Check draft review comments for vague or biased wording

About this exercise

Check the manager's five draft review comments and return a table with the header Comment | Problem | Neutral rewrite. One row per comment, same order. Problem is exactly one of: Vague, Personality label, Personal trait, OK. Neutral rewrite is exactly "Add a dated example" for Vague and Personality label rows, exactly "Remove" for Personal trait rows, and exactly "No change" for OK rows. Do not rate or rank the employee, and do not suggest a rating. Plain text. The manager and HR make the final call.

Common mistakes when you ask AI for this

• Wrong labels. The AI invents its own categories. Try: Say: "Problem is exactly one of Vague, Personality label, Personal trait, OK."
• Rating the employee. The AI suggests a score or comments on the assignment. Try: Say: "Do not rate, rank or suggest a rating."
• Different table. The AI adds columns or merges rows. Try: Say: "Header exactly Comment | Problem | Neutral rewrite, five rows in order."
• Trusting the AI to count words. AI is bad at counting. Ask for a total word limit and it often lands over it. Try: Cap each part instead, for example: "each line under 15 words."
• Markdown. The AI bolds words or adds headings. Try: Say: "Plain text, no bold, no headings."

What a strong prompt includes

• Exact header
• Allowed labels
• Fixed rewrite text
• No rating
• One row per comment

Practice this now ↑

Related exercises

• Accrue unpaid wages for the working days after the last pay period (Finance AI · Accountants)
• Acknowledge an employee's concern without promising outcomes (People & HR AI · HR and recruiting)
• Age a returns queue in business days and flag the ones over the limit (Customer Support & Success AI · Customer support teams)
• Alert sales to a competitor's price change, facts only (Research & AI Search · Product managers)
• Announce a colleague's departure neutrally to the team (People & HR AI · Managers and team leads)