Using AI to Write Performance Reviews: Everything You Need to Know

Artificial intelligence (AI) has transformed the workplace, and performance reviews are no exception. AI helps take manual work out of the review process, reducing the time you spend making sense of scattered notes or looking back over past conversations. 

Take the Lattice AI Agent. By quickly summarizing past feedback, one-on-one conversations, goals, and the review history of each team member, the Lattice AI agent can quickly surface all the context needed for thoughtful, productive reviews, saving managers and employees time. Then, Lattice Writing Assist helps make tailored improvements, tone adjustments, and more. 

Here’s how Lattice AI can help write performance reviews filled with genuine, specific, and useful content. 

How Generative AI Can Help With Performance Reviews

Performance reviews take time. But they’re also a defining factor of employee engagement and retention. Lattice’s 2025 State of People Strategy Report found that 74% of managers agree that these reviews are very helpful or critical for getting the most out of their teams. 

But the information overload associated with these reviews is becoming a real issue. The same report found that 49% of managers find it challenging to review a year’s worth of feedback, and 42% find the performance review process a burden.

The answer to lifting that burden, at least a little? AI. 

“AI can be a game-changer for performance reviews, making them quicker to write and more impactful,” said Theresa Fesinstine, an HR executive turned AI educator for HR teams and founder of peoplepower.ai. “Instead of spending hours trying to find the right words, AI can give you a solid starting point, offering up varied and specific phrases. So, when you're giving a shout-out to multiple employees for being team players, AI can help you say it in different ways. That keeps your praise fresh and makes each person feel uniquely valued.”

Creating this solid starting point can save managers and employees a significant amount of time. But generative AI can also be used to improve on that starting point and further streamline the performance review process by:

• Diversifying language 
• Offering meaningful vocabulary
• Prompting ideas for key competencies 
• Tailoring the tone and format of reviews 
• Suggesting employee development plans 
• Increasing the speed of writing each review
• Detecting bias or inconsistencies in review language
• Generating employee goals based on defined criteria
• Tracking feedback themes for each employee over time 
• Helping employees summarize their achievements and goals 
• Developing personalized learning plans for career progression 
• Aligning employee impact with company values or strategic goals 
• Putting together summaries and identifying trends in performance data collected throughout the year

Nathan Deily, cofounder and chief people officer of nth Venture, mentioned that most of us have already learned that generative AI is useful for completing a specific portfolio of tasks when it’s given the right kind of focus and instructions. But it does need to be used in the right way. 

How Not to Use AI-Powered Performance Reviews 

Imagine finding out your individual performance review wasn’t written by your manager, but by AI. That’s one surefire way to harm trust, motivation, and employee engagement (not to mention self-esteem). 

The key to the ethical use of AI within the review process is “to think of AI as your assistant, not your replacement,” recommended Fesinstine. She added that while AI can give us a helping hand, it can’t — and shouldn’t — do all the work. “Using it to spit out generic, one-size-fits-all feedback won’t do your team any favors,” she cautioned. 

Managers and employees shouldn’t ever rely on AI to create a complete performance review, but it can be used as a starting point if you’re unsure how to structure things or are facing writer’s block. This can then be edited and adjusted as necessary because, as Fesinstine noted, “a performance review is a chance for real talk about how someone is doing, and that requires human insight.”

But, given the right prompts, generative AI can form part of an effective performance management system. 

AI Prompts for Managers and Employees

AI doesn’t just spit out the perfect response on the first attempt. The quality of AI output depends on the quality of your input, so for the best results, it pays to develop a range of detailed prompts. 

Prompts Managers Can Try

If you’re ready to use AI when writing performance reviews, Fesinstine suggested the first step is to keep an ongoing bulleted list of successes and challenges for each member of your team. 

“Then, in order to get the most out of AI tools like ChatGPT and Claude 2, the trick is in asking the right questions,” she said. Fesinstine recommended managers try the following prompt to kick things off:

• How can an employee improve in areas such as teamwork? Take into account that they were coached on Y feedback this year.

At Lattice, we also suggest the following prompts:

• Using the following employee traits [list traits here], offer alternative vocabulary, using a positive tone. 
• Check these comments about five different employees [insert comments here] for signs of unconscious bias. Highlight any patterns relating to assumptions, inequitable treatment, or gendered language. 
• Analyze this employee’s top achievements [list them here] and identify any key themes that emerge. Which hard and soft skills are most evident, and which may need development? 
• I want to give actionable feedback that balances praise and constructive input. Based on these successes and challenges [insert bulleted list here], help me create notes for a performance review that includes both and uses a supportive tone of voice. 
• These are the goals my team member set at the start of this review cycle [insert goals here], and here’s their progress toward each goal [insert progress here]. Help me write a summary that evaluates their progress and highlights whether their current approach is working. 

“These kinds of questions can guide the AI to give you more targeted and useful feedback that you can then tailor further,” explained Fesinstine. Tools like Lattice AI also help managers streamline the review writing process, pulling insights from metrics like goal completion, peer recognition, past performance, and more. 

{{rich-highlight-1}}

Prompts Employees Can Try

AI isn’t just for managers. It’s also a great way for employees to prepare for their reviews, using prompts like these as a starting point:

• Help me reflect on my career growth over the last year. Here’s my job description [insert], and some challenges I worked hard to overcome [add examples here]. Please turn this into a summary I can include in my self-evaluation. 
• Turn this bulleted list of successes into a narrative account of my accomplishments, making sure to highlight any key themes. [Add list here.]
• I’m preparing for a performance review with my manager. Based on this list of achievements [add list here], create a summary of my year, including any key themes or strengths. 
• I’ve worked at my company for Y years. Last year, my performance feedback included [add specific details here]. Using this information, create a list of questions my manager might ask me, and some I can ask them. 
• My current job title is X with a salary of Y, and I want to work toward Z. Here are my accomplishments [add them here]. Write a request for a promotion, including reasons why I should be considered. 

Remember that good prompts need good data.

Using AI systems might initially seem like a way to save time, but it still requires a significant amount of data collection. To avoid generating boring or ambiguous responses, it’s worth experimenting with your prompts. Try adding as much detail as possible, but stick to clear and concise language. 

As Deily noted, employee performance reviews are a particularly challenging domain for generative AI to work well in: “There is a lot of very specific context and nuance to be considered in what is often a very subjective process.”

Here’s an example of a generic prompt that falls short, plus a more detailed prompt designed to get better results. 

❌ Help me write a performance review for [Name of team member].

Why it’s not helpful:

• Vague: The prompt doesn’t include any details about the person’s role or recent accomplishments.
• Compromises privacy: The prompt includes the employee’s name, which isn’t recommended unless using an internal, GDPR-compliant AI tool.

✅ Write a performance review summary for employee X, a [insert job title here]. During this performance review cycle, they [insert key achievements here, for example: mentored a new team member, improved our customer satisfaction score by Y%, and created new email templates and call scripts]. Challenges to mention include [insert key details here, for example, occasionally struggling with project management, and building confidence in presenting updates to our leadership team]. 

Why it’s helpful:

• Detailed: Including the employee’s job title gives a foundation for the AI, while listing successes and challenges results in better, more personalized output. 
• Respects privacy: The prompt doesn’t include any identifying information and protects confidentiality.

Without the right data and detailed prompts, AI may be less of a helpful assistant and more of a potential risk. 

Risks to Watch for When Using AI to Write Performance Reviews 

AI is great, but it still needs human oversight. That means human resources leaders and legal teams need to carefully consider the risks and how to reduce the chances of those risks impacting their people. 

Bias

“Watch out for biases in the language the AI might use — it’s only as unbiased as the data it was trained on,” highlighted Fesinstine.

This is well illustrated in a 2023 experiment by Textio: It found that when ChatGPT was prompted to write feedback for specific job titles, the results often showed gender bias. For example, ChatGPT used “she” 90% of the time when writing a review for a receptionist, and it used “he” in 100% of reviews generated for a construction worker. 

For other roles, including doctors and lawyers, the feedback was completely gender-neutral. When prompts included gendered pronouns, ChatGPT tended to write longer feedback for female employees, and generally, the additional feedback was critical. 

Privacy 

“Be cautious about privacy,” warned Fesinstine. “Do not include specific names of employees or any other personally identifiable information.” 

While tools like Lattice AI Agent comply with the highest standards of data privacy and security, information entered into other generative AI tools like ChatGPT and Google Gemini won’t necessarily be protected by your company’s data protection regulations. 

If in doubt, follow these best-practice tips.

🔒AI Prompt Privacy Tips

✅ Do

• Follow your company’s AI policy
• Use job titles instead of full names

❌ Don’t

• Use any confidential details or documents 
• Use full names or any other identifying information, like employee ID numbers

Misuse of Intellectual Property 

Generative AI is trained using data lakes — huge collections of information pulled from a wide range of sources. But often, the intellectual property owners of this information haven’t consented to it being used in this way. If the AI tool you’re using creates performance review comments based on examples from a copyrighted book, that may be considered copyright infringement.

Because AI-driven technology is still relatively new, the legal implications of using it in this way are still being established. If possible, check that the provider of any tool you’re using can confirm it was trained using open-source, non-copyrighted content. 

Distrust 

If managers aren’t open about using AI during the employee evaluation process, the trust between managers and their teams may be negatively affected. Employees may be discouraged or upset if they discover their performance appraisal wasn’t written by their manager, but by AI. 

A 2021 article on the effects of using and disclosing AI-generated performance feedback found that AI feedback tends to improve employee performance more than human feedback does, but only when an employee doesn’t know the feedback was generated by AI. When this information is disclosed, job performance decreases, and employees tend to trust the quality of feedback to a lesser degree.

What can HR leaders do to ensure the responsible use of AI?

It’s no longer a question of whether AI is used during performance evaluations, but how it’s used. That means it’s up to senior leadership teams and HR professionals to shape what that might look like at their company. 

One of the best ways to achieve this is by developing a comprehensive AI policy, with guardrails to guide appropriate use. 

“HR has the opportunity to play a lead role in the rollout and utilization of AI — in the drive of efficiency, creativity, and risk mitigation,” said Fesinstine. She recommended having clear rules around what’s okay and what’s not when it comes to using AI at work. “Training sessions can help everyone get up to speed on how to use AI responsibly. And don't just set it and forget it — keep an eye on how things are going with regular checks,” she said. 

Deily added that HR’s role here should be “to reinforce the importance of the performance management task, provide some clarity on the applicability (or lack thereof) of certain AI tools, and caution against the frightening scenario of having an employee find out that their manager cared so little about them and their review that they punted the task to ChatGPT.”

Developing Policies for the Responsible Use of AI at Work

An AI usage policy outlines clear, value-based guidelines for the responsible use of AI. Consider including sections covering:

• Ethical guidelines 
• Usage guidelines 
• Data privacy and protection
• Development and acquisition 
• Training and awareness
• Monitoring and compliance 
• Reporting and whistleblowing

Before publishing an AI usage policy, always consult legal counsel to ensure it complies with relevant laws and regulations. 

{{rich-highlight-3}}

Ensuring a Fair and Accurate AI-Powered Performance Review Workflow: A Manager’s Checklist

If you’re keen to use AI within the review process, we recommend you:

• Check (and follow) your company’s policy on the use of AI, which may include restrictions on its use.
• Talk to your team about how you can all use AI responsibly during reviews and what this might look like. 
• Leverage AI to build on your feedback, not just to create something vague from scratch.
• Double-check all AI outputs with a human eye. 
• Ask for employee feedback, thoughts, and opinions regularly.
• Improve or adjust your process as necessary.

{{rich-highlight-2}}