as a crucial step towards true medical superintelligence.
This has some significant implications for the future of healthcare and, more broadly, for the singularity:
Could this truly be a "path to medical superintelligence" as Microsoft suggests, leading to vastly more accurate and accessible healthcare worldwide?
How might this impact the role of human clinicians, shifting them from diagnosticians to more specialized roles or even "AI orchestrators" themselves?
Are there biases inherent in the training data that could lead to disparities in care, even with high accuracy rates on benchmarks? (Some external analyses have raised this point).
What are the next steps for validating and deploying such a system in real-world, messy clinical environments, beyond controlled case studies?
I'm curious to hear your thoughts, r/Singularity. Is this a significant step towards a medical singularity, or are there still major hurdles to overcome before we see such widespread impact?
Let's discuss!
| 2023-01-01T00:00:00 |
https://www.reddit.com/r/singularity/comments/1lu07gk/microsofts_path_to_medical_superintelligence_a/
|
[
{
"date": "2023/01/01",
"position": 36,
"query": "AI healthcare"
},
{
"date": "2023/02/01",
"position": 41,
"query": "AI healthcare"
},
{
"date": "2023/12/01",
"position": 66,
"query": "AI healthcare"
},
{
"date": "2025/02/01",
"position": 61,
"query": "AI healthcare"
},
{
"date": "2025/04/01",
"position": 54,
"query": "AI healthcare"
},
{
"date": "2025/06/01",
"position": 55,
"query": "AI healthcare"
}
] |
|
Health research & technology advancements - Google for Health
|
Healthcare Research & Technology Advancements
|
https://health.google
|
[] |
Helping everyone build AI for healthcare applications with open foundation models · Predicting fetal well-being from cardiotocography signals using AI. How AI ...
|
We are researching and testing AI models with the goal of helping alleviate the global shortages of physicians, as well as the low access to modern imaging and diagnostic tools in many parts of the world. With improved tech, we hope to increase accessibility and help more patients receive timely and accurate diagnoses and care.
| 2023-01-01T00:00:00 |
https://health.google/health-research/
|
[
{
"date": "2023/01/01",
"position": 37,
"query": "AI healthcare"
},
{
"date": "2023/02/01",
"position": 38,
"query": "AI healthcare"
},
{
"date": "2023/07/01",
"position": 51,
"query": "AI healthcare"
},
{
"date": "2023/08/01",
"position": 51,
"query": "AI healthcare"
},
{
"date": "2023/11/01",
"position": 50,
"query": "AI healthcare"
},
{
"date": "2023/12/01",
"position": 76,
"query": "AI healthcare"
},
{
"date": "2024/01/01",
"position": 52,
"query": "AI healthcare"
},
{
"date": "2024/03/01",
"position": 51,
"query": "AI healthcare"
},
{
"date": "2024/09/01",
"position": 55,
"query": "AI healthcare"
},
{
"date": "2024/11/01",
"position": 50,
"query": "AI healthcare"
},
{
"date": "2025/02/01",
"position": 41,
"query": "AI healthcare"
},
{
"date": "2025/04/01",
"position": 39,
"query": "AI healthcare"
},
{
"date": "2025/06/01",
"position": 39,
"query": "AI healthcare"
}
] |
|
AI Solutions for Healthcare - ITRex Group
|
AI Solutions for Healthcare — ITRex
|
https://itrexgroup.com
|
[] |
AI solutions for healthcare that transform care delivery and medical research, ethically, securely, and with patient safety as an imperative.
|
Hospitals & Clinics
Medtech & Wellness Startups
Pharmaceuticals & R&D Companies
Life Science & Biotech Companies
We help you to eliminate inefficiencies and automate workflows, foster in-patient care, and pave your way to other value-driving applications of AI in medical diagnosis and treatment
We can enrich your apps, medical devices, and remote patient monitoring systems with AI capabilities to help you win the market with next-gen solutions
We help you to facilitate medical research, advance clinical trials, and enjoy other benefits of artificial intelligence in medicine and vaccine development
We help you leverage the power of data to boost biology R&D, drive digitization and effectiveness in the lab, and design and develop commercially successful products
| 2023-01-01T00:00:00 |
https://itrexgroup.com/services/ai-for-healthcare/
|
[
{
"date": "2023/01/01",
"position": 39,
"query": "AI healthcare"
},
{
"date": "2023/02/01",
"position": 33,
"query": "AI healthcare"
},
{
"date": "2023/07/01",
"position": 37,
"query": "AI healthcare"
},
{
"date": "2023/08/01",
"position": 38,
"query": "AI healthcare"
},
{
"date": "2023/11/01",
"position": 36,
"query": "AI healthcare"
},
{
"date": "2023/12/01",
"position": 37,
"query": "AI healthcare"
},
{
"date": "2024/01/01",
"position": 35,
"query": "AI healthcare"
},
{
"date": "2024/03/01",
"position": 33,
"query": "AI healthcare"
},
{
"date": "2024/09/01",
"position": 37,
"query": "AI healthcare"
},
{
"date": "2024/11/01",
"position": 34,
"query": "AI healthcare"
},
{
"date": "2025/02/01",
"position": 30,
"query": "AI healthcare"
},
{
"date": "2025/04/01",
"position": 30,
"query": "AI healthcare"
},
{
"date": "2025/06/01",
"position": 29,
"query": "AI healthcare"
}
] |
|
What Is Google for Health? - Google for Health
|
What Is Google for Health?
|
https://health.google
|
[] |
Google for Health wants to help everyone live more life every day. Learn more about what Google for Health is and how we're aiding in healthcare ...
|
HCA Healthcare is redesigning patient care with generative AI and Google Cloud
Discover how HCA Healthcare is innovating with generative AI to help improve workflows and allow physicians and nurses to spend more time with patients. Dr. Michael Schlosser, SVP of Care Transformation and Innovation at HCA Healthcare, shares how their partnership with Google Cloud helps HCA harness big data and AI to strip away administrative burden and return healthcare providers to the bedside.
| 2023-01-01T00:00:00 |
https://health.google/
|
[
{
"date": "2023/01/01",
"position": 54,
"query": "AI healthcare"
},
{
"date": "2023/02/01",
"position": 55,
"query": "AI healthcare"
},
{
"date": "2023/07/01",
"position": 27,
"query": "AI healthcare"
},
{
"date": "2023/08/01",
"position": 28,
"query": "AI healthcare"
},
{
"date": "2023/11/01",
"position": 26,
"query": "AI healthcare"
},
{
"date": "2023/12/01",
"position": 22,
"query": "AI healthcare"
},
{
"date": "2024/01/01",
"position": 27,
"query": "AI healthcare"
},
{
"date": "2024/03/01",
"position": 27,
"query": "AI healthcare"
},
{
"date": "2024/09/01",
"position": 25,
"query": "AI healthcare"
},
{
"date": "2024/11/01",
"position": 27,
"query": "AI healthcare"
},
{
"date": "2025/02/01",
"position": 68,
"query": "AI healthcare"
},
{
"date": "2025/02/01",
"position": 71,
"query": "artificial intelligence healthcare"
},
{
"date": "2025/03/01",
"position": 70,
"query": "artificial intelligence healthcare"
},
{
"date": "2025/04/01",
"position": 69,
"query": "AI healthcare"
},
{
"date": "2025/04/01",
"position": 70,
"query": "artificial intelligence healthcare"
},
{
"date": "2025/06/01",
"position": 68,
"query": "AI healthcare"
}
] |
|
Is your health care system AI-ready? - American Medical Association
|
Is your health care system AI-ready?
|
https://www.ama-assn.org
|
[] |
Get the info you need on augmented intelligence (AI) governance for your health care system. Establish a governance framework to implement, ...
|
The AMA Update covers a range of health care topics affecting the lives of physicians and patients. Learn more about the top challenges that pediatricians are facing today. Learn more about University of Mississippi Medical Center's orientation program for new residents.
| 2023-01-01T00:00:00 |
https://www.ama-assn.org/practice-management/digital-health/your-health-care-system-ai-ready
|
[
{
"date": "2023/01/01",
"position": 59,
"query": "AI healthcare"
},
{
"date": "2023/02/01",
"position": 59,
"query": "AI healthcare"
},
{
"date": "2023/07/01",
"position": 66,
"query": "AI healthcare"
},
{
"date": "2023/08/01",
"position": 64,
"query": "AI healthcare"
},
{
"date": "2023/11/01",
"position": 68,
"query": "AI healthcare"
},
{
"date": "2023/12/01",
"position": 45,
"query": "AI healthcare"
},
{
"date": "2024/01/01",
"position": 71,
"query": "AI healthcare"
},
{
"date": "2024/03/01",
"position": 67,
"query": "AI healthcare"
},
{
"date": "2024/09/01",
"position": 68,
"query": "AI healthcare"
},
{
"date": "2024/11/01",
"position": 67,
"query": "AI healthcare"
}
] |
|
Artificial Intelligence (AI) in Healthcare Market Size & Growth [2033]
|
Artificial Intelligence (AI) in Healthcare Market Size & Growth [2033]
|
https://www.businessresearchinsights.com
|
[] |
Hospitals: AI is used by hospitals for operational management, diagnostics, and patient monitoring. AI improves clinical decision-making and ...
|
Our Research is the Cornerstone of 1000 Firms to Stay in the Lead
Artificial Intelligence (AI) in Healthcare Market OVERVIEW
The global Artificial Intelligence (AI) in Healthcare Market was valued at USD 4.85 billion in 2024 and is expected to rise to USD 6.24 billion in 2025, eventually reaching USD 46.37 billion by 2033, expanding at a CAGR of 28.5% from 2025 to 2033.
The AI in Healthcare Market refers to the incorporation of artificial intelligence technologies into medical procedures for the purposes of strengthening diagnostics, treatment planning, and patient care. The market is growing rapidly because of advancements in machine learning, natural language processing, and data analytics. The applications of AI vary from predictive analytics to robotic surgeries to strengthen healthcare outcomes and operational efficiency. Rising demand for customized medicine and the necessity to lower the costs of healthcare are major driving factors. The market is thus witnessing huge investments and partnerships between tech firms, healthcare establishments, and research centers.
COVID-19 IMPACT
Artificial Intelligence (AI) in Healthcare Market Industry Had a positive impact due to during COVID-19 Pandemic
The global COVID-19 pandemic has been unprecedented and staggering, with the market experiencing Higher-than-anticipated demand across all regions compared to pre-pandemic levels. The sudden market decline reflected by the rise in CAGR is attributable to the market’s decline and demand returning to pre-pandemic levels.
The use of AI in healthcare was spurred by the COVID-19 pandemic. AI technologies were used to manage resources, forecast outbreaks, and enable remote patient monitoring. AI was used by healthcare providers to optimize treatment protocols and triage patients. The crisis brought to light AI's potential to improve emergency healthcare delivery. As a result, during the pandemic, the market saw faster growth and innovation.
LATEST TREND
Clinical Environments with Ambient AI
Ambient AI is becoming more popular. It involves passively gathering and analyzing data while interacting with patients. Real-time transcription of doctor-patient conversations is made possible by technologies such as AI scribes, which lessen administrative workloads. This trend improves both patient engagement and clinician efficiency. Businesses like Abridge and Microsoft are spearheading advancements in this field. Workflow management and clinical documentation could be completely transformed by the incorporation of ambient AI.
Artificial Intelligence (AI) in Healthcare Market SEGMENTATION
BY TYPE
Based on Type, the global market can be categorized into
Deep Learning: Deep learning models analyze large data sets to detect patterns, which is helpful for diagnostics and predictive analysis. They play a crucial role in analyzing medical images and genomic information. It improves the precision of disease detection and treatment planning.
Natural Language Processing (NLP): NLP allows meaningful clinical information to be extracted from unstructured clinical information. It supports effective documentation and enhances communication between patients and providers. Applications of NLP are critical in handling electronic health records and clinical decision support systems.
Context-Aware Processing: Context-aware processing takes into account contextual data like patient history and environmental conditions to deliver individualized health care solutions. Context-aware processing improves the effectiveness and pertinence of AI-based recommendations. Context-aware systems facilitate more precise diagnoses and personalized treatment plans.
Other: Other types of markets are robotic process automation and machine learning, which automate administrative processes and facilitate clinical operations. These help enhance efficiency and minimize human error in the healthcare environment. Their adoption is growing in different areas of healthcare.
BY APPLICATION
Based on application, the global market can be categorized
Hospitals: AI is used by hospitals for operational management, diagnostics, and patient monitoring. AI improves clinical decision-making and helps allocate resources. Both patient outcomes and hospital efficiency are enhanced by these applications.
Clinics: AI is used in clinics for patient engagement, scheduling, and diagnostics. AI technologies help physicians deliver individualized treatment. This results in more satisfied patients and more efficient clinic operations.
Research Organizations: Research organizations use AI to analyze data, conduct clinical trials, and find new drugs. AI speeds up research procedures and improves the precision of results. These developments support the growth of medical knowledge and innovation.
Other: Wearable medical technology, telemedicine platforms, and home healthcare services are examples of additional applications. In these situations, AI makes individualized care and remote monitoring possible. This promotes preventive medicine and increases access to healthcare.
MARKET DYNAMICS
Market dynamics include driving and restraining factors, opportunities and challenges stating the market conditions.
DRIVING FACTOR
Advances in Technology
Ongoing advancements in AI algorithms and computing capacity are driving the healthcare market. These advances allow for more precise diagnoses and effective treatment strategies. The use of AI with new technologies such as IoT and blockchain further improves healthcare services. Consequently, the implementation of AI in healthcare is gaining momentum worldwide.
Growing Healthcare Data
The exponential increase in information in healthcare requires sophisticated analytics for effective information. AI applications are capable of analyzing huge volumes of data to find patterns, associations, and trends. It facilitates evidence-based decision-making and tailor-made medicine. The need for AI-based solutions in healthcare information management is thus growing.
RESTRAINING FACTOR
Shortage of Qualified Workforce
AI adoption in healthcare is inhibited by the shortage of healthcare professionals equipped with knowledge in healthcare and AI technologies. The deficiency restricts the creation and implementation of AI solutions. Bridging this gap calls for specific education and training programs. A boost in the workforce ability is indispensable to the healthy growth of AI in healthcare
Growth in Emerging Markets Opportunity Emerging economies offer considerable prospects for AI growth in the healthcare sector. They are investing in healthcare facilities and digital technologies. AI has the capability to solve issues like poor access to healthcare and shortage of resources. Customized AI solutions have the potential to enhance healthcare delivery and outcome in these markets. Successful partnerships between governments, technology firms, and healthcare providers are important. Data Security and Privacy Issues Challenge AI in healthcare raises privacy and security concerns because it handles sensitive patient data. It is crucial to make sure that laws like GDPR and HIPAA are followed. To keep patients' trust, strong data protection measures must be put in place. For AI to be widely used in healthcare, these issues must be resolved.
Artificial Intelligence (AI) in Healthcare Market REGIONAL INSIGHTS
● NORTH AMERICA
Because of its sophisticated infrastructure, substantial investments, and encouraging policies, North America leads the AI in Healthcare Market. Through programs like the "United States Artificial Intelligence (AI) in Healthcare Market" strategy, the US in particular makes a significant contribution. This entails supporting innovation, cultivating public-private partnerships, and providing funding for research. The United States is positioned as a global leader in AI-driven healthcare solutions thanks to these initiatives.
● EUROPE
Due to its sizable population and rising healthcare needs, Asia is becoming a major player in the AI in Healthcare Market. China, India, and Japan are among the nations investing in AI infrastructure and research. Collaborations between the public and private sectors are encouraging innovation. Asia is now positioned as a major contributor to the global AI healthcare landscape as a result of these developments.
● ASIA
Due to its sizable population and rising healthcare needs, Asia is becoming a major player in the AI in Healthcare Market. China, India, and Japan are among the nations investing in AI infrastructure and research. Collaborations between the public and private sectors are encouraging innovation. Asia is now positioned as a major contributor to the global AI healthcare landscape as a result of these developments.
KEY INDUSTRY PLAYERS
The AI healthcare market experiences substantial changes because of the significant contributions from leading industry participants who drive innovation and investment through strategic partnerships. The AI healthcare market benefits from Intel Corporation together with Nvidia Corporation and Google alongside IBM Corporation and Microsoft Corporation which develop custom artificial intelligence solutions for healthcare operations. Through their work they provide strong processing units which support AI calculations while also creating diagnostic algorithms and delivering data management through their cloud platforms. The organizations collaborate with healthcare providers and research institutions to conduct AI technology trials which lead to implementation in healthcare systems. These companies lead the adoption of AI in healthcare through their resources and market influence which establishes standards and determines future market development.
LIST OF TOPS Artificial Intelligence (AI) in Healthcare Market COMPANIES
Intel Corporation: U.S.
Nvidia Corporation: U.S.
Google: U.S.
IBM Corporation: U.S.
Microsoft Corporation: U.S.
KEY INDUSTRY DEVELOPMENT
Eko Health Inc.: Eko Health Inc. obtained Food and Drug Administration approval for its low ejection fraction AI algorithm in April 2024 following its development with the Mayo Clinic to detect heart failure through routine medical checkups.
Tempus AI: The month of June 2024 marked the public listing of Tempus AI on Nasdaq through which the company promotes its precision medicine solutions for oncology and cardiology and several other medical fields.
REPORT COVERAGE
The study encompasses a comprehensive SWOT analysis and provides insights into future developments within the market. It examines various factors that contribute to the growth of the market, exploring a wide range of market categories and potential applications that may impact its trajectory in the coming years. The analysis takes into account both current trends and historical turning points, providing a holistic understanding of the market's components and identifying potential areas for growth.
This research report examines the segmentation of the market by using both quantitative and qualitative methods to provide a thorough analysis that also evaluates the influence of strategic and financial perspectives on the market. Additionally, the report's regional assessments consider the dominant supply and demand forces that impact market growth. The competitive landscape is detailed meticulously, including shares of significant market competitors. The report incorporates unconventional research techniques, methodologies and key strategies tailored for the anticipated frame of time. Overall, it offers valuable and comprehensive insights into the market dynamics professionally and understandably.
| 2023-01-01T00:00:00 |
https://www.businessresearchinsights.com/market-reports/artificial-intelligence-ai-in-healthcare-market-124954
|
[
{
"date": "2023/01/01",
"position": 61,
"query": "AI healthcare"
},
{
"date": "2023/01/01",
"position": 65,
"query": "artificial intelligence healthcare"
},
{
"date": "2023/04/01",
"position": 64,
"query": "artificial intelligence healthcare"
},
{
"date": "2023/07/01",
"position": 65,
"query": "AI healthcare"
},
{
"date": "2023/08/01",
"position": 66,
"query": "AI healthcare"
},
{
"date": "2023/09/01",
"position": 69,
"query": "artificial intelligence healthcare"
},
{
"date": "2023/11/01",
"position": 66,
"query": "AI healthcare"
},
{
"date": "2023/11/01",
"position": 64,
"query": "artificial intelligence healthcare"
},
{
"date": "2023/12/01",
"position": 77,
"query": "AI healthcare"
},
{
"date": "2024/01/01",
"position": 69,
"query": "AI healthcare"
},
{
"date": "2024/03/01",
"position": 66,
"query": "AI healthcare"
},
{
"date": "2024/09/01",
"position": 66,
"query": "AI healthcare"
},
{
"date": "2024/11/01",
"position": 66,
"query": "AI healthcare"
}
] |
|
Towards fair decentralized benchmarking of healthcare AI ... - Nature
|
Towards fair decentralized benchmarking of healthcare AI algorithms with the Federated Tumor Segmentation (FeTS) challenge
|
https://www.nature.com
|
[
"Zenk",
"German Cancer Research Center",
"Dkfz",
"Heidelberg",
"Division Of Medical Image Computing",
"Medical Faculty Heidelberg",
"Heidelberg University",
"Baid",
"Center For Federated Learning In Medicine",
"Indiana University"
] |
... FL algorithms and evaluation of Healthcare AI algorithm generalizability in real-world cancer imaging datasets.
|
This research complies with all relevant ethical regulations. Informed consent in signed form was obtained from all subjects at the respective institutions that contributed training and validation data, and the protocol for releasing the data was approved by the institutional review board of the data-contributing institution. The provided training and validation data describe mpMRI scans, acquired from: University of Pennsylvania (PA, USA), University of Alabama at Birmingham (AL, USA), Heidelberg University (Germany), University of Bern (Switzerland), University of Debrecen (Hungary), Henry Ford Hospital (MI, USA), University of California (CA, USA), MD Anderson Cancer Center (TX, USA), Emory University (GA, USA), Mayo Clinic (MN, USA), Thomas Jefferson University (PA, USA), Duke University School of Medicine (NC, USA), Saint Joseph Hospital and Medical Center (AZ, USA), Case Western Reserve University (OH, USA), University of North Carolina (NC, USA), Fondazione IRCCS Instituto Neuroligico C. Besta, (Italy), Ivy Glioblastoma Atlas Project, MD Anderson Cancer Center (TX, USA), Washington University in St. Louis (MO, USA), Tata Memorial Center (India), University of Pittsburg Medical Center (PA, USA), University of California San Francisco (CA, USA), Unity Health, University Hospital of Zurich.
This section describes the FeTS Challenge 2022. A description of how the FeTS Challenge 2021 differed from it is provided in the Supplementary Note 5.
Challenge datasets
Data sources
We leverage data from the BraTS challenge4,5,52,53,54, and from 32 collaborators of the largest to-date real-world federation28. The following sections apply to both of them unless otherwise noted. Both sources contain mpMRI scans routinely acquired during standard clinical practice along with their reference annotations for the evaluated tumor sub-regions. These are augmented with meta-data of the scans’ partitioning in an anonymized manner. Each case describes four structural mpMRI scans for a single patient at the pre-operative baseline time point. The exact mpMRI sequences included for each case are (i) native T1-weighted (T1), (ii) contrast-enhanced T1 (T1-Gd), (iii) T2-weighted (T2), and (iv) T2 Fluid Attenuated Inversion Recovery (T2-FLAIR).
Data preprocessing
The preprocessing pipeline from the BraTS challenge is applied in the FeTS challenge, too. Specifically, all input scans (i.e., T1, T1-Gd, T2, T2-FLAIR) are rigidly registered to the same anatomical atlas (i.e., SRI-2455) using the Greedy diffeomorphic registration algorithm56, ensuring a common spatial resolution of 1 mm3. After registration, brain extraction is done to remove any apparent non-brain tissue, using a deep learning approach specifically designed for brain MRI scans with apparent diffuse glioma57. All preprocessing routines have been made publicly available through the Cancer Imaging Phenomics Toolkit (CaPTk)58,59,60 and the FeTS tool61.
Annotation protocol
The skull-stripped scans are used for annotating the brain tumor sub-regions. The annotation process follows a pre-defined clinically approved annotation protocol3,4, which was provided to all clinical annotators, describing in detail the radiologic appearance of each tumor sub-region according to the specific provided MRI sequences. The annotators were given the flexibility to use their tool of preference for making the annotations, and also follow either a complete manual annotation approach or a hybrid approach where an automated approach is used to produce some initial annotations followed by their manual refinements. The summarized definitions of the tumor sub-regions communicated to annotators are:
1. The enhancing tumor (ET) delineates the hyperintense signal of the T1-Gd sequence compared to T1, after excluding the vessels. 2. The tumor core (TC) represents what is typically resected during a surgical operation and includes ET as well as the necrotic tumor core (NCR). It outlines regions appearing dark in both T1 and T1-Gd images (denoting necrosis/cysts) and dark regions in T1-Gd and bright in T1. 3. The farthest tumor extent, also called whole tumor (WT), consists of the TC as well as the peritumoral edematous and infiltrated tissue (ED). WT delineates the regions characterized by the hyperintense abnormal signal envelope on the T2-FLAIR sequence.
The provided segmentation labels have values of 1 for NCR, 2 for ED, 4 for ET, and 0 for everything else.
For the BraTS data, each case was assigned to a pair of annotator-approver. Annotators spanned across various experience levels and clinical/academic ranks, while the approvers were the 2 experienced board-certified neuroradiologists (with more than 13 years of experience with glioma). Annotations produced by the annotators were passed to the corresponding approver, who was then responsible for signing off these annotations. Specifically, the approver would review the tumor annotations in tandem with the corresponding mpMRI scans, and send them back to the annotators for further refinements if necessary. This iterative approach was followed for all cases until their annotations reached satisfactory quality (according to the approver) for being publicly available and noted as final reference segmentation labels for these scans.
Collaborators from the FeTS federation were asked to use a semi-automatic annotation approach, leveraging the predictions of an ensemble of state-of-the-art BraTS models. Specifically, collaborators were supplied with the FeTS tool61, containing pre-trained models of the DeepMedic62, nnU-Net63, and DeepScan64 approaches trained on the BraTS data, with label fusion performed using the Simultaneous Truth and Performance Level Estimation (STAPLE) algorithm65,66. Refinements of the fused labels were then performed by neuroradiology experts at each site according to the BraTS annotation protocol4. Sanity checks to ensure the integrity and quality of the annotations were performed in a preceding FL study28.
Training, validation, and test case characteristics
Training and Validation sets for the FeTS challenge were gathered from the BraTS dataset, sampling a specific subset of radiographically appearing glioblastoma while excluding cases without an apparent enhancement. The exact numbers can be found in Table 3. Training cases encompass the mpMRI volumes, the corresponding tumor sub-region annotations, as well as a pseudo-identifier of the site where the scans were acquired. In contrast, validation cases only contain the unannotated mpMRI volumes. We provided two schemas to the participants for partitioning the provided data and used a third partitioning internally for re-training submissions before the test set evaluation (details in Supplementary Fig. 1):
1. Geographical partitioning by institution (partitioning 1, 23 sites) 2. Artificial partitioning using imaging information (partitioning 2, 33 sites), by further sub-dividing each of the 5 largest institutions in partition 1 into three equally large parts after sorting samples by their whole tumor size. 3. Refined geographical partitioning (partitioning 3, 29 sites), which was generated as a refinement of the geographical partitioning (partitioning 1), by subdividing the largest institution into seven parts. This institution comprises a system of hospitals in close geographical proximity, which were combined for partitioning 1. For partitioning 3, they were re-grouped into seven pseudo-institutions.
Testing datasets were also gathered from BraTS and the FeTS federation collaborators but were not shared with the challenge participants. Access to the centralized test datasets was exclusive to Task 1 organizers, while the datasets for Task 2 remained decentralized throughout the competition, inaccessible for the Task 2 organizer. This collaborative, multi-site evaluation approach scaled up the size and diversity of the test dataset compared to the BraTS 2021 challenge significantly (Supplementary Fig. 11).
Table 3 Overview of the number of cases and institutions in the training, validation, and test sets Full size table
Performance evaluation
Predictions of the submitted segmentation algorithms were required to follow the format of the provided reference segmentations. Segmentation quality is assessed on the ET, TC, and WT sub-regions, corresponding to the union of labels {4}, {1, 4}, and {1, 2, 4}, respectively. For each region, the predicted segmentation is compared with the reference segmentation using the following metrics:
Dice similarity coefficient (DSC), which measures the extent of spatial overlap between the predicted masks (\(\hat{Y}\)) and the provided reference ( Y ), defined by $${{\rm{DSC}}}=\frac{2| Y\cap \hat{Y}| }{| Y|+| \hat{Y}| }.$$ (1) DSC scores range from 0 (worst) to 1 (best). The DSCs of the three individual tumor regions can be averaged to obtain a mean DSC.
Hausdorff distance (HD), which quantifies the distance between the boundaries of the reference labels against the predicted label. This makes the HD sensitive to local differences, as opposed to the DSC, which represents a global measure of overlap. For brain tumor segmentation, local differences may be crucial for properly assessing segmentation quality. In this challenge, the 95 th percentile of the HD between the contours of the two segmentation masks is calculated, which is more robust to outlier pixels: $${{{\rm{HD}}}}_{95}(\hat{Y},Y)=\max \left\{\begin{array}{cc}{P}_{95\%}\,d(\hat{y},Y),&{P}_{95\%}\,d(y,\hat{Y})\\ \hat{y}\in \hat{Y}&y\in Y\end{array}\right\},$$ (2) where \(d(a,B)={\min }_{b\in B}| | a-b| | \) is the distance of a to set B . Lower distances correspond to more accurate boundary delineations.
Convergence Score is an additional metric used for Task 1 only. It measures how quickly algorithms are able to reach a desired segmentation performance. Methods with fast convergence allow to stop training earlier, thus saving communication and computation resources and enhancing the efficiency of federated training. To calculate the convergence score, in each round of an FL experiment, the mean DSC on a fixed validation split (20%) of the official training data and the simulated round time T are computed. Details on how T is simulated are in the FL framework methods. Over the course of an experiment, this results in a DSC-over-time curve. The validation DSC can in some cases decrease at later times (e.g., due to overfitting or randomness in the optimization), but as the model with the best DSC is used as the final model, such a decrease should not be penalized. Therefore, a projected DSC curve is computed as \({{{\rm{DSC}}}}_{{{\rm{proj}}}}(t)=\mathop{\max }_{{t}^{{\prime} }\le t}{{\rm{DSC}}}({{{\rm{t}}}}^{{\prime} })\). The final convergence score metric is calculated as the area under that projected DSC-over-time curve. Higher values of this metric indicate enhanced convergence and, thus, the best FL approach. To standardize the time-axis for the convergence score among the Task 1 participants, all FL experiments performed during the challenge were limited to one week of simulated total time, which was a realistically feasible duration based on the experience from the FeTS initiative28. The FL runs were terminated once the simulated time exceeded one week and the model with the highest validation score before the last round was used as the final model, to make sure that a long last round exceeding the time limit does not benefit the participant.
Task 1: federated training (FL weight aggregation methods)
Model architecture
To focus on the development of aggregation methods, we needed a pre-established segmentation model architecture. Based on current literature indications, we picked U-Net67 with residual connections, which has shown robust performance across multiple medical imaging datasets57,63,68,69,70,71. The U-Net architecture consists of an encoder, comprising convolutional layers and downsampling layers (applying max-pooling operation), and a decoder of upsampling layers (applying transpose convolution layers). The encoder-decoder structure contributes in capturing information at multiple scales/resolutions. The U-Net also includes skip connections, which consist of concatenated feature maps paired across the encoder and the decoder layers, to improve context and feature re-usability, boosting overall performance.
Federated learning framework
We employ the typical aggregation server FL workflow14, in which a central server (aggregator) exchanges model weights with participating sites (collaborators), which are simulated for the FeTS challenge Task 1 on a single machine using the real-world multicentric data described in the challenge datasets methods. This process is repeated in multiple FL-based training rounds. At the start of a single round, each collaborator locally validates the model received from the aggregator. Each collaborator then trains this model on their local data to update the model gradients. The local validation results along with the model updates of each site are then sent to the aggregator, which combines all model updates to produce a new consensus model. This model is then passed back to each collaborator and a new federated round begins. Following extensive prior literature33,63,71,72, the final model for each local institutional training is chosen based on the best local validation score at pre-determined training intervals, i.e., rounds.
To guarantee fair competition, all challenge participants were required to use an implementation of this FL framework based on PyTorch and openFL73,74 provided by the organizers. Modifications were allowed in the following components:
Aggregation method: Participants could customize how weights from the current training round are combined into a consensus model.
Collaborator selection: Instead of involving all collaborators in each round, participants can selectively sample collaborators, for example based on validation metrics or round completion time.
Hyperparameters for local training: In each FL round, participants could adjust the values of two essential FL parameters, the learning rate of the stochastic gradient descent (SGD) optimizer, and the number of epochs per round.
Efficiency is an important practical aspect of FL with its inherent communication and computation constraints. As described in the evaluation section, we take this into account in the FL benchmarking framework by limiting wall clock runtime and by evaluating the convergence score metric, both of which require the realistic simulation of FL round durations. To make this simulation as realistic as possible, we used a subset of the real-world times measured in the FeTS initiative28. Note that the simulated time is different from the program runtime; it is rather an estimate of the wall time such an FL experiment would take in a real federation similar to the FeTS initiative. Specifically, we subdivide simulated time into: training time T train , validation time T val , model weight download T down and upload time T up . In each round, the simulated time for each collaborator k is
$${T}_{k}={T}_{{{\rm{down}}},k}+{T}_{{{\rm{up}}},k}+{T}_{{{\rm{val}}},k}\cdot {N}_{{{\rm{val}}},k}+{T}_{{{\rm{train}}},k}\cdot {N}_{{{\rm{train}}},k}$$ (3)
and the total time for each round is \(\mathop{\max }_{k}\{{T}_{k}\}\). To simulate a realistic FL setup, T x,k was sampled from a normal distribution: \({T}_{{{\rm{x}}},k} \sim {{\mathcal{N}}}({\mu }_{{{\rm{x}}},k},{\sigma }_{{{\rm{x}}},k})\), where x can be replaced with train/val/down/up. The parameters of the normal distribution are fixed but different for each client k, and based on time measurements in a previous real-world FL study, which used the same model28. Random seeds guarantee that these are identical for all FL experiments, so that all participants use the same timings.
Ranking
Before evaluating the submissions on the Task 1 test set, all algorithms were re-trained by the organizers, to ensure reproducible results and to prevent data leakage between federated sites. As the participants should develop generalizable FL algorithms that do not overfit on a particular collaborator, the unseen, refined geographical partitioning (partitioning 3) was used. Then, based on the measured metric values, a ranking methodology akin to the BraTS challenges was employed. All teams are ranked for each of the N test cases, 3 tumor regions, and 2 segmentation metrics separately, yielding N ⋅ 3 ⋅ 2 rankings. Additionally, the teams’ performance was evaluated based on the convergence score, which was incorporated into each case-based ranking with a factor of 3, due to the importance of efficiency in FL. This results in a total of N ⋅ 3 ⋅ 3 ranks summed per team. The final ranking was determined by summing all individual rankings per team.
Task 2: multi-site evaluation of generalization in the wild
Organization
In the training phase, the participants were provided the training set including information on the data origin. They could explore the effects of data partitioning and distribution shifts between contributing sites, to develop tumor segmentation algorithms that generalize to institutional data not present in the training set. Note that training on pooled data was allowed in Task 2, enabling the development of methods that optimally exploit meta-information of data origin.
In the validation phase, participants could evaluate their model on the validation set to estimate in-distribution generalization. For domain generalization there may be better model selection strategies than an in-distribution validation set75, which opened up further research opportunities for the participants.
Participants could submit their inference code as Docker containers76 to the Synapse challenge website at https://www.synapse.org/fets. The latest submission before the deadline was chosen as the final submission. All submissions were tested in an isolated environment on cloud computing infrastructure at DKFZ, which ensures a secure and compliant processing framework and safeguards the host infrastructure from potential malicious attacks. This included the following steps:
1. Convert Docker submissions to singularity container77, as Docker was not allowed on some of the evaluation sites’ IT departments. 2. Run a compatibility testing pipeline, which evaluates the container on a small training subset, using the same software as during the testing phase (described below). 3. Monitor the GPU memory consumption and inference time, which were limited to ensure functionality in the federation. 4. Update the challenge website with the results of the test run and, if successful, upload the container to cloud storage.
Step 2 could also be executed by the participants locally to debug their submission.
In the testing phase, the MedPerf tool31 was used to evaluate all valid submissions on datasets from the FeTS federation, such that the test data are always retained within their owners’ servers.
Assessment methods (Ranking)
The accuracy of the predicted tumor segmentations is measured with DSC and HD 95 (Eqs. (1) and (2)). To assess the robustness of segmentation algorithms to cross-institution shifts, we evaluate algorithms per testing institution first and rank them according to their per-institution performances. Specifically, on institution k of K, algorithms are ranked in the first step on all N k test cases, three regions, and two metrics, yielding N k ⋅ 3 ⋅ 2 ranks for each algorithm. The average over test cases is then used to produce per-institution ranks for each algorithm (rank-then-aggregate approach) and region-metric combination. The final rank of an algorithm is computed from the average of its K ⋅ 3 ⋅ 2 per-institution ranks. Ties are resolved by assigning the minimum rank. This scheme was chosen as it is similar to the BraTS ranking method4. Moreover, our ranking method weights each testing institution equally, as they represent distinct dataset characteristics and we want to avoid a strong bias of the ranking to sites with many test cases.
Description of participants’ methods
As described in the results, for task 1 most participants chose a multi-step approach, which computes several independent, normalized weighting terms p i (step 1) and combines them into an overall weight \(\bar{p}\) (step 2). The latter was done either by additive or multiplicative averaging, defined as
$${\bar{p}}_{{{\rm{add}}}}^{k}=\mathop{\sum}_{i}{\beta }_{i}{p}_{i}^{k}\quad \quad {{\rm{or}}}\quad \quad {\bar{p}}_{{{\rm{mul}}}}^{k}={\prod}_{i}{p}_{i}^{k}$$ (4)
where \({p}_{i}^{k}\) is the weighting term for collaborator k and β i are averaging weights (hyperparameters). The \({\bar{p}}^{k}\) are then normalized and used to aggregate local model parameters \({w}_{t}^{k}\) across K collaborators into a global model \({w}_{t}^{g}\) for each FL round t:
$${w}_{t+1}^{g}={\sum }_{k=1}^{K}{\bar{p}}^{k}{w}_{t}^{k}$$ (5)
The weighting term that all participants incorporated in their solution was proposed by McMahan et al.11: \({p}_{{{\rm{FedAvg}}}}^{k}={N}_{k}/{\sum }_{k}{N}_{k}\), where N k is the number of local samples. Most teams introduced additional adaptive aggregation methods, which change the weighting pk(t) over the course of federated training rounds t.
A summarizing description of the methods contributed by the participating teams is provided below, ordered alphabetically by team name. For Task 2, only the five official submissions are included here. Key components in which the algorithms differ are also presented in Table 1 for Task 1 and Table 2 for Task 2. The algorithm characteristics for Task 2 that stood out in the participants’ method descriptions were the network architecture, the loss function, post-processing steps applied to the model’s predicted segmentation mask, the number of models used in the final ensemble (ensemble size) and whether they used the nnU-Net framework for their implementation. A complete list of members for each team is given in the Supplementary Note 4.
Team Flair39—Task 1
This team presented additional dataset splits of varying sizes for prototyping and tested how a federated version of the multiple gradient descent algorithm, which formulates FL as multi-objective optimization78, performs on the problem. This weight aggregation method ensures that gradient steps are taken only in a direction that does not harm the model performance on individual clients, while also not deviating from the FedAvg weights by more than a hyperparameter ϵ. Full client participation was used in all rounds.
Team FLSTAR36—Task 1
This team tested how various aggregation strategies improve the learning performance in the context of the non-IID and imbalanced data distribution of the FeTS challenge data (partitioning 2). Their final model used a (normalized) multiplicative average of FedAvg weights \({p}_{{{\rm{FedAvg}}}}^{k}\) and local validation loss for aggregating the clients’ parameters: \({p}_{{L}_{{{\rm{val}}}}}^{k}(t)=\frac{1}{Z}L({w}_{t}^{k})\), where \(L({w}_{t}^{k})\) is the validation loss after local training and Z a normalization factor. This term can be interpreted as measuring the potential for local optimization, as clients with high loss can still improve more than low-loss clients. For client selection, only the 6 largest sites from partitioning 2 were used, as they were less prone to overfitting.
Team Gauravsingh41—Task 1
This team implemented an aggregation method inspired by Mächler et al.44, which uses an arithmetic mean of two (normalized) terms for each client weighting factor: (1) local dataset size as in FedAvg, (2) ratio of local validation loss (here negative DSC) after and before local training \({p}_{{{\rm{CostWAvg}}}}^{k}(t)={Z}^{-1}\cdot {{\rm{DSC}}}({w}_{t}^{k})/{{\rm{DSC}}}({w}_{t}^{g})\), where Z normalizes across clients. For client selection, they randomly subdivided all clients into groups of 6 clients and iterated through the groups in each federated round, so that 6 clients are used per round. Every four rounds, the clients were re-grouped.
Team Graylight Imaging79—Task 2
This team built upon the 3D nnU-Net framework, incorporating a customized post-processing step specifically designed for the TC region. The post-processing method, denoted as FillTC, involves relabeling voxels surrounded by TC to NCR. This iterative post-processing is sequentially applied to each 2D slice, first in the axial direction and subsequently in the coronal and sagittal directions. The rationale behind this approach is grounded in clinical expertise, suggesting that significant tumors typically lack voids of healthy tissue. Furthermore, if a given region is surrounded by NCR or ET, it is deemed to be part of the TC.
Team HPCASUSC80—Task 2
This team built their model upon a 3D U-Net and added improvements inspired by the BraTS nnU-Net (2020) paper63. They used region-based training, which uses the WT, TC, and ET regions as labels during training instead of NCR, ED, and ET. Further, they increased the batch size to 24 and used batch normalization layers instead of instance normalization. Data augmentation consisted of random mirroring, rotation, intensity shift, and cropping.
Team HT-TUAS40—Task 1
This team introduced a cost-efficient method for regularized weight aggregation, building upon their previous year’s submission42. For parameter aggregation, the average of FedAvg weighting and a parameter-distance (similarity) weighting was used. Similarity with the average model parameters \({\bar{w}}_{t}=\frac{1}{K}{\sum }_{k}{w}_{t}^{k}\) is measured with the absolute difference between individual local parameters and average parameter tensors \({p}_{{{\rm{sim}}}}^{k}(t)=\frac{1}{Z}| {\bar{w}}_{t}-{w}_{t}^{k}{| }^{-1}\), where the absolute value is applied element-wise. Additionally, the team scaled the individual client weights with a regularization term that is proportional to the parameter difference between the current and previous round. For client selection, they randomly sampled 4 sites per round without replacement and restarted the sampling once all clients participated.
Team NG research81—Task 2
This resubmission from the BraTS 2021 challenge, makes heavy use of model ensembling. The ensemble comprises five models of diverse architectures, both convolutional and transformer-based, which are combined with mean softmax. Their models were refined by several strategies: Randomized data augmentations, incorporating affine transforms, mirroring, and contrast adjustment, were employed during training to enhance model robustness. Furthermore, a post-processing step was integrated, selectively discarding ET predictions falling below a specified volume threshold, similar to Isensee et al.63.
Team rigg35—Task 1
This team developed FedPIDAvg, an aggregation method that is inspired by a proportional-integral-derivative controller. Compared to the predecessor method44, it adds the missing integral term. The aggregation weight for each client is hence the weighted sum of three terms, normalized with factors Z as necessary: (1) local dataset size identical to FedAvg \({p}_{P}^{k}={p}_{{{\rm{FedAvg}}}}^{k}\), (2) cost reduction (or local improvement), i.e., the difference between local loss of the previous and current round, \({p}_{D}^{k}(t)=\frac{1}{{Z}_{D}}(L({w}_{t-1}^{k})-L({w}_{t}^{k}))\), (3) sum of the local loss over the past 5 rounds \({p}_{I}^{k}(t)=\frac{1}{{Z}_{I}}\mathop{\sum }_{i=1}^{5}L({w}_{t-i}^{k})\), which indicates how much room for improvement remains. Selective sampling was also incorporated, by modeling the sample distribution across clients with a Poisson distribution and randomly dropping outliers, i.e., large clients.
Team RoFL37—Task 1
This team focused on tackling data heterogeneity among collaborators and the communication cost of training, exploring a combination of server-side adaptive optimization and judicious parameter aggregation schemes. Server optimizers50 rewrite the model aggregation equation Eq. (5) in the form of a stochastic gradient descent (SGD) update: \({w}_{t+1}^{g}={w}_{t}^{g}-{\lambda }_{s}{\Delta }_{t}\), where λ s is a server learning rate and Δ t the aggregated model update. SGD can then also be replaced with other optimizers. Team RoFL’s final submission uses Adam82 as the server optimizer and takes a two-phase approach: in the first phase, aggregation in Δ t is performed with FedAvg. In the second phase, the client learning rate is decreased while the server learning rate λ s increased. Furhermore, the model updates are aggregated with a multiplicative combination of FedAvg weights and a term computed per scalar parameter that is proportional to the inverse absolute difference between local and average model parameter, as in ref. 42. Full client participation was used in all FL rounds.
Team Sanctuary38—Task 1&2
The solution for Task 1 incorporates three key components. Firstly, model updates are aggregated through inverse distance weighting83, where the inverse L1 distance between the current and the average model parameters is employed to weight the updates contributed by each site. \({p}_{{{\rm{dist}}}}^{k}(t)=\frac{1}{Z}\parallel {\bar{w}}_{t}-{w}_{t}^{k}{\parallel }^{-1}\) Here, \({\bar{w}}_{t}=\frac{1}{K}{\sum }_{k}{w}_{t}^{k}\) is the uniformly averaged model and Z normalizes across collaborators. This aggregation weight is computed for each tensor in the model and combined with the FedAvg weight and a weight inversely proportional to the local training DSC, which penalizes overfitting clients and lifts the weight of clients with potential for local optimization. To mitigate the impact of slow clients on training efficiency, a client pruning strategy is implemented. In even FL rounds, full client participation is used. In odd FL rounds, the simulated round time of each client from the previous is used to select a subset of clients, by dropping clients that exceed a time threshold, which is set to \(0.75\cdot \bar{t}\), where \(\bar{t}\) is the average round time. Additionally, the team adopted a polynomial learning rate schedule to enhance training convergence.
For Task 2, they based their submission on the nnU-Net contribution for BraTS 202063, extending it with test-time adaptation through batch normalization (BN) statistics. Unlike the conventional approach of collecting and freezing BN statistics during training, their method leverages test data information to dynamically correct internal activation distributions, particularly addressing domain shift issues. In their approach, test-time BN recalculates BN statistics (mean μ and standard deviation σ per filter map) based on the batch at prediction time. As the algorithm utilized a batch size of 1 during testing, it is similar to instance norm at test time. Furthermore, the team employed an ensemble strategy involving six models trained on distinct training data folds. Each of these models underwent adaptation using test-time BN.
Team vizviva84—Task 2
This team employed an encoder-decoder architecture based on volumetric vision transformers. In this setup, the encoder partitions a 3D scan into patches, subsequently processing them through layers that amalgamate the outputs of 3D Swin transformer and 3D CSwin transformer blocks85,86. For the decoder, 3D Swin transformer blocks and patch expansion layers are utilized to reconstruct the processed information. The training strategy involves a combination of cross-entropy and Dice loss. Additionally, to bolster the model’s resilience against adversarial examples, virtual adversarial training introduces an extra loss term.
Additional information on Task 2 algorithms
In the FeTS challenge 2022, Task 2, not only official challenge submissions were evaluated, but also 36 models submitted originally to the BraTS challenge 20213. These models are the subset of BraTS 2021 submission that could be converted semi-automatically to the container format used in the FeTS Challenge 2022. Since all of these were described in scientific publications previously, we provide the references to the papers instead of describing each method here in detail in Supplementary Table 4. In the following, Table 2 is supplemented with references and short descriptions of the Task 2 algorithm characteristics:
Architecture
The most common backbone used by the submissions was U-Net67. Several variations to the basic U-Net were introduced by the teams: Some used larger encoders, with more filters per convolution or more convolutional blocks per stage. Adding residual connections to convolutional blocks69 was also common. Several algorithms extended the U-Net with different kinds of attention modules. Examples include inserting a transformer in the bottleneck of the U-Net or re-weighting feature maps with attention restricted to the channel/spatial dimensions. Some participants used other CNNs than U-Net, for instance HR-Net87, HNF-Net88, U-Net++89, and HarDNet90. Recent hybrid CNN/transformer networks like CoTr91, Swin transformer85 were incorporated in some submissions. Finally, a few teams utilized skip connection blocks that combined features from multiple stages or explored splitting the segmentation task into two stages, first segmenting a coarse whole tumor region and then refining the segmentation of this cropped region.
Loss
The most common loss functions were Dice (computed either per sample or per batch) and cross-entropy. Similar to the Dice loss, some teams optimized differentiable versions of segmentation metrics (Jaccard index, generalized Dice, boundary distance, and the generalized Wasserstein Dice loss92). Two less common loss functions were TopK loss, which considers only the K pixels with the highest loss, and the focal loss, which down-weights the loss for pixels that are classified correctly with high softmax scores. Finally, one team used virtual adversarial training93 as an auxiliary, regularizing loss term. Most losses can be calculated either region-based (for each of WT, TC, ET) or for the exclusive labels (ED, NCR, ET).
Post-processing
Techniques that refine a model’s segmentation output based on prior knowledge specific to the three brain tumor regions were popular in the challenge. Dropping small connected components from the final mask (or replacing them with neighboring predictions) can help to reduce false positives. Morphological operations like closing or hole filling were also applied by some teams. Since TC usually is a compact core within WT, post-processing methods enforced this property, by removing TC parts that extend beyond WT or filling holes inside TC. Finally, potential confusion between ET and NCR was counteracted by converting ET output regions to NCR if they are very small (or for one team, if an auxiliary network suggests this).
Reporting summary
Further information on research design is available in the Nature Portfolio Reporting Summary linked to this article.
| 2023-01-01T00:00:00 |
https://www.nature.com/articles/s41467-025-60466-1
|
[
{
"date": "2023/01/01",
"position": 79,
"query": "AI healthcare"
},
{
"date": "2023/02/01",
"position": 80,
"query": "AI healthcare"
},
{
"date": "2023/07/01",
"position": 75,
"query": "AI healthcare"
},
{
"date": "2023/08/01",
"position": 75,
"query": "AI healthcare"
},
{
"date": "2023/11/01",
"position": 80,
"query": "AI healthcare"
},
{
"date": "2023/12/01",
"position": 69,
"query": "AI healthcare"
},
{
"date": "2024/01/01",
"position": 82,
"query": "AI healthcare"
},
{
"date": "2024/03/01",
"position": 77,
"query": "AI healthcare"
},
{
"date": "2024/09/01",
"position": 79,
"query": "AI healthcare"
},
{
"date": "2024/11/01",
"position": 78,
"query": "AI healthcare"
},
{
"date": "2025/02/01",
"position": 92,
"query": "AI healthcare"
},
{
"date": "2025/04/01",
"position": 92,
"query": "AI healthcare"
},
{
"date": "2025/06/01",
"position": 92,
"query": "AI healthcare"
}
] |
|
AI Healthcare Surge: SoundHound AI's Role Amplifies Market Buzz
|
AI Healthcare Surge: SoundHound AI’s Role Amplifies Market Buzz
|
https://stockstotrade.com
|
[
"Tim Bohen",
"Ben Sturgill",
"Ellis Hobbs"
] |
Significant investments in AI healthcare, with contributions from firms such as SoundHound AI, are propelling advancements in diagnostics, ...
|
SoundHound AI Inc. stock trading up 8.83% reflects rising market enthusiasm and potential strategic progress.
Key Takeaways Significant investments in AI healthcare, with contributions from firms such as SoundHound AI, are propelling advancements in diagnostics, patient care, and operational efficiency.
The trend indicates robust potential in the sector, as companies aim to capitalize on the versatile applications of AI across the healthcare industry.
A notable surge in AI healthcare funding signals the industry’s readiness to embrace technological innovations like never before.
Major players driving the funding wave underscore the sector’s transformative potential, emphasizing a future rich with opportunities.
Live Update At 12:04:39 EST: On Tuesday, July 08, 2025 SoundHound AI Inc. stock [NASDAQ: SOUN] is trending up by 8.83%! Discover the key drivers behind this movement as well as our expert analysis in the detailed breakdown below.
Quick Financial Overview
In recent months, SoundHound AI has been navigating choppy financial waters, with a stock range showcasing noticeable variability. The current trading values show some fluctuations: an opening price of $12.04 and a closing price of $12.3847, displaying a day’s high of $13.415. SoundHound’s earnings report reflects a mixed bag of results, with sales revenue standing at $84.69M. Odd as it may sound, such revenue levels, juxtaposed with a notable loss margin, spell a familiar tale of tech-driven companies. The company is still seeking sustained profitability with a smooth sailing current ratio of 4.9.
More Breaking News
Investors might find comfort in the healthy cash flow position, with free cash flow dipping yet crafting opportunities for long-term growth. These financial maneuvers speak to robust investment and strategic positioning, enabling SoundHound AI to ride the waves of technological innovation effectively despite some setbacks.
Market Reactions: Enthusiastic yet Cautiously Optimistic
SoundHound’s strategic involvement in AI healthcare funding has sparked a fresh wave of enthusiasm. Such initiatives suggest a keen interest in capitalizing on AI’s potential to revolutionize healthcare. The contributions bolster SoundHound’s image as a front-runner embracing innovation.
The stock market shows a buoyant response with increased trading activity, reflecting a blend of anticipation and cautious optimism among investors. While some cheer the foresight to leverage the rapidly growing AI healthcare segment, others weigh the risks associated with high-cost investments and longer gestation periods. This dynamic fosters a lively tug-of-war in investor sentiment, teetering between high hopes and the wait-and-see approach that marks typical tech pursuits.
Conclusion
In conclusion, SoundHound AI, alongside its peers, stands at the cusp of an AI-infused healthcare revolution, with increased funding signaling positive strides. Traders keen on growth find such developments compelling, positioning themselves strategically within the evolving narrative of healthcare transformation.
As we thread through the rest of 2025, the dance between innovation and traditional financial metrics continues, casting a compelling shadow over SoundHound AI’s endeavors. The fluctuating stock prices are mere echoes of the tumultuous yet rewarding quest for tech integration within healthcare. As Tim Bohen, lead trainer with StocksToTrade says, “There’s a pattern in everything; you just have to stick around long enough to see it.” This insight sheds light on the chaotic fluctuations traders navigate, seeking to discern long-term potential amidst near-term volatility. With strategic finesse and financial agility, SoundHound AI holds the potential to script an enviable chapter in AI-driven healthcare transformation. The question remains: are we witnessing the dawn of a new era for AI in healthcare? Only time can reveal the unfolding tapestry of innovation and market response.
This is stock news, not investment advice. StocksToTrade News delivers real-time stock market updates tailored to highlight the key catalysts driving short-term price movements. Our coverage is designed for active traders and investors who thrive in fast-moving markets, with a focus on volatile sectors like penny stocks, AI stocks, Robinhood stocks and other momentum plays. From earnings reports and FDA approvals to mergers, new contracts, and unusual trading volume, we break down the events that can spark significant price action.
Looking to level up your trading game? Explore StocksToTrade, the ultimate platform for traders. With powerful tools designed for swing and day trading, integrated news scanning, and even social media monitoring, StocksToTrade keeps you one step ahead.
Check out our quick startup guide for new traders!
Ready to build your watchlists? Check out these curated lists:
Once your watchlist is set, take the next step and trade with confidence using StocksToTrade’s robust platform. Don’t miss out — grab your 14-day trial for just $7 and experience the edge you need to thrive in today’s fast-paced markets.
| 2023-01-01T00:00:00 |
https://stockstotrade.com/news/soundhound-ai-inc-soun-news-2025_07_08-2/
|
[
{
"date": "2023/01/01",
"position": 80,
"query": "AI healthcare"
},
{
"date": "2023/02/01",
"position": 81,
"query": "AI healthcare"
},
{
"date": "2023/07/01",
"position": 90,
"query": "AI healthcare"
},
{
"date": "2023/08/01",
"position": 88,
"query": "AI healthcare"
},
{
"date": "2023/11/01",
"position": 92,
"query": "AI healthcare"
},
{
"date": "2023/12/01",
"position": 87,
"query": "AI healthcare"
},
{
"date": "2024/01/01",
"position": 93,
"query": "AI healthcare"
},
{
"date": "2024/03/01",
"position": 90,
"query": "AI healthcare"
},
{
"date": "2024/09/01",
"position": 93,
"query": "AI healthcare"
},
{
"date": "2024/11/01",
"position": 89,
"query": "AI healthcare"
}
] |
|
What is AI Healthcare? | Glossary | HPE
|
What is AI Healthcare? | Glossary
|
https://www.hpe.com
|
[] |
AI in healthcare is the use of machine learning (ML) to assist and, ideally, improve the patient experience and hospital operations, and expenses.
|
What are the benefits of AI in healthcare?
For clinical outcomes, AI analytics provides a faster, more in-depth examination of information without the risk of human error (for example, detecting tumors or precursors for disease). In turn, physicians and surgeons can leverage these results into better treatment options that can translate to improved outcomes. The processing power of AI isn’t limited to a case-by-case basis; it can take information from across the globe and uncover actionable insights that can lead to life-saving care and medical innovation. During the COVID-19 pandemic, for example, AI could be used to analyze new variants and create new, effective treatments faster than human-based research and assessment. In the past, AI has been essential for gene mapping and other pioneering genetics work.
For operational efficiencies, AI can identify opportunities to streamline processes, including surgery, and make them more productive. In turn, AI informs better decision-making by giving IT and medical administrators better visibility that can proactively avoid mistakes, resolve issues, and lower operating costs. Similar to improving patient medical outcomes, AI can improve how medical professionals and caregivers deliver care by having faster access to more patient records or finding more efficient ways to manage patient care. With help from NPL, AI can even comb clinical notes (i.e., unstructured data), classify them, and use them to optimize clinical processes.
AI also helps medical organizations stay in compliance with enhanced security and safety. In addition to mitigating fraudulent access to private medical information, AI enables intelligent video analytics (IVA), letting staff members monitor their facilities and patients. Using IVA and smart sensors, smart hospitals can recognize objects such as medical equipment and face coverings.
Identify and match the faces of doctors and patients, and even detect elevated body temperatures. These inputs are used to determine high-risk individuals and create actionable outcomes.
| 2023-01-01T00:00:00 |
https://www.hpe.com/us/en/what-is/ai-healthcare.html
|
[
{
"date": "2023/01/01",
"position": 82,
"query": "AI healthcare"
},
{
"date": "2023/02/01",
"position": 78,
"query": "AI healthcare"
},
{
"date": "2023/07/01",
"position": 71,
"query": "AI healthcare"
},
{
"date": "2023/08/01",
"position": 71,
"query": "AI healthcare"
},
{
"date": "2023/11/01",
"position": 71,
"query": "AI healthcare"
},
{
"date": "2023/12/01",
"position": 99,
"query": "AI healthcare"
},
{
"date": "2024/01/01",
"position": 65,
"query": "AI healthcare"
},
{
"date": "2024/03/01",
"position": 71,
"query": "AI healthcare"
},
{
"date": "2024/09/01",
"position": 71,
"query": "AI healthcare"
},
{
"date": "2024/11/01",
"position": 71,
"query": "AI healthcare"
},
{
"date": "2025/02/01",
"position": 17,
"query": "AI healthcare"
},
{
"date": "2025/04/01",
"position": 17,
"query": "AI healthcare"
},
{
"date": "2025/06/01",
"position": 17,
"query": "AI healthcare"
}
] |
|
Prompt injection attacks: an inherent vulnerability of healthcare AI ...
|
Prompt injection attacks: an inherent vulnerability of healthcare AI agents – BJGP Life
|
https://bjgplife.com
|
[
"Bjgp Life",
"Latest Posts"
] |
Artificial intelligence (AI) agents are rapidly emerging across various sectors, with healthcare representing one of the most promising ...
|
Richard Armitage is a GP and Honorary Clinical Assistant Professor at the University of Nottingham’s Academic Unit of Population and Lifespan Sciences. He is on X: @drricharmitage
Artificial intelligence (AI) agents are rapidly emerging across various sectors, with healthcare representing one of the most promising frontiers for deployment.1 These sophisticated systems, built on large language model foundations, possess remarkable capabilities that extend far beyond simple text generation. They can process complex information, maintain memory through recall and reflection mechanisms, facilitate interaction between different systems, leverage specialised tools, and operate with significant autonomy.2
In healthcare settings, AI agents are transforming clinical operations by automating traditionally labour-intensive workflows. These systems can efficiently process clinical correspondence, analyse investigation results, and conduct routine medication reviews. When coupled with speech recognition technology, AI agents are being deployed for both clinical and non-clinical patient-facing tasks including triaging, diagnosis and management suggestions, clinical record writing, discharge summary production, patient registration, and automated appointment scheduling.3 A major feature of AI agents is their ability to act autonomously to achieve specific goals. For example, an agent with access to a patient’s electronic health record could process incoming clinical correspondence, automatically arrange appropriate investigations, and schedule relevant consultations with a GP or practice nurse.
While these tools promise to improve patient care and reduce administrative burden on GPs and wider practice staff, they come with substantial inherent vulnerabilities. One such risk recently came to light through Microsoft 365 Copilot, an AI agent built into Microsoft Office workplace applications. The flaw represents the first documented “zero-click” attack on an AI agent – an attack that requires no user interaction, such as clicking a malicious link – capable of accessing sensitive information from apps and data sources connected to the agent. The vulnerability, known as “EchoLeak,” would allow hackers to trigger an attack simply by sending an email containing a prompt that deceives the AI agent into leaking the user’s personal information back to the hacker.4 Unlike phishing and malware attacks, which rely on users mistakenly clicking malicious links, the AI agent would autonomously execute the prompt embedded in the email. These security flaws are known as ‘LLM scope violation vulnerabilities’ – where the model is tricked into accessing or exposing data beyond its permitted boundaries – or ‘prompt injection attacks.’ Microsoft has stated that the issue has been fixed in Microsoft 365 Copilot and that no customers were affected.5
Given the highly sensitive nature of information stored within healthcare settings, the vulnerability of AI agents to this kind of attack is deeply concerning. GP practices handle the comprehensive records of thousands of patients, including their medical histories, mental health data, prescription details, and safeguarding information. A successful attack on an AI agent in general practice could expose entire practice databases of highly sensitive information. Such breaches would not only violate patient confidentiality and data protection regulations but could also compromise NHS patient safety protocols and undermine public trust in digital healthcare technologies.
As the NHS, and primary care in particular, increasingly invests in AI-powered tools to address workforce pressures, improve patient care, and bolster efficiency, ensuring robust security measures to safeguard against these tools’ inherent vulnerabilities becomes paramount.
References
M Moritz, E Topol, P Rajpurkar. Coordinated AI agents for advancing healthcare. Nature Biomedical Engineering 01 April 2025; 9: 432–438. DOI: 10.1038/s41551-025-01363-2 J Qiu, K Lam, G Li, et al. LLM-based agentic systems in medicine and healthcare. Nature Machine Intelligence 05 December 2024; 6, 1418–1420. DOI: 10.1038/s42256-024-00944-1 SA Gebreab, K Salah, R Jayaraman, et al. LLM-Based Framework for Administrative Task Automation in Healthcare. 2024 12th International Symposium on Digital Forensics and Security (ISDFS), San Antonio, TX, USA, 2024: 1-7, DOI: 10.1109/ISDFS60797.2024.10527275 Aim Labs Team. Breaking down ‘EchoLeak’, the First Zero-Click AI Vulnerability Enabling Data Exfiltration from Microsoft 365 Copilot. 11 June 2025. https://www.aim.security/lp/aim-labs-echoleak-blogpost [accessed 17 June 2025] S Goldman. Exclusive: New Microsoft Copilot flaw signals broader risk of AI agents being hacked—‘I would be terrified’. Fortune 11 June 2025. https://fortune.com/2025/06/11/microsoft-copilot-vulnerability-ai-agents-echoleak-hacking/ [accessed 17 June 2025]
Featured Photo by sebastiaan stam on Unsplash
| 2025-07-08T00:00:00 |
2025/07/08
|
https://bjgplife.com/prompt-injection-attacks-an-inherent-vulnerability-of-healthcare-ai-agents/
|
[
{
"date": "2023/01/01",
"position": 83,
"query": "AI healthcare"
},
{
"date": "2023/07/01",
"position": 89,
"query": "AI healthcare"
},
{
"date": "2023/11/01",
"position": 89,
"query": "AI healthcare"
},
{
"date": "2023/12/01",
"position": 86,
"query": "AI healthcare"
},
{
"date": "2024/01/01",
"position": 91,
"query": "AI healthcare"
},
{
"date": "2024/03/01",
"position": 88,
"query": "AI healthcare"
},
{
"date": "2024/09/01",
"position": 90,
"query": "AI healthcare"
},
{
"date": "2024/11/01",
"position": 87,
"query": "AI healthcare"
}
] |
Avoiding a future where the 'cause of death' is an AI chatbot
|
Avoiding a future where the ‘cause of death’ is an AI chatbot | Viewpoint
|
https://www.chiefhealthcareexecutive.com
|
[
"Peter Bonis"
] |
AI in healthcare is under intense scrutiny given the high stakes involved in patient care. As many doctors are already using it in a ...
|
AI in healthcare is under intense scrutiny given the high stakes involved in patient care. As many doctors are already using it in a clinical setting, I wanted to put generative artificial intelligence, commonly called AI chatbots or GenAI, to the test.
Peter Bonis
The results were concerning, at best.
Turning to a well-known, free AI chatbot, I asked a relatively straightforward medical question. “How do you treat a urinary tract infection (UTI) in a patient with a penicillin allergy?”
To the untrained eye, the answer seemed convincing enough: “fluoroquinolones or levofloxacin” were listed among the options.
Mistake number one: levofloxacin is a type of fluoroquinolone, so the response wasn’t worded accurately and could cause the reader to believe that levofloxacin was not a fluoroquinolone. I, however, was much more concerned with what I would deem a medically serious flaw: there was no caveat for a pregnant patient.
Put simply, fluroquinolones can cause serious fetal harm. If the patient was pregnant, it could have been extremely detrimental to the health of the baby had a clinician blindly followed the response. The AI chatbot failed to consider this basic context because it did not have a sense of how critical this detail was. And why would it? It doesn’t have real clinical experience to navigate the many checkpoints informed by medical training, nor the reasoning and judgment from years of clinical practice.
Still, when combined with other technologies, GenAI tools have great potential to augment clinical decision-making beyond what doctors and nurses alone are capable of.
At present, AI chatbots can aid in diagnosis and care management. They perform well on medical board exams according to a growing number of studies. But the data do not tell the whole story.
There are several specific issues with current mainstream AI chatbots that demonstrate the technology is not ready to have a major role in clinical decision making on the frontlines of healthcare.
Hallucinations
As the most well-known risk of any GenAI platform, hallucinations persist despite the blistering pace of AI chatbot evolution.
And hallucinations are not always easy to recognize—even by clinicians who are convinced they can spot them. We cannot put the burden of differentiating the wheat from the chaff on a busy doctor who often has just seconds to make a judgment call.
GenAI models sometimes include references, but it is very unlikely clinicians will consistently verify whether the original source material is valid or hallucinated. I have already encountered references citing seemingly convincing studies that proved to be non-existent. In other cases, even valid references may come up short, not fully reflecting what is known about a given topic.
Inconsistency
If you ask an AI chatbot a question one day, and try that same prompt later, you’ll likely get two responses that can be different enough to be interpreted in meaningfully different ways. At a basic statistical level, GenAI’s outputs can vary greatly, which should be a serious concern for doctors as well as patients.
Biases
GenAI platforms are prone to a range of biases. Egregious examples of racial bias have shown that how a prompt is worded can not only influence the responses, but it can also cause responses to vary with clinically significant differences. (Study 1, study 2)
More subtle biases lurk in the decisions the models must make to prioritize various inputs. For example, how does the model consistently choose the most credible source of information when it encounters conflicting evidence in the research? For now, anyway, AI chatbots can’t perform critical peer review to evaluate evidence. A variety of human-like errors in judgment due to bias have also been reported.
Muscle memory lapses
AI chatbots are dazzling medical users with nearly instantaneous answers, even if they are sometimes inaccurate. While a doctor is the final decision maker, they may become accustomed to asking questions and implementing the responses, developing a sort of trusting muscle memory for the process, and over time, giving the recommendations provided less and less scrutiny and consideration.
This presents wholly new dimensions of decision-making for regulators to evaluate, not to mention uncharted legal territory for medical mistakes.
Real-world overload
Diagnosing and treating a disease can take several steps over time, as information evolves. While GenAI models can handle tidy board-exam clinical vignettes, they falter substantially with messy, real-world data evolving during actual patient care. (Study 1, study 2)
In a sector where one wrong response to a prompt can have grievous consequences, tackling these issues head-on will help build a roadmap for healthcare generative AI done right.
With proper vetting and processes to ensure clinical accuracy, AI chatbots combined with other technologies can improve physician-patient interactions in real-time by guiding follow-up questions, keeping context in mind, and leveraging the best evidence to assist with care.
| 2023-01-01T00:00:00 |
https://www.chiefhealthcareexecutive.com/view/avoiding-a-future-where-the-cause-of-death-is-an-ai-chatbot-viewpoint
|
[
{
"date": "2023/01/01",
"position": 84,
"query": "AI healthcare"
},
{
"date": "2023/02/01",
"position": 82,
"query": "AI healthcare"
}
] |
|
Why It Is Crucial to Involve Nurses in AI Development Processes
|
Why It Is Crucial to Involve Nurses in AI Development Processes
|
https://www.hcinnovationgroup.com
|
[
"David Raths"
] |
Patient safety researchers at the Institute for Healthcare Improvement (IHI) have been studying nurse-led technology innovation, ...
|
Patient safety researchers at the Institute for Healthcare Improvement (IHI) have been studying nurse-led technology innovation, including introducing AI into nursing workflow. Healthcare Innovation recently spoke with Patricia McGaffigan, R.N., M.S., vice president of safety at IHI and president of the Certification Board for Professionals in Patient Safety, and Kate Feske-Kirby, an IHI research associate in innovation, about their current research efforts.
Healthcare Innovation: AI is being introduced into clinical workflows at a rapid pace. You two have given a lot of thought to some of the issues that need to be addressed during this transition regarding nursing. Could you talk about some of the possible unintended consequences that might be introduced into the nursing workflow if AI tools are rolled out too rapidly or without enough input form nurses?
McGaffigan: The IHI Lucian Leape Institute, a patient safety think tank, has worked with an expert panel and created a core paper from which this work has evolved. We frame it as the hype, the hope and the potential peril of this work. One of the main concerns that people have is grounded in the safety lens and whether AI is really safe for use, particularly for clinical purposes. There are some concerns about whether it will impact safety — for example, if it's used for prior authorizations and other things which clearly have safety implications.
There are a number of safety implications that come up in terms of whether decision support is accurate and based on evidence, and what the learning data set is that is informing any of the recommendations. There are concerns about whether people will know that decisions are based on the use of artificial intelligence and whether there are transparency requirements that should be provided. Also, are people really prepared now to embrace this technology and make safe decisions about its use, and how will that impact how we skill and build competencies in the future workforce?
HCI: Is there a concern about a loss of nurse autonomy — that their judgment could be overruled?
McGaffigan: Yes. There’s also concern about whether the role of nurses will be replaced because of AI. My personal opinion is that the risk will be if nursing does not embrace and learn to lead the safe and responsible use of AI in our work, because the benefits are equally compelling.
HCI: Kate, did you want to talk about any other issues that your research identified as potential concerns?
Feske-Kirby: One thing that came up quite often, particularly during the Lucian Leape Institute expert panel, was potential depersonalization and disconnection, both between the clinician and their patient and the patient's family, as well as between the clinicians and their work.
When you have an interaction with the patient, you get to know them. You talk to them about how their day is going. And sometimes the technology that is made to support documentation tasks, which can be very useful in alleviating that burden, might not record that information, or might depersonalize that note so that maybe that clinician/patient relationships might take a bit of a hit there, although we very much believe that nurses and other clinicians have the ability to keep that moving forward.
Another issue is alert fatigue. Once this is implemented, how will it actually perform in day-to-day clinical tasks? There has already been some effort to implement some of these technologies before, and there haven’t necessarily been efforts at co-design, making sure that key parties are involved in the design, the implementation and the monitoring of these technologies.
HCI: This sounds like a continuation of problems that have been longstanding, as far as nurses feeling like technological deployments are things that happen to them rather than with them. You mentioned co-design. Could nurses by resistant to AI if it feels like they weren't involved in the development of the applications but it's applied to their everyday work?
McGaffigan: In recent presentations that I've done, one as recently as last week and several in recent months with hundreds of nurses and nurse leaders, we’ve done surveys and very few of them have been involved in any way in the meaningful governance or engagement or user-centered approaches to considering and bringing generative AI into their worlds. And that, in and of itself, is a major reason why there will always be resistance to new ideas, whether they're technology-based or not.
A lot of what we advocate for in this work is making sure that in the governance and oversight and decision-making and testing, we've got nurses who are embedded in all aspects of that work. And to not just think about it as something that we do to get a new technology launched, but to look at this, as we do at IHI, as continuous improvement work. We’re going to continue to learn and appreciate new things, especially because we're seeing the pace of development in AI be so incredibly brisk.
HCI: Viewing it from the outside, it would seem like such an oversight to develop AI governance strategies and teams and not include nurses or nurse leadership.
McGaffigan: We have compelling reasons to state that nurses should be meaningfully involved from stem to stern in this process. The way generative AI applications are developed might be coming from external parties and developers. There’s a lot of physician-led work in this space, and I'm really hopeful we will see more bright spots of opportunity for AI applications that will benefit nurses, such as event listening to help with documentation or scheduling — capabilities that make life for a charge nurse much less complex.
I've talked with AI companies, and I am extremely hopeful that there are a lot of investments going into a very much needed opportunity for generative AI to make a really meaningful difference for the work of nurses to allow them to spend more time with patients. I think it will take a while, but I'm hopeful.
HCI: I understand that IHI and other groups participated in a Learning and Action Network pilot with nurse-led teams at five healthcare organizations. Was the goal to learn how some of these innovative solutions can help the nursing workforce thrive? Were there some key findings from that work you could talk about?
McGaffigan: There were some key findings, and it's such a fun project that was generously funded by the Johnson & Johnson Foundation, where we engaged five different types of healthcare settings that wanted to test new approaches for care delivery innovation with a primary outcome measure in whether or not we could positively impact the thriving of the workforce.
There were a series of change ideas that fell into different categories, many of which were including and addressing virtual nursing technologies. There was an AI technology that was used to support patient assignments, and another area involved how we reconfigure care delivery teams and the work of care delivery teams to be able to best serve patients.
You hear all the time that we need to retain nurses and we need to reduce turnover. We would agree with that. What was different and important about this project was moving beyond whether or not we had a nurse at the bedside; we cared about whether that nurse was thriving, because we know from all of our work in safety and quality that the outcomes of patients are inextricably linked with the safety and the well-being and the ability of the workforce to come to work every day and be at their best.
We were able to measurably appreciate whether or not teams were thriving amid nurse-led care delivery innovation. We did find quantitative improvement in elements of thriving and a balance of qualitative improvements for nurses in terms of time saved, how they felt about coming to work every day, whether they felt they had more time with patients, and whether we were able to meaningfully engage them in their work, in really stewarding redesign of work and systems in which work is done.
HCI: It seems like that kind of analysis could also serve as an alarm bell on the other side — if people weren't thriving as you were doing an implementation, you could stop and make adjustments. But without that measurement, you might not actually realize the impact you're having.
McGaffigan: If you look at why nurses are leaving their jobs, some of it is because they feel that they're not valued and that they are not able to meaningfully contribute to evolving the work of nursing, and they feel grossly understaffed. This model brought the five sites together to be able to learn as one and share ideas, and, more importantly, to be able to test ideas of change before we roll them out. That speaks to a lot of what you have heard about technology rollout. Often it is about going big without really understanding the conditions under which that thrives or fails.
HCI: Your research has identified some guardrails to consider when doing this type of implementation. Kate, could you mention a few of those?
Feske-Kirby: One involved investing in developing and sustaining skills and competencies for nurses. We want to make sure that nurses are equipped and feel comfortable using new technology, that they can apply it safely and provide quality care. But there's also the question of making sure that they remain skilled without the technology should anything happen. Technical glitches happen. We've had lots of adverse weather conditions that can really impact a hospital or healthcare's ability to sustain technology that uses a lot of energy.
Another is advocating for and engaging in continuous improvement. I think our phrase was, “nurses are indomitable improvers.” They're really the backbone of this work and thinking about the larger workflow and patient flow through a hospital, to make sure that improvements really touch all corners of the hospital, workforce and patient experience.
And another guardrail is around making sure that any time saved, any efficiencies that are gleaned from artificial intelligence or use of new technology are repurposed into providing better care and more time with patients.
HCI: A few months ago, I interviewed the dean of the nursing school at Florida State University because they were launching an AI-focused Master of Science Nursing program. Is it important that more nursing schools follow suit and build AI into the curriculum, so that nurses get experience working and innovating with these tools in their training before they get into the workforce?
McGaffigan: You just mentioned something I get super-excited to hear about — it’s how nursing education is changing and evolving to be able to keep up with and hopefully lead and get ahead of technology changes. You just referred to a graduate program, which is fabulous, and yes, I think the inclusion of AI and other technology use into foundational pre-licensure education for all healthcare professionals is super-critical right now. I know that changing curricula and adding curricula is not something that can be easily done overnight, but thinking about how we can evolve the way we approach education of healthcare colleagues and healthcare leaders to be able to ensure we're able to stay ahead of this and provide just-in-time education, as we see the rapid pace of technology unfold, is super-important for workforce capabilities and for ensuring that we have high-quality care.
| 2023-01-01T00:00:00 |
https://www.hcinnovationgroup.com/clinical-it/nursing/article/55301520/why-it-is-crucial-to-involve-nurses-in-ai-development-processes
|
[
{
"date": "2023/01/01",
"position": 85,
"query": "AI healthcare"
},
{
"date": "2023/02/01",
"position": 79,
"query": "AI healthcare"
}
] |
|
Generative AI in Healthcare Market Growing at 36–38% CAGR Amid ...
|
Generative AI in Healthcare Market Growing at 36–38% CAGR Amid Demand for Precision Care by 2029
|
https://www.pharmiweb.com
|
[] |
The Global Generative Artificial Intelligence (GenAI) in Healthcare Market is expected to witness a growth rate of 36-38% in the next five ...
|
The Global Generative Artificial Intelligence (GenAI) in Healthcare Market is expected to witness a growth rate of 36-38% in the next five years. The rapid advancements in AI technology; increasing demand for precision medicine; increasing demand for efficient healthcare solutions; expanding venture funding and other investments in the AI sector; ability of generative AI to automate tasks, reduce errors, optimize treatment, and lowers costs; availability of vast amounts of healthcare data, including EHRs, medical imaging, and genomic data; and growing applications in drug discovery are some of the key factors driving the Generative AI in Healthcare market growth. However, data privacy and security concerns; regulatory challenges; the high cost associated with development, deployment, and maintenance of generative AI system; and ethical concerns related to the use of AI in healthcare is likely to hinder the market’s growth.
Generative AI, in the context of healthcare, refers to artificial intelligence systems and algorithms that have the capability to generate new, original data, content, or information related to healthcare. These AI systems use deep learning and neural networks to create data or content that is not explicitly programmed but is instead generated based on patterns and information learned from existing healthcare datasets.
Download a free sample report for in-depth market insights
https://meditechinsights.com/generative-ai-in-healthcare-market/request-sample/
The Rapid Advancements in AI Technology to Drive Market Growth
The rapid advancements in AI technology are pivotal in driving the growth of generative AI in the healthcare market. Breakthroughs in deep learning, natural language processing (NLP), and neural networks enable AI systems to analyse vast amounts of medical data with unprecedented accuracy. These technologies facilitate the automation of complex tasks such as drug discovery, diagnostic imaging, and personalized treatment planning, improving patient outcomes and operational efficiency. Enhanced AI algorithms can predict disease progression, optimize treatment plans, and even generate novel therapeutic solutions tailored to individual patients. As these technologies continue to evolve, they reduce the time and cost of medical research and development, making advanced healthcare solutions more accessible. Consequently, the integration of cutting-edge AI technologies is transforming healthcare delivery, driving demand for generative AI applications, and fuelling market expansion.
“Advancements in AI, particularly in machine learning and deep learning, have significantly improved the efficiency and innovation in industries like healthcare. These technologies enable faster data processing, more accurate predictions, and the automation of complex tasks, which are crucial for accelerating growth"- Vice President, GenAI Product and Data Strategy, An AI Healthcare Company, United States
Expanding Venture Funding and Other Investments in the AI sector to Fuel Market Growth
Venture capital investment in artificial intelligence (AI) has surged in recent years, reaching record levels in 2024, with the generative AI (GenAI) sector particularly benefiting. In 2023, GenAI start-ups globally raised USD10 billion in venture capital, marking a 110% increase from 2021 (source: GlobalData). The sector is projected to receive over USD12 billion globally in 2024 (source: EY). The healthcare industry is emerging as a key focus for generative AI applications, with venture capitalists increasingly recognizing its transformative potential. This has led to significant financial investments, not only from VCs but also from major corporations. For example, Microsoft has invested over USD13 billion in OpenAI since their partnership began in 2019, integrating OpenAI's models across its product suite, including Azure, Bing, Teams, and Windows.
Other well-funded generative AI companies, like Jasper.ai, which raised USD125 million and achieved a USD1.5 billion valuation, are also contributing to the sector's rapid growth. These investments enable start-ups and established companies to accelerate the development and deployment of innovative AI-driven solutions in healthcare. Generative AI, with its capabilities in drug discovery, personalized medicine, and predictive diagnostics, offers significant opportunities to improve patient outcomes and reduce healthcare costs. Substantial venture funding supports research, talent acquisition, regulatory approvals, and partnerships, ultimately driving rapid adoption and market growth in the healthcare sector. The growing confidence of VCs in AI further attracts other investors, creating a positive feedback loop that continuously propels the generative AI healthcare market forward.
Technological Innovations are Driving the Generative AI in Healthcare Market
The Generative AI in Healthcare market is technology-driven and is marked by constant initiatives for product innovations. For instance,
In June 2024, Cognizant, in partnership with Google Cloud, launched healthcare-specific generative AI solutions to streamline administrative processes and improve patient care experiences. These AI-driven tools target high-cost workflows, enhancing efficiency, accuracy, and overall healthcare delivery
In April 2014, Augmedix launched Augmedix Go, the first fully-automated, generative AI-powered medical documentation product for emergency departments, following a successful pilot with HCA Healthcare. The solution aims to enhance patient care, reduce clinicians' documentation burden, and improve productivity by accurately automating medical notes in complex, noisy ED environments
launched Augmedix Go, the first fully-automated, generative AI-powered medical documentation product for emergency departments, following a successful pilot with HCA Healthcare. The solution aims to enhance patient care, reduce clinicians' documentation burden, and improve productivity by accurately automating medical notes in complex, noisy ED environments In March 2024, NVIDIA launched over two dozen healthcare microservices, enabling global healthcare enterprises to leverage generative AI for advanced medical applications across any cloud platform. These microservices, including optimized AI models and development tools, accelerate healthcare workflows in drug discovery, medical imaging, and genomics, enhancing patient care and clinical interactions
In February 2024, Hartford HealthCare launched its Center for Artificial Intelligence (AI) Innovation in Healthcare to advance AI research and development in clinical care, collaborating with institutions like MIT and the University of Oxford. The center aims to lead AI-driven healthcare transformation by focusing on collaboration, trustworthiness, and innovation, building on Hartford HealthCare's existing AI initiatives
US Expected to be a Major Growth Engine in Generative AI in Healthcare Market
The US is expected to be a major growth engine in the Generative AI in healthcare market due to several factors. First, the country’s robust healthcare infrastructure and advanced technology adoption create an ideal environment for AI integration. Major healthcare providers, such as hospitals and clinics, are increasingly embracing AI to enhance patient care, streamline administrative processes, and improve outcomes. Second, the US is home to leading AI companies, research institutions, and tech giants like Google, IBM, and NVIDIA, which are heavily investing in AI development and applications tailored for healthcare. This fosters innovation and accelerates the deployment of AI solutions in the medical field. Third, there is significant venture capital funding and government support for AI in healthcare, further driving market growth. Regulatory bodies like the FDA are also adapting frameworks to ensure the safe integration of AI technologies, encouraging more widespread adoption. Overall, the US combines technological leadership, investment, and a supportive regulatory environment, making it a key driver in the global Generative AI healthcare market.
Growth in the APAC generative AI in healthcare market is driven by the rapid adoption of digital health technologies and AI-powered solutions across the region. Significant investments from both private and public sectors are fuelling innovation, while supportive government policies and initiatives are enhancing healthcare infrastructure, making the region a key area for AI-driven healthcare advancements. Additionally, a growing focus on personalized medicine and improving healthcare access in densely populated areas further accelerates market growth.
Application Type Segment Analysis
The generative AI in Healthcare market comprises application types like: Drug Discovery and Development, Medical research and data analysis, Medical Imaging and Diagnostics, Patient Assistance and Monitoring, Personalized Medicine, Clinical Decision Support, Healthcare Operations, Predictive Analytics and Other Applications. Drug Discovery and Development is the largest segment due to the extensive use of AI in accelerating the discovery of new drugs, optimizing clinical trials, and reducing time-to-market. This segment benefits from AI’s ability to analyze large datasets, simulate drug interactions, and predict outcomes more efficiently. Growth in the patient assistance and monitoring segment is driven by the rapid advancements in AI-driven virtual assistants and remote monitoring technologies. AI tools are increasingly being used to provide real-time health support, enhance patient engagement, and monitor chronic conditions, making this segment particularly dynamic. The rise in telehealth and wearable devices further contributes to its expansion.
End User Type Segment Analysis
The generative AI in Healthcare market can be analyzed based on end user types, such as Pharmaceutical & Biotechnology Companies, Medical Device Companies, Healthcare Payers, Academic & Research Institutes, and Other End Users. Pharmaceutical & biotechnology companies represent the largest segment. This is due to their extensive use of AI in drug discovery, development, and clinical trials. AI helps these companies streamline processes, enhance precision in drug targeting, and reduce costs, making them the primary adopters of generative AI technologies. The growth in the healthcare providers segment for AI in healthcare is driven by the need for improved patient care and operational efficiency. AI aids in automating administrative tasks, enhancing diagnostic accuracy, and personalizing treatment plans. This technology supports real-time data analysis and decision-making, leading to better patient outcomes and streamlined workflows, thus fueling its adoption among healthcare providers.
Organic and Inorganic Growth Strategies Adopted by Players to Establish Their Foothold in the Market
Players operating in this market are adopting both organic and inorganic growth strategies such as collaborations, acquisitions, and new product launches to garner market share. For instance,
In July 2024, GE HealthCare and Amazon Web Services (AWS) formed a strategic partnership to develop generative AI applications aimed at enhancing medical diagnostics and patient care. GE HealthCare will use AWS’s cloud and AI services to create innovative solutions that improve clinical workflows, diagnostic accuracy, and patient outcomes, accelerating the development and implementation of new healthcare technologies
and formed a strategic partnership to develop generative AI applications aimed at enhancing medical diagnostics and patient care. GE HealthCare will use AWS’s cloud and AI services to create innovative solutions that improve clinical workflows, diagnostic accuracy, and patient outcomes, accelerating the development and implementation of new healthcare technologies In March 2024, Google Cloud integrated its Vertex AI Search with MedLM and Healthcare Data Engine (HDE) to enhance generative AI healthcare services, improving patient record summaries and access to longitudinal data. The updates include expanded HDE access, new MedLM features for chest x-ray classification, and a data mapping tool, aiming to advance AI-driven healthcare solutions while addressing potential issues with AI credibility
In February 2024, CitiusTech launched, the CitiusTech Gen AI Quality & Trust solution, a pioneering solution to enhance the reliability, quality, and trust of generative AI in healthcare, addressing common concerns that delay AI adoption. The solution offers a comprehensive framework with metrics and methods tailored to healthcare, enabling organizations to confidently scale Gen AI applications
In November 2023, Wipro partnered with NVIDIA to enhance healthcare solutions using generative AI, leveraging NVIDIA’s AI Enterprise software for improved member experience, enrolment, and claims processing. This collaboration aims to accelerate the adoption of AI in healthcare, enabling custom AI models and transforming digital and business processes in the industry
The generative AI in Healthcare market is expected to gain further momentum in the coming years due to technological advancements, rising R&D investments, new product launches, and aggressive organic and inorganic growth strategies followed by the players.
Unlock key data with a sample report for competitive analysis:
https://meditechinsights.com/generative-ai-in-healthcare-market/request-sample/
Competitive Landscape Analysis: Generative AI in Healthcare Market
The global generative AI in Healthcare market is marked by the presence of established market players such as Amazon Web Services, Cognizant, Google LLC, IBM Corporation, Meta, Microsoft Corporation, NVIDIA, OpenAI, Oracle Corporation, and Syntegra, among others.
Future Outlook of the Generative AI in Healthcare Market
The global generative AI in Healthcare market is expected to gain further momentum in the coming years due to its abilities to create synthetic datasets that for training machine learning models; enhance patient engagement; streamline processes and improve efficiency; and the growing trend of collaboration between AI developers and healthcare professionals. These factors collectively contribute to the growth and evolution of the generative AI in healthcare market.
About Medi-Tech Insights
Medi-Tech Insights is a healthcare-focused business research & insights firm. Our clients include Fortune 500 companies, blue-chip investors & hyper-growth start-ups. We have completed 100+ projects in Digital Health, Healthcare IT, Medical Technology, Medical Devices & Pharma Services in the areas of market assessments, due diligence, competitive intelligence, market sizing and forecasting, pricing analysis & go-to-market strategy. Our methodology includes rigorous secondary research combined with deep-dive interviews with industry-leading CXO, VPs, and key demand/supply side decision-makers.
Contact:
| 2025-07-07T00:00:00 |
2025/07/07
|
https://www.pharmiweb.com/press-release/2025-07-07/generative-ai-in-healthcare-market-growing-at-36-38-cagr-amid-demand-for-precision-care-by-2029
|
[
{
"date": "2023/01/01",
"position": 87,
"query": "AI healthcare"
},
{
"date": "2023/02/01",
"position": 86,
"query": "AI healthcare"
},
{
"date": "2023/07/01",
"position": 87,
"query": "AI healthcare"
},
{
"date": "2023/08/01",
"position": 86,
"query": "AI healthcare"
},
{
"date": "2023/11/01",
"position": 88,
"query": "AI healthcare"
},
{
"date": "2023/12/01",
"position": 71,
"query": "AI healthcare"
},
{
"date": "2024/01/01",
"position": 90,
"query": "AI healthcare"
},
{
"date": "2024/03/01",
"position": 87,
"query": "AI healthcare"
},
{
"date": "2024/09/01",
"position": 88,
"query": "AI healthcare"
},
{
"date": "2024/11/01",
"position": 86,
"query": "AI healthcare"
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.