Rewrite a review draft to remove loaded language and list the changes

About this exercise

Rewrite the manager's draft feedback so it describes behavior and facts only, with two labeled parts on their own lines: Rewrite: (plain text, 3 sentences, keeping every dated fact) and Changed: (exactly 3 dash bullets, each "original phrase -> replacement" using phrases from the draft). Remove personality labels and gendered or emotional terms. Keep the two missed deadlines and the 3 interruptions. End with the exact line: HR reviews before sending. Plain text, under 150 words.

Common mistakes when you ask AI for this

• Keeping loaded terms. The AI keeps "assertive" or "emotional". Try: Say: "Remove personality labels and gendered or emotional terms."
• Losing the facts. The AI softens until the dates disappear. Try: Say: "Keep every dated fact and number."
• Vague changes list. The AI describes changes in prose. Try: Say: "Exactly 3 dash bullets: original phrase -> replacement."
• Missing HR line. The AI ends with a tip. Try: Say: "End with the exact line HR reviews before sending."
• Markdown. The AI bolds labels. Try: Say: "Plain text."
• 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."

What a strong prompt includes

• Two labeled parts
• Keep facts
• Remove loaded language
• Changes format
• HR line

Practice this now ↑

Related exercises

• Accrue unpaid wages for the working days after the last pay period (Finance AI · Accountants)
• Acknowledge a director's critical feedback without defensiveness (Leadership AI · Executives)
• 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 CFO departure in three plain sentences (Leadership AI · Executives)