{"id":"dat-pm-rice-score-reestimate","audience":"product-managers","category":"decisions","technique":"verification","title":"Rescore a feature backlog with RICE after a new estimate","free":false,"task":"You're picking next quarter's first build using RICE (reach x impact x confidence ÷ effort). Write exactly 4 numbered lines, one per feature, each showing the math and score, then one unnumbered last line: Build first: [feature]. In this morning's standup, engineering re-estimated Slack alerts at 1.5 person-weeks (the sheet isn't updated yet). Ignore opinions that aren't in the scoring, plain text, under 90 words.","materialLabel":"Backlog sheet and notes (attached to your prompt automatically)","material":"Q1 CANDIDATES - RICE inputs (product sheet, Nov 3)\n\nFeature | Reach (users/qtr) | Impact (1-3) | Confidence | Effort (person-weeks)\nBulk export | 2,000 | 2 | 80% | 4\nDark mode | 5,000 | 1 | 100% | 5\nSlack alerts | 1,500 | 3 | 50% | 3\nCustom roles | 800 | 3 | 80% | 6\n\nNotes:\n- Eng estimates last updated Oct 20.\n- The CEO keeps asking about custom roles for the Halvorsen deal.\n- Design says dark mode is \"basically free\" but it's still 5 weeks in the sheet; no new estimate.\n- Support tickets mentioning export: 38 this month.\n- Q1 planning meeting is next Wednesday.\n- Reach estimates come from analytics.\n- Shared with the team in the usual folder.","rules":[{"type":"numberedItems","count":4},{"type":"plainText"},{"type":"maxWords","max":90}],"mistakes":[{"title":"Using the old estimate","why":"The AI scores Slack alerts on 3 weeks and picks Dark mode.","fix":"Add: \"Slack alerts effort is now 1.5 weeks, per today's standup.\"","checks":["r0","r2"]},{"title":"Not asking to see the work","why":"Without the math you can't spot a slipped decimal.","fix":"Add a line to copy: \"1. Bulk export: 2,000 x 2 x 0.8 ÷ 4 = 800\"","checks":["r1","numberedItems"]},{"title":"Letting opinions in","why":"The AI weighs the CEO's ask or design's hunch into the pick.","fix":"Add: \"Pick on score only. Ignore opinions not in the inputs.\"","checks":["r2"]},{"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: \"each line under 16 words.\"","checks":["maxWords"]},{"title":"Forgetting where it goes","why":"AI loves markdown tables and bold, which show up as clutter in a planning doc comment.","fix":"Add: \"Plain text, no bold, headings or tables.\"","checks":["plainText"]}],"promptHints":[{"label":"Uses the new estimate","patterns":["1\\.5","re-?estimat","latest|new estimate","eng"]},{"label":"Defines the score","patterns":["rice","reach.{0,20}impact","÷|divid"]},{"label":"Asks to show the math","patterns":["show (the |your )?(math|work)","x \\$|\\bx\\b.{0,10}=","calculation","step"]},{"label":"Asks for the pick last","patterns":["build first","then (pick|name)","last line"]},{"label":"Asks for plain text","patterns":["plain","no bold","no markdown","no formatting","no (headings|tables)"]}],"hint":"One input changed after the sheet was made, and only you know it. Tell the AI the new estimate and ask it to show every score before it picks.","rubricLabels":["Slack alerts uses the new 1.5-week effort: 1,500 x 3 x 0.5 ÷ 1.5 = 1,500","The other scores are shown with their math and correct: Bulk export 800, Dark mode 1,000, Custom roles 320","The last line picks Slack alerts, after the score lines, and the pick is not swayed by the CEO request or design's 'basically free' comment"]}