{"id":"pm-rice-scores-ranked","audience":"product-managers","category":"data","track":"data","technique":"verification","title":"Rank five features with RICE scores you can check","free":false,"task":"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.","materialLabel":"Your RICE worksheet notes (attached to your prompt automatically)","material":"RICE inputs - Q1 planning (Fieldnote app)\nReach = users per quarter. Impact: 3 massive, 2 high, 1 medium, 0.5 low, 0.25 minimal. Confidence as %. Effort = person-months.\n\nSaved filters - Reach 4,000 / Impact 1 / Confidence 80% / Effort 2\nBulk edit - Reach 1,500 / Impact 2 / Confidence 100% / Effort 3\nOffline mode - Reach 6,000 / Impact 3 / Confidence 50% / Effort 4\nSlack alerts - Reach 3,000 / Impact 0.5 / Confidence 80% / Effort 1\nDark mode - Reach 5,000 / Impact 0.25 / Confidence 100% / Effort 1\n\nThread after the scoring session:\nMarta (eng): Looked at offline mode again. Sync conflicts are worse than we thought. Effort is 6 person-months, not 4.\nJoel (PM): Updated. Use 6 for offline mode.\nAna (design): Dark mode gets asked for in every user group I run, can we bump it?\nJoel: Let's let the scores speak first.\n\nReminder: planning review is Tuesday at 10. Bring laptops.","rules":[{"type":"maxBullets","max":5},{"type":"maxWords","max":110},{"type":"plainText"}],"mistakes":[{"title":"Just asking for the ranking","why":"The AI gives a ranked list or a markdown table without the math, so you can't spot a wrong number.","fix":"Show the shape: \"One line per feature like '- Saved filters: 4000 x 1 x 0.8 / 2 = 1600'.\"","checks":["r2","maxBullets"]},{"title":"Trusting the AI to count words","why":"AI is bad at counting. Ask for a total word limit and it often lands over it.","fix":"Cap each line instead: \"each line under 15 words, just the name and the math.\"","checks":["maxWords"]},{"title":"Missing the updated estimate","why":"The old effort is in the table and the change is buried in a thread, so the AI uses the old number.","fix":"Add: \"Offline mode effort is 6 (the latest estimate), not 4.\"","checks":["r0"]},{"title":"Ranking before scoring","why":"The AI ranks as it goes, and without the numbers in front of it, it often gets the order wrong.","fix":"Add: \"Show all 5 scores first, then end with one line: Ranking: highest to lowest.\"","checks":["r1"]},{"title":"Letting it add advice","why":"The AI tacks on a recommendation paragraph and formatting you didn't ask for.","fix":"Add: \"Output only the 5 lines. Plain text, no tables or bold.\"","checks":["plainText","r2"]}],"promptHints":[{"label":"Asks to show the math","patterns":["show.{0,15}(math|work|calculation|formula)","x .{0,10}x","reach x","\\bx\\b.{0,20}/"]},{"label":"Uses the updated effort","patterns":["\\b6\\b","latest","updated","new estimate"]},{"label":"Sorts by score","patterns":["highest","rank","sort","descending"]},{"label":"Sets the number of lines","patterns":["\\b(5|five)\\b.{0,15}(line|item|feature)"]},{"label":"Asks for plain text","patterns":["plain","no bold","no markdown","no formatting","no headings"]}],"hint":"When AI does math for you, make it show the math so you can check it. Also tell it which estimate is current and to rank only after scoring.","rubricLabels":["Offline mode uses Effort 6, giving a score of 1,500 (not 2,250 from the old estimate of 4)","The final Ranking line lists Saved filters, Offline mode, Dark mode, Slack alerts, Bulk edit in that order","Each feature line shows the multiplication and division before the score (Confidence can be written as 0.8 or 80%), and nothing comes after the Ranking line (no recommendation or commentary)"]}