Check a gala press release against the final event tally

About this exercise

Your board chair drafted a press release about last week's gala, and the final tally from the finance team just came in. You want one numbered line per stat in the release, under 60 words total, labeled Matches, Wrong, or Not in tally, with the tally's figure after any Wrong label. Use only the final tally, plain text, nothing else.

Common mistakes when you ask AI for this

• Using gala-night numbers. The preliminary count is in the tally as a reference, so the AI may treat it as valid. Try: Say: "Use only the final Nov 4 figures."
• Calling history claims wrong. The tally doesn't cover past galas, so 'most successful' can't be checked here. Try: Add: "If the tally doesn't cover it, label it Not in tally."
• Getting a new release. The AI rewrites the release instead of showing what to fix. Try: Say: "Label only, no rewrite."
• Trusting the AI to count words. AI is bad at counting. Ask for a total word limit and it often lands 10-20% over. Try: Cap each line: "each line under 10 words."
• Getting markdown back. AI defaults to bold labels and headings, which show up as stray symbols in an email to your board chair. Try: Ask for "plain text, no bold, no headings."

What a strong prompt includes

• Gives exact labels
• Uses the final figures
• Asks for the tally's figure
• Sets a length limit
• Asks for plain text

Practice this now ↑

Related exercises

• Alert sales to a competitor's price change, facts only (Research AI · Product managers)
• Answer a buyer's HOA questions from the bylaws (Research AI · Real estate agents)
• Answer a coworker's travel policy question in one Slack reply (Research AI · Office and admin)
• Answer a family's visiting questions from the current policy (Research AI · Nurses and healthcare workers)
• Answer winter break housing questions from the current policy (Research AI · College students)