Summarize a hotline report neutrally for the ethics chair

About this exercise

Summarize the hotline call notes for Ethics Committee chair Rosa Delgado. Plain text, exactly four labeled lines in this order: Allegation:, Where:, Timing:, Needs from compliance:. Under 80 words. Start Allegation: with the word Alleged. Refer to the accused person by job title only, never by name. Do not include the caller's guess about motive or anything that identifies the caller. Do not say whether the allegation is true.

Common mistakes when you ask AI for this

• Naming people. The AI includes the supervisor's and the caller's names. Try: Say: "Job title only for the accused. Nothing that identifies the caller."
• Repeating speculation. The AI repeats the caller's guess about motive. Try: Say: "Leave out the caller's opinions about motive."
• Missing facts. The AI skips the case number, dock or timing. Try: Say: "Include case id, location and timing."
• Free-form summary. The AI writes a paragraph with its own headings. Try: Say: "Four labeled lines in this 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

• Four labels
• Starts Alleged
• Job title only
• Protect the caller
• Neutral

Practice this now ↑

Related exercises

• Announce a delay to three audiences with different limits (Leadership AI · Communications and PR)
• Announce one feature separately to admins and to end users (Customer Support & Success AI · Customer success managers)
• Answer "we'll build it ourselves" with their own numbers (Sales AI · Sales and customer success)
• Answer "what does a CSM do for us?" in plain spoken words (Customer Support & Success AI · Customer success managers)
• Answer a business owner's contract questions or send to legal (Legal & Compliance AI · Legal teams)