{"id":"cx-qa-sampling-plan-hours-gap","audience":"managers","category":"support-work","technique":"verification","track":"support","level":"advanced","title":"Check whether the QA sampling plan fits the reviewers' hours","free":false,"task":"Start with the line \"QA CHECK - week of Nov 9\" on its own. Write four lines starting \"Reviews:\", \"Hours:\", \"Reviewers:\" and \"Decision:\". Show the arithmetic on the first three. Plain text, under 100 words. The Decision line must start with \"Decision: Fits\" or \"Decision: Does not fit\", then compare the totals from your lines.","materialLabel":"Your material (attached to your prompt automatically)","material":"QA SAMPLING PLAN (draft)\n- Team: 12 agents, of which 2 are in their first month (new hires).\n- Each agent is reviewed on 5 tickets per week.\n- New hires get double that: 10 tickets per week.\n- Each review takes 15 minutes.\n\nREVIEWER CAPACITY\n- 2 reviewers, each with 8 hours per week for QA.\n- Calibration meeting: 1 hour per week per reviewer, taken from those 8 hours.\n\nNOTES\nLast quarter the plan was 5 tickets per agent for everyone (60 reviews). The plan above is new.","rules":[{"type":"plainText"},{"type":"maxWords","max":100}],"mistakes":[{"title":"Using last quarter's 60","why":"The AI ignores the double sampling for new hires.","fix":"Say: \"New hires get 10 each; 10 agents get 5.\"","checks":["r0"]},{"title":"Forgetting the calibration hour","why":"The AI uses 16 hours of capacity.","fix":"Say: \"Capacity is 8 hours minus 1 calibration hour for each reviewer.\"","checks":["r1"]},{"title":"Verdict without numbers","why":"The AI says 'it should be tight'.","fix":"Say: \"The Decision line compares the two hour totals.\"","checks":["r2"]},{"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":"Names the four lines","patterns":["reviews:","hours:","reviewers:","decision:"]},{"label":"Asks to show arithmetic","patterns":["show the (math|arithmetic)","x \\d"]},{"label":"Mentions calibration time","patterns":["calibration","minus 1"]},{"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+"]}],"hint":"Name the four lines, ask for the arithmetic, and point out the two details that change the totals.","rubricLabels":["The first line is exactly \"QA CHECK - week of Nov 9\". The Reviews line shows 10 agents x 5 + 2 new hires x 10 = 70 reviews (not 60)","The Hours line shows 70 x 15 minutes = 1,050 minutes = 17.5 hours, and the Reviewers line shows capacity of 2 x (8 - 1) = 14 hours","The line starting \"Decision: Does not fit\" says the plan does not fit, because 17.5 hours is more than 14 hours (a gap of 3.5 hours)"]}