Library › Data AI › Managers and team leads
Total candidate scorecards and pick who advances
Practice: Catching mistakes and made-up facts. About 5 minutes.
About this exercise
Three candidates finished panel interviews, and you need to pick two for the final round. Write exactly 3 numbered lines, one per candidate in the order listed, each showing the score math as 'a + b + c + d = total', then one final line starting 'Advance:' naming the two highest totals, plain text, under 70 words. Use the corrected score.
Common mistakes when you ask AI for this
- Asking 'who should advance'. The AI gives a pick and a paragraph without the math. Try: Show it: "1. Priya: 4 + 3 + 4 + 3 = 14".
- 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 line instead: "each line under 12 words."
- Using the wrong score. Marcus's original score appears first, with the correction below it. Try: Add: "Marcus's data use is 4 (corrected)."
- Opinions and pick first. The AI repeats panel impressions and states the pick before the numbers. Try: Add: "Advance line last. No panel chatter. Plain text."
What a strong prompt includes
- Asks to show the math
- Uses the correction
- Puts the pick last
- Ignores chatter
- Sets a word limit
Related exercises
- Alert sales to a competitor's price change, facts only (Research AI · 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)
- Average daily call activity after fixing a dialer glitch (Data AI · Sales and customer success)
- Average handle times after removing outage calls (Data AI · Customer support teams)