Check a manager's draft against the policy before it goes out

About this exercise

Review the manager's draft reply to an employee against the policy excerpt. Output exactly three lines: line 1 starts "Verdict:" and is one of Send as is, Edit first, Hold for HR. Line 2 starts "Issues:" and lists each mismatch with the policy section number in under 40 words (or "None"). Line 3 starts "Fix:" with one sentence. Plain text. You are checking consistency only; HR makes the final call.

Common mistakes when you ask AI for this

• Approving the draft. The AI says the kind message is fine. Try: Say: "Check each statement against the numbered policy."
• No section numbers. The AI describes problems vaguely. Try: Say: "Cite the policy section number for each mismatch."
• Extra commentary. The AI writes a long review with praise. Try: Say: "Exactly three lines: Verdict:, Issues:, Fix:."
• 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

• Three labeled lines
• Allowed verdicts
• Section numbers
• Policy only
• Word cap

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)