{"id":"hr-calibration-distribution-math","audience":"hr","category":"data","track":"data","technique":"verification","title":"Summarize rating distribution with the percentages shown","free":false,"task":"You're summarizing the performance rating distribution for the leadership calibration meeting. Write exactly 3 numbered lines, one per rating, each showing the math as 'count / total = percent' rounded to the nearest whole percent, then one line comparing against the guideline, plain text, under 60 words. Use the corrected counts.","materialLabel":"Rating data (attached to your prompt automatically)","material":"Mid-year ratings - Operations (Cedar Freight), pre-calibration\n\nTotal employees rated: 80.\n\nCounts:\n- Exceeds: 14\n- Meets: 60\n- Below: 6\n  CORRECTION (Jun 24, HR): 2 people in \"Exceeds\" were rated by a manager who left; their new manager re-rated them as \"Meets\". Updated counts: Exceeds 12, Meets 62, Below 6.\n\nCompany guideline (not a quota): Exceeds usually 10-20%.\n\nNotes:\n- Don't list names or managers in the summary.\n- Leaders asked for \"the numbers with the math so we can check them.\"","rules":[{"type":"numberedItems","count":3},{"type":"maxWords","max":60},{"type":"plainText"}],"mistakes":[{"title":"Asking for 'a summary'","why":"The AI gives percentages without the math, so leaders can't check them.","fix":"Show it: \"1. Exceeds: 12 / 80 = 15%\".","checks":["r1","numberedItems"]},{"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 line instead: \"each line under 12 words.\"","checks":["maxWords"]},{"title":"Using the old counts","why":"The first counts appear before the correction.","fix":"Add: \"Use the corrected counts: 12, 62, 6.\"","checks":["r0"]},{"title":"Skipping the comparison","why":"The AI lists numbers but doesn't say how they compare to the guideline.","fix":"Add: \"End with one line comparing Exceeds to the 10-20% guideline. Plain text.\"","checks":["r2","plainText"]}],"promptHints":[{"label":"Asks to show the math","patterns":["show.{0,15}(math|work)","count ?/ ?total","/ ?80"]},{"label":"Uses the corrected counts","patterns":["correct","\\b12\\b","62"]},{"label":"Compares to the guideline","patterns":["guideline","10.?20%"]},{"label":"Sets the number of lines","patterns":["\\b(3|three)\\b.{0,15}(line|rating)"]},{"label":"Sets a word limit","patterns":["\\d+\\s*words","word (limit|count)"]}],"hint":"When numbers will be checked, have the AI show its work. Tell it the corrected counts, the line shape, and to end with the guideline comparison.","rubricLabels":["The lines show Exceeds 12 / 80 = 15%, Meets 62 / 80 = 78% (77.5% rounded, 77% or 78% acceptable), Below 6 / 80 = 8% (7.5% rounded, 7% or 8% acceptable), using the corrected counts (not 14 or 60)","Each numbered line shows the division before the percent","The final line says Exceeds at 15% is within the 10-20% guideline, and no names or managers appear"]}