{"id":"cs-feedback-rank-by-arr-not-count","audience":"managers","category":"support-work","technique":"verification","track":"support","level":"intermediate","title":"Rank product requests by total ARR instead of account count","free":false,"task":"Rank the top 3 requests for the product team by total ARR of the accounts asking, highest first. Exactly three numbered lines formatted \"1. Request: $X ARR (N accounts)\". Add up the ARR yourself. Plain text, nothing else.","materialLabel":"Your material (attached to your prompt automatically)","material":"FEEDBACK BY REQUEST, Oct (ARR of each asking account)\nSSO enforcement: Acme $40,000; Bolt $30,000; Cora $20,000.\nCSV export: Dune $35,000; Echo $25,000.\nMobile app: Halo $200,000.\nDark mode: Fable $10,000.\n\nAE comment: 'SSO is the most requested, so it should be number 1.' (It is the most requested by count, not by ARR.)\nThe product manager, Lucia, prioritizes by revenue at stake. The request names are as written above.\n\nCONTEXT: These counts come from the October feedback log, where each account is listed once per request even if it raised it several times. ARR figures are the current annual contract values from the CRM. Lucia will take the top three to the Monday planning meeting and wants the ARR total visible so nobody has to add it up. Accounts that asked for more than one thing appear only under the request they called most important.","rules":[{"type":"numberedItems","count":3},{"type":"plainText"}],"mistakes":[{"title":"Ranking by count","why":"The AE comment pushes the AI to rank SSO first.","fix":"Say: \"Rank by total ARR, not by number of accounts.\"","checks":["r1"]},{"title":"Adding wrong totals","why":"The AI misadds the ARR.","fix":"Say: \"Add up the ARR of each request yourself.\"","checks":["r1"]},{"title":"Wrong line format","why":"The AI adds a fourth item or writes prose.","fix":"Say: \"Top 3 only, formatted 1. Request: $X ARR (N accounts).\"","checks":["r0","r2"]},{"title":"Leaving the list shape open","why":"The AI picks its own number of items and its own layout.","fix":"Show the shape: \"exactly N numbered lines like: 1. Label: detail\".","checks":["numberedItems"]},{"title":"Getting markdown back","why":"AI adds bold and headings by default, which show up as stray symbols where this is pasted.","fix":"Say \"plain text, no bold, no headings, no asterisks\".","checks":["plainText"]}],"promptHints":[{"label":"Fixes the number of lines","patterns":["\\b\\d+\\b.{0,15}(lines|items|numbered)","numbered","exactly \\d+"]},{"label":"Asks for plain text","patterns":["plain","no bold","no markdown","no formatting","no headings"]},{"label":"Ranks by ARR","patterns":["by arr","total arr","revenue"]},{"label":"Shows the line format","patterns":["\\$x arr","n accounts","1\\."]}],"hint":"Ranking depends on the metric. Say to rank by total ARR, to add it up, and give the line format.","rubricLabels":["The output has exactly three numbered lines formatted like 1. Request: $X ARR (N accounts)","The ranking is 1. Mobile app: $200,000 ARR (1 account), 2. SSO enforcement: $90,000 ARR (3 accounts), 3. CSV export: $60,000 ARR (2 accounts)","Dark mode is not included, and SSO is not ranked first"]}