Library › Data AI › Product managers
Rank five features with RICE scores you can check
Practice: Catching mistakes and made-up facts. About 5 minutes.
About this exercise
Your team scored 5 backlog features with RICE, and you need a ranking for planning you can double-check. You want 5 bullet lines, one per feature, each showing the math as 'Reach x Impact x Confidence / Effort = score', then one final line starting 'Ranking:' with the features highest score first. Keep it plain text and under 110 words, and use the latest effort estimate, since one changed after the first round.
Common mistakes when you ask AI for this
- Just asking for the ranking. The AI gives a ranked list or a markdown table without the math, so you can't spot a wrong number. Try: Show the shape: "One line per feature like '- Saved filters: 4000 x 1 x 0.8 / 2 = 1600'."
- 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 15 words, just the name and the math."
- Missing the updated estimate. The old effort is in the table and the change is buried in a thread, so the AI uses the old number. Try: Add: "Offline mode effort is 6 (the latest estimate), not 4."
- Ranking before scoring. The AI ranks as it goes, and without the numbers in front of it, it often gets the order wrong. Try: Add: "Show all 5 scores first, then end with one line: Ranking: highest to lowest."
- Letting it add advice. The AI tacks on a recommendation paragraph and formatting you didn't ask for. Try: Add: "Output only the 5 lines. Plain text, no tables or bold."
What a strong prompt includes
- Asks to show the math
- Uses the updated effort
- Sorts by score
- Sets the number of lines
- Asks for plain text
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)