{"id":"mgr-x-candidate-scorecard-totals","audience":"managers","category":"decisions","track":"data","technique":"verification","title":"Total candidate scorecards and pick who advances","free":false,"task":"Three candidates finished panel interviews, and you need to pick two for the final round. Write exactly 3 numbered lines, one per candidate in the order listed, each showing the score math as 'a + b + c + d = total', then one final line starting 'Advance:' naming the two highest totals, plain text, under 70 words. Use the corrected score.","materialLabel":"Scorecards (attached to your prompt automatically)","material":"Panel scores - Support Team Lead (scale 1-5 per competency)\nCompetencies: de-escalation, coaching, prioritization, data use.\n\nCandidate A - Priya: 4, 3, 4, 3\nCandidate B - Marcus: 5, 4, 3, 2\n  CORRECTION (Hana, HR): Marcus's data use score was entered wrong; it's 4, not 2.\nCandidate C - Elena: 3, 4, 3, 3\n\nRule: the 2 highest totals advance. Ties go to the higher coaching score.\n\nPanel chatter (ignore): \"Marcus seemed a bit cocky.\" \"Elena reminds me of my sister.\"","rules":[{"type":"numberedItems","count":3},{"type":"maxWords","max":70},{"type":"plainText"}],"mistakes":[{"title":"Asking 'who should advance'","why":"The AI gives a pick and a paragraph without the math.","fix":"Show it: \"1. Priya: 4 + 3 + 4 + 3 = 14\".","checks":["r0","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 wrong score","why":"Marcus's original score appears first, with the correction below it.","fix":"Add: \"Marcus's data use is 4 (corrected).\"","checks":["r0","r1"]},{"title":"Opinions and pick first","why":"The AI repeats panel impressions and states the pick before the numbers.","fix":"Add: \"Advance line last. No panel chatter. Plain text.\"","checks":["r2","r1","plainText"]}],"promptHints":[{"label":"Asks to show the math","patterns":["show.{0,15}(math|work)","\\+","total"]},{"label":"Uses the correction","patterns":["correct","marcus.{0,20}4"]},{"label":"Puts the pick last","patterns":["advance:? .{0,20}last","final line","then.{0,10}advance"]},{"label":"Ignores chatter","patterns":["chatter","ignore","cocky","opinion"]},{"label":"Sets a word limit","patterns":["\\d+\\s*words","word (limit|count)"]}],"hint":"When totals decide, have the AI show the sums and pick last. Tell it the corrected score and to ignore impressions.","rubricLabels":["The lines show Priya 4 + 3 + 4 + 3 = 14, Marcus 5 + 4 + 3 + 4 = 16 (using the corrected 4, not 2), and Elena 3 + 4 + 3 + 3 = 13","The final line starts 'Advance:' and names Marcus and Priya, after the three score lines","No panel chatter appears (cocky, sister), and there is no intro or commentary"]}