Library › Data AI › HR and recruiting
Summarize rating distribution with the percentages shown
Practice: Catching mistakes and made-up facts. About 5 minutes.
About this exercise
You're summarizing the performance rating distribution for the leadership calibration meeting. Write exactly 3 numbered lines, one per rating, each showing the math as 'count / total = percent' rounded to the nearest whole percent, then one line comparing against the guideline, plain text, under 60 words. Use the corrected counts.
Common mistakes when you ask AI for this
- Asking for 'a summary'. The AI gives percentages without the math, so leaders can't check them. Try: Show it: "1. Exceeds: 12 / 80 = 15%".
- 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 old counts. The first counts appear before the correction. Try: Add: "Use the corrected counts: 12, 62, 6."
- Skipping the comparison. The AI lists numbers but doesn't say how they compare to the guideline. Try: Add: "End with one line comparing Exceeds to the 10-20% guideline. Plain text."
What a strong prompt includes
- Asks to show the math
- Uses the corrected counts
- Compares to the guideline
- Sets the number of lines
- 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)