{"id":"cs-pilot-conversion-criteria-extension-lines","audience":"customer-success","category":"support-work","technique":"verification","track":"support","level":"advanced","title":"Judge a pilot against its start-of-pilot criteria","free":false,"task":"Judge the pilot in three lines: \"Criterion 1:\", \"Criterion 2:\" and \"Recommendation:\". Each criterion ends with Pass or Fail with the math or count shown. The recommendation follows the outcome rules exactly. Use the average across all four weeks, not the last week. Plain text, under 100 words. The CSM and AE decide.","materialLabel":"Your material (attached to your prompt automatically)","material":"PILOT AGREEMENT (set Oct 5, Maple Logistics, 30 days, 10 pilot users)\nCriteria to convert to a paid plan:\n1. Average weekly-active rate across the 4 weeks is 70% or higher.\n2. At least 2 integrations are connected and syncing by day 30.\nOutcome rules: both met = offer conversion; exactly one met = offer one 2-week extension; neither met = close the pilot.\n\nRESULTS\nWeekly-active rate by week: week 1 52%, week 2 64%, week 3 72%, week 4 78%.\nIntegrations syncing at day 30: CRM and billing (2).\nThe AE says: \"Week 4 hit 78%, that's the number that matters. Let's convert.\"\nPilot users: 10; no one dropped out.","rules":[{"type":"plainText"},{"type":"maxWords","max":100}],"mistakes":[{"title":"Using the last week","why":"The AI follows the AE and uses 78%.","fix":"Say: \"Use the average across all four weeks.\"","checks":["r1","r2"]},{"title":"Converting anyway","why":"The AI recommends conversion because trends are positive.","fix":"Say: \"Follow the outcome rules exactly: exactly one met = a 2-week extension.\"","checks":["r2"]},{"title":"No math shown","why":"The AI writes Pass or Fail only.","fix":"Say: \"Show the math or count on each criterion.\"","checks":["r1"]},{"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"]},{"title":"Trusting the AI to count words","why":"The AI runs long and cannot count its own words.","fix":"Cap each part (\"each line under 12 words\") and add \"under N words in total\".","checks":["maxWords"]},{"title":"Leaving a requirement unstated","why":"The AI follows its own defaults unless the prompt spells this out.","fix":"State it plainly in your prompt: the output has three lines starting 'Criterion 1:', 'Criterion 2:' and 'Recommendation:' with no other text.","checks":["r0"]}],"promptHints":[{"label":"Names the three labels","patterns":["criterion 1","criterion 2","recommendation"]},{"label":"Average across weeks","patterns":["average","all four weeks","not the last"]},{"label":"Follows outcome rules","patterns":["outcome rules","exactly one","extension"]},{"label":"Shows the math","patterns":["math","count","shown"]},{"label":"Asks for plain text","patterns":["plain","no bold","no markdown","no formatting","no headings"]},{"label":"Sets a word cap","patterns":["\\d+\\s*words","under \\d+","word"]}],"hint":"Pilot decisions should follow the criteria agreed at the start. Tell the AI to use the stated metric, show the math and ignore pressure.","mission":"Judge whether the pilot met its start-of-pilot criteria.","musts":["Average all four weeks","Show math or count","Follow outcome rules exactly"],"rubricLabels":["The output has three lines starting \"Criterion 1:\", \"Criterion 2:\" and \"Recommendation:\" with no other text","Criterion 1 is Fail with the average (52 + 64 + 72 + 78) / 4 = 66.5% against 70%, and Criterion 2 is Pass with 2 integrations (CRM and billing)","The Recommendation is to offer one 2-week extension because exactly one criterion is met, not to convert"]}