Check review comments for consistent wording about the same behavior

About this exercise

Four draft review comments describe the same behavior: one late deliverable each. Output a table with the header Name | Label | Neutral rewrite. Label is Neutral if the comment states a specific behavior with a date or count, and Loaded if it describes character or uses vague words like always. For Loaded comments, write a rewrite under 14 words that states the behavior with the date from the facts; for Neutral comments write a dash. Last line, exactly: HR reviews before sending. Plain text, under 120 words.

Common mistakes when you ask AI for this

• Rewriting neutral comments. The AI rewrites all four. Try: Say: "For Neutral comments write a dash."
• Keeping character words. The AI keeps unreliable or careless. Try: Say: "State the behavior with the date from the facts."
• Using the wrong facts. The AI invents dates. Try: Say: "Use the dates from the project tracker facts."
• Wrong labels. The AI invents labels like Mild. Try: Say: "Label is Neutral or Loaded."
• 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

• Gives the header
• Defines the labels
• Dash for neutral
• Uses the tracker facts
• Closing 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)