{"id":"cs-onboarding-risk-ranking-points","audience":"managers","category":"support-work","technique":"verification","track":"support","level":"advanced","title":"Rank onboarding accounts by risk points with tie-breaks","free":false,"task":"Rank the five accounts by risk points. Output a table with the header row exactly \"Rank | Account | Points\" and five rows. Points follow the rules in the notes, including their exact boundaries. Ties are broken by higher ARR first. Plain text, under 60 words, table only.","materialLabel":"Your material (attached to your prompt automatically)","material":"ONBOARDING RISK POINTS\n+2 if the kickoff happened MORE than 14 days after signing.\n+2 if FEWER than 50% of users are trained.\n+3 if the sponsor has not replied for 10 or MORE days.\n+3 if the integration is blocked.\nHigher points = higher risk. Tie-break: higher ARR ranks higher.\n\nACCOUNT DATA\nAlpine: ARR $60,000. Kickoff 20 days after signing. 30% trained. Sponsor replied 2 days ago. Integration blocked.\nBirch: ARR $50,000. Kickoff 5 days after signing. 80% trained. Sponsor silent for 12 days. Integration working.\nCove: ARR $90,000. Kickoff 16 days after signing. 45% trained. Sponsor silent for 11 days. Integration working.\nDune: ARR $40,000. Kickoff 10 days after signing. 49% trained. Sponsor replied yesterday. Integration blocked.\nEmber: ARR $70,000. Kickoff 14 days after signing. 50% trained. Sponsor silent for 10 days. Integration working.","rules":[{"type":"plainText"},{"type":"maxWords","max":60}],"mistakes":[{"title":"Miscounting the boundaries","why":"Ember's 14 days and 50% do not score, but its 10 days silent does.","fix":"Say: \"Apply the exact boundaries: MORE than 14, FEWER than 50%, 10 or MORE.\"","checks":["r1"]},{"title":"Missing the tie-break","why":"Cove and Alpine tie on 7; the AI lists them in table order.","fix":"Say: \"Ties: higher ARR first.\"","checks":["r2"]},{"title":"Extra text","why":"The AI explains each score.","fix":"Give the header row and say table only.","checks":["r0"]},{"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":"AI is bad at counting and usually runs long, so a vague \"keep it short\" lands well over the limit.","fix":"Cap each part instead of the total, for example \"each line under 15 words\".","checks":["maxWords"]}],"promptHints":[{"label":"Asks for plain text","patterns":["plain","no bold","no markdown","no formatting","no headings"]},{"label":"Sets a length limit","patterns":["\\d+\\s*words","word (limit|count)","under \\d+"]},{"label":"States the boundaries","patterns":["more than 14","fewer than 50","10 or more"]},{"label":"States the tie-break","patterns":["tie","higher arr"]}],"hint":"Boundary cases decide the score. Quote the exact boundaries, the tie-break and the table shape.","rubricLabels":["The header row is exactly \"Rank | Account | Points\" with five rows and nothing outside the table","The points are Cove 7, Alpine 7, Dune 5, Ember 3, Birch 3","The order is Cove, Alpine, Dune, Ember, Birch, using higher ARR as the tie-break"]}