How do I give critical feedback in a performance review?

Attach it to a specific occasion and state what the better version would have looked like. Feedback that describes a trait rather than an action gives the person nothing to change, which is why it is received as a personal judgement.

Should AI write performance reviews?

It can structure and phrase them; the judgements must be yours. The examples, the assessment and the decision about what to raise are things only the manager has, and a review written from generic input reads as exactly that.

Which AI model is best for writing a performance review?

All of them handle this; what changes is the packaging. This page shows the same prompt written for Claude, ChatGPT, Gemini. Claude follows XML-delimited structure most reliably, ChatGPT works best with markdown headings, and Gemini prefers the task stated before the material. The content of the prompt is identical in each.

Can I change this prompt for my own situation?

Yes, and you should. Replace the placeholders with your own details, then open it in the builder to add context specific to you. The builder scores what you supply and tells you exactly which missing piece would improve it most.

Why does this prompt include rules I did not ask for?

Because writing tasks carry requirements that experienced practitioners apply automatically and rarely write down. The compiler adds them so the output does not fail on something obvious. Every added rule is listed on the how it works page.

AI prompt for writing a performance review

This is a ready-made AI prompt for writing a performance review, written for Claude and free to copy. Reviews go wrong when feedback is about personality rather than behaviour, because personality feedback cannot be acted on. The banned phrases here are the classic examples: unfalsifiable, and impossible to improve against. The prompt below handles that: it is compiled as a writing task, so it carries the structure and the constraints that kind of work needs.

The prompt

Written for Claude. Compiled as a writing task — producing original prose: articles, essays, stories, letters, and long-form copy.

<role>
You are a senior writer and editor with a decade of experience in this exact form.
</role>

<context>
What they did well, with examples: {{strengths}}. Where they need to improve, with examples: {{development}}. Period covered: {{period}}.
</context>

<task>
Write a performance review for {{name}}, who works as {{role}}.
</task>

<constraints>
- Every judgement must be attached to a specific example from the period.
- Development areas must state what "better" would look like concretely.
- Do not use ratings language you cannot justify with an example.
- Separate behaviour from personality. Review what they did, not who they are.
- Avoid needs to be more proactive.
- Avoid lacks executive presence.
- Avoid attitude.
- When claiming an improvement, state the baseline being improved on and the dimension of the improvement.
- Write in plain, direct prose. Do not restate the prompt, and do not open with a throat-clearing sentence.
- Vary sentence length. Do not begin consecutive sentences with the same word or structure.
- Do not invent facts, statistics, quotations, or attributed opinions.
</constraints>

<output_format>
Respond in Markdown. Use descriptive headings, and keep paragraphs to three sentences or fewer. Length: 500 words. Treat this as a requirement, not a suggestion.
</output_format>

Now, write a performance review for {{name}}, who works as {{role}}.

Open this in the prompt builder to add your own context and see what would improve it most.

What makes writing a performance review hard to prompt for

Reviews go wrong when feedback is about personality rather than behaviour, because personality feedback cannot be acted on. The banned phrases here are the classic examples: unfalsifiable, and impossible to improve against.

Why this prompt works

Background comes before the instruction: The model reads the situation before it learns what to do with it, which stops the instruction being diluted by everything that follows. The task is then restated as the final line, where models weight it most heavily.
Rules a writing task assumes but nobody writes down: Write in plain, direct prose. Do not restate the prompt, and do not open with a throat-clearing sentence. Vary sentence length. Do not begin consecutive sentences with the same word or structure. These are added automatically because leaving them implicit is the most common reason this kind of output disappoints.
Uncheckable words replaced with checkable ones: "better" reads like a requirement but cannot be verified by the model. The prompt swaps it for a property that can be checked, which is the difference between a request and a specification.

What to replace

Placeholder	What to put there
{{strengths}}	Your strengths.
{{development}}	Your development.
{{period}}	Your period.
{{name}}	Your name.
{{role}}	Your role.

Check the output before you use it

Every criticism should name a specific occasion, not a pattern you feel exists.
For each development area, check you have said what doing it well would look like.
Remove anything describing the person rather than their work.

The same prompt for other models

Identical content, packaged the way each model reads most reliably.

ChatGPT

## Role

You are a senior writer and editor with a decade of experience in this exact form.

## Context

What they did well, with examples: {{strengths}}. Where they need to improve, with examples: {{development}}. Period covered: {{period}}.

## Task

Write a performance review for {{name}}, who works as {{role}}.

## Constraints

- Every judgement must be attached to a specific example from the period.
- Development areas must state what "better" would look like concretely.
- Do not use ratings language you cannot justify with an example.
- Separate behaviour from personality. Review what they did, not who they are.
- Avoid needs to be more proactive.
- Avoid lacks executive presence.
- Avoid attitude.
- When claiming an improvement, state the baseline being improved on and the dimension of the improvement.
- Write in plain, direct prose. Do not restate the prompt, and do not open with a throat-clearing sentence.
- Vary sentence length. Do not begin consecutive sentences with the same word or structure.
- Do not invent facts, statistics, quotations, or attributed opinions.

## Output format

Respond in Markdown. Use descriptive headings, and keep paragraphs to three sentences or fewer. Length: 500 words. Treat this as a requirement, not a suggestion.

Now, write a performance review for {{name}}, who works as {{role}}.

Gemini

**Task**

Write a performance review for {{name}}, who works as {{role}}.

**Role**

You are a senior writer and editor with a decade of experience in this exact form.

**Context**

What they did well, with examples: {{strengths}}. Where they need to improve, with examples: {{development}}. Period covered: {{period}}.

**Constraints**

- Every judgement must be attached to a specific example from the period.
- Development areas must state what "better" would look like concretely.
- Do not use ratings language you cannot justify with an example.
- Separate behaviour from personality. Review what they did, not who they are.
- Avoid needs to be more proactive.
- Avoid lacks executive presence.
- Avoid attitude.
- When claiming an improvement, state the baseline being improved on and the dimension of the improvement.
- Write in plain, direct prose. Do not restate the prompt, and do not open with a throat-clearing sentence.
- Vary sentence length. Do not begin consecutive sentences with the same word or structure.
- Do not invent facts, statistics, quotations, or attributed opinions.

**Output format**

Respond in Markdown. Use descriptive headings, and keep paragraphs to three sentences or fewer. Length: 500 words. Treat this as a requirement, not a suggestion.

Now, write a performance review for {{name}}, who works as {{role}}.

Common questions

How do I give critical feedback in a performance review?: Attach it to a specific occasion and state what the better version would have looked like. Feedback that describes a trait rather than an action gives the person nothing to change, which is why it is received as a personal judgement.
Should AI write performance reviews?: It can structure and phrase them; the judgements must be yours. The examples, the assessment and the decision about what to raise are things only the manager has, and a review written from generic input reads as exactly that.
Which AI model is best for writing a performance review?: All of them handle this; what changes is the packaging. This page shows the same prompt written for Claude, ChatGPT, Gemini. Claude follows XML-delimited structure most reliably, ChatGPT works best with markdown headings, and Gemini prefers the task stated before the material. The content of the prompt is identical in each.
Can I change this prompt for my own situation?: Yes, and you should. Replace the placeholders with your own details, then open it in the builder to add context specific to you. The builder scores what you supply and tells you exactly which missing piece would improve it most.
Why does this prompt include rules I did not ask for?: Because writing tasks carry requirements that experienced practitioners apply automatically and rarely write down. The compiler adds them so the output does not fail on something obvious. Every added rule is listed on the how it works page.

Browse all ready-made prompts, the full prompt library, or read the guides.