Performance Review
Performance Review That Is Fair
Turn notes into a balanced review: evidence, impact, and next-cycle goals - no surprise attacks.
The Prompt
performance-review-that-is-fair.md
Write a performance review from evidence, not mood. Person / role: {{role}} Cycle: {{cycle}} Manager notes (wins, misses, quotes): {{notes}} Goals from last cycle: {{last_goals}} Rating scale we use: {{scale}} Write: 1. Summary paragraph 2. What went well - each point tied to a note or outcome 3. Where to grow - each point with an example, not a trait attack 4. Rating suggestion on {{scale}} with a one-line rationale 5. 3 goals for next cycle (observable, dated) Rules: - Do not invent metrics. - Do not use "always" / "never". - If notes are only negative or only glowing, say the packet is incomplete before drafting.
Negative prompt
Included when you copy the prompt
Do not invent metrics, quotes, or outcomes not in the notes. Do not use always/never. Do not attack personality traits; tie growth points to examples. If notes are one-sided, flag the incomplete packet before drafting.
Fill in your details below - this prompt updates as you type, then copy it.
Fill in your details
0 of 5 filled. Preview updates as you type - then copy the finished prompt (negative prompt included when present).
performance-review-that-is-fair.md
Prompt preview
Write a performance review from evidence, not mood. Person / role: {{role}} Cycle: {{cycle}} Manager notes (wins, misses, quotes): {{notes}} Goals from last cycle: {{last_goals}} Rating scale we use: {{scale}} Write: 1. Summary paragraph 2. What went well - each point tied to a note or outcome 3. Where to grow - each point with an example, not a trait attack 4. Rating suggestion on {{scale}} with a one-line rationale 5. 3 goals for next cycle (observable, dated) Rules: - Do not invent metrics. - Do not use "always" / "never". - If notes are only negative or only glowing, say the packet is incomplete before drafting.
Examples
Example input
Role: Maya Chen, Product Designer. Cycle: H1 2026. Notes: Shipped checkout redesign (conversion +2.1%); missed two design-system deadlines; peer praise for critique facilitation. Last goals: Own checkout UX; document components. Scale: Exceeds / Meets / Needs improvement.
What you should get
A balanced review: summary, evidence-tied wins (checkout lift), growth areas with examples (deadline misses), Meets rating with rationale, and three dated next-cycle goals - no invented metrics or always/never language.
When to use this prompt
Use it when
- You need help with managers.
- You need help with hrbps.
Skip it when
- You only need a one-line ask with no constraints, format, or context.
- You cannot supply the fill-in details the template asks for.
- A different category or tool-specific workflow fits the job better.
How to get a good result
Done when
A balanced review: summary, evidence-tied wins (checkout lift), growth areas with examples (deadline misses), Meets rating with rationale, and three dated next-cycle goals - no invented metrics or always/never language.
Common mistakes
- Leaving role, cycle, notes vague - the model then invents placeholders.
- Asking ChatGPT or Claude for a shorter answer after a long structured prompt - that throws away the format rules.
- Stopping when the first draft appears instead of checking it against the success criteria below.
FAQ
- What do I fill in before I copy this prompt?
- Replace these placeholders with your details: role, cycle, notes, last_goals, scale. Required fields are marked on the page. The prompt text updates as you type.
- Which AI tools is this prompt written for?
- It works best with ChatGPT, Claude. Copy the filled prompt and paste it into the tool you already use.
- What should a good result look like?
- A balanced review: summary, evidence-tied wins (checkout lift), growth areas with examples (deadline misses), Meets rating with rationale, and three dated next-cycle goals - no invented metrics or always/never language.
- What are common mistakes with this prompt?
- Leaving role, cycle, notes vague - the model then invents placeholders. Asking ChatGPT or Claude for a shorter answer after a long structured prompt - that throws away the format rules. Stopping when the first draft appears instead of checking it against the success criteria below.
Best for
- Managers
- HRBPs
Related Prompts
More prompts like this — same topic and style.