Library › AI Evals › Marketing and content
Check an AI blog intro against your own survey report
Practice: Catching mistakes and made-up facts. About 5 minutes.
About this exercise
An AI drafted a blog intro from your customer survey report, and every stat has to match before it's published. Write exactly 5 numbered lines, one per claim, each labeled Matches, Wrong or Not in report. For each Wrong line, add the report's figure in quotation marks. Judge only by the report. Plain text, under 100 words.
Common mistakes when you ask AI for this
- Asking for a proofread. The AI fixes commas and style and never checks the numbers against the report. Try: Say: "Label each claim Matches, Wrong or Not in report."
- Letting rounding slide. 'Nearly a month' sounds close enough to the AI, but 18 days isn't. Try: Add: "Wrong includes rounding that changes the meaning."
- No proof for corrections. The AI says a stat is off without giving the real figure. Try: Add: "For Wrong, quote the report's figure."
- A rewritten intro. The AI 'helps' by rewriting the paragraph. Try: Be exact: "Exactly 5 numbered lines, one per claim, nothing else."
What a strong prompt includes
- Gives exact labels
- Makes the report the judge
- Asks for a quote as evidence
- Says exactly how many
- Asks for plain text
Related exercises
- Alert sales to a competitor's price change, facts only (Research & AI Search · Product managers)
- Approve or return expense claims against the policy (Productivity AI · Finance and accounting)
- Approve part of an overtime request with the math (Writing AI · Managers and team leads)
- Catch a chatbot's mistake on your invoice total (Data AI · Freelancers and creators)
- Catch a chatbot's mistakes about a supplier's return policy (Research & AI Search · Small business owners)