Library › Data AI › Business analysts
Find the problems in a weekly metrics draft before it ships
- For Business analysts
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Advanced
About this exercise
You're reviewing a draft weekly metrics report before it goes to the leadership team. Write a checklist of the problems you can prove from the notes, each as a line starting '- [ ] Metric name:' then the problem and the number that shows it. At most 5 lines, plain text, under 130 words. Don't list items that are fine.
Common mistakes when you ask AI for this
- Listing every metric. The AI comments on all metrics including delivery time, which is fine. Try: Add: "List only problems provable from the notes; skip anything that checked out."
- Vague problems. The AI says 'data may be inconsistent' with no number. Try: Add: "Each line: metric, problem, and the number that shows it."
- Long unformatted review. The AI writes headings and paragraphs of advice. Try: Add: "At most 5 lines starting '- [ ]'. No intro or fixes."
- Leaving the format to chance. The AI picks its own length and layout unless told the exact shape. Try: Add: "At most 5 bullets. Plain text, no bold or headings."
- 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
- Asks for a checklist shape
- Names the issues
- Asks for numbers
- Says what to skip
- Caps length
Related exercises
- Accrue unpaid wages for the working days after the last pay period (Finance AI · Accountants)
- 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)
- Annualize recurring revenue without the one-time fee (Data AI · Finance and accounting)
- Answer a credit dispute with the full-hour rule and the math (Customer Support & Success AI · Customer support teams)