{"id":"lead-retro-summary-memo-headings","audience":"product-managers","category":"leadership-work","track":"leadership","level":"intermediate","technique":"format","title":"Turn retro sticky notes into a one-page memo with headings","free":false,"task":"Turn the raw retro notes into a short memo for the team in plain text. Use exactly these four headings, each on its own line followed by a colon: Went well, Went badly, Patterns, Actions. Keep it under 130 words. Each Action has one owner's first name and a date. Merge duplicate notes, and do not assign anyone who was not named.","materialLabel":"Sprint 14 retro sticky notes (attached to your prompt automatically)","material":"Sprint 14 retro - raw notes\n\nWent well\n- Demo to client was smooth (Ravi)\n- Pairing on the search bug worked (Kim)\n- Demo went great, client loved it (Ravi's pod)\n- Fewer after-hours pings\n\nWent badly\n- Test environment down 2 days\n- QA got builds too late, twice\n- Env was down again Wed-Thu\n- Requirements for the export feature changed mid-sprint\n- Standup too long\n\nIdeas\n- Get a stand-in for the test env owner (Kim volunteered)\n- Freeze requirements by day 2 (Ravi will draft the rule by Nov 15)\n- Builds to QA by Wednesday noon (nobody owns this yet)\n\nJoke note: \"More pizza.\" Ignore.","rules":[{"type":"maxWords","max":130},{"type":"plainText"}],"mistakes":[{"title":"Different headings","why":"The AI uses '## What went well' or other titles.","fix":"Say: \"Exactly these headings with a colon: Went well:, Went badly:, Patterns:, Actions:.\"","checks":["r0"]},{"title":"Repeating duplicates","why":"The AI lists the demo and the env outage twice.","fix":"Say: \"Merge duplicate notes into one item.\"","checks":["r1"]},{"title":"Inventing owners","why":"The AI assigns the unowned action to the PM or the QA lead.","fix":"Say: \"If nobody owns an action, write 'owner needed'.\"","checks":["r2"]},{"title":"Markdown headings","why":"The AI adds # signs and bold.","fix":"Say: \"Plain text, no # and no bold.\"","checks":["plainText"]},{"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 sections: \"each section under 40 words.\"","checks":["maxWords"]},{"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 part instead, for example: \"each line under 12 words.\"","checks":["maxWords"]}],"promptHints":[{"label":"Lists the four headings","patterns":["went well","went badly","patterns","actions"]},{"label":"Merges duplicates","patterns":["merge","duplicate","combine"]},{"label":"Handles owners","patterns":["owner","unowned|no owner","don'?t assign","not named"]},{"label":"Plain text","patterns":["plain text","no #","no bold"]},{"label":"Sets a length","patterns":["under \\d+ words","\\d+ words"]}],"hint":"Tell the AI the exact headings, to merge repeats, and what to do when an action has no owner.","rubricLabels":["Uses exactly the headings Went well:, Went badly:, Patterns: and Actions: as plain-text lines, in that order","Duplicates are merged: the client demo appears once and the test environment outage appears once (as a 2-day or Wed-Thu outage)","Actions give Kim for the test env stand-in and Ravi by Nov 15 for the requirements freeze, and the builds-to-QA action is marked as having no owner yet instead of naming someone"]}