{"id":"dat-hr-panel-scores-recusal","audience":"hr","category":"decisions","technique":"context","title":"Average interview panel scores after a recusal","free":false,"task":"You're the recruiter closing out a hiring panel. Ravi told you privately that he worked with Marco Ruiz before, so his score for Marco must be dropped (the scorecards don't show this). Write exactly 3 numbered lines, one per candidate, each showing the scores added and divided into an average (2 decimals), then one unnumbered last line: Advance: [name]. Plain text, under 70 words.","materialLabel":"Panel scorecards (attached to your prompt automatically)","material":"PANEL SCORECARDS - Senior Account Manager (1-5, overall rating)\n\nCandidate | Pat | Ravi | Sue | Dee\nLena Cho | 3 | 4 | 4 | 3\nMarco Ruiz | 4 | 5 | 4 | 3\nTasha Green | 4 | 4 | 4 | 3\n\nInterviewer comments:\n- Ravi on Marco: \"Great culture fit, I'd hire him tomorrow.\"\n- Sue on Tasha: \"Strongest on the account plan exercise.\"\n- Dee on Lena: \"Good, a bit quiet in the group round.\"\n- Pat: \"All three are solid. Tasha's references came back strong.\"\n\nProcess notes:\n- Hiring manager wants one name to advance to the final round by Friday.\n- Ties go to the candidate with the higher account plan score (not needed if no tie).\n- Offer approvals go through Comp, not the panel.","rules":[{"type":"numberedItems","count":3},{"type":"plainText"},{"type":"maxWords","max":70}],"mistakes":[{"title":"Not telling the AI about the recusal","why":"The scorecards don't show it, so the AI counts Ravi's 5 and Marco comes out on top.","fix":"Add: \"Drop Ravi's score for Marco. Average Marco over 3 interviewers.\"","checks":["r0","r2"]},{"title":"Not asking to see the work","why":"Bare averages hide which scores were counted.","fix":"Add a line to copy: \"1. Lena Cho: (3 + 4 + 4 + 3) ÷ 4 = 3.50\"","checks":["r1","numberedItems"]},{"title":"Letting comments sway it","why":"The AI weighs Ravi's 'culture fit' praise into the pick.","fix":"Add: \"Pick on the averages only.\"","checks":["r2"]},{"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: \"each line under 14 words.\"","checks":["maxWords"]},{"title":"Forgetting where it goes","why":"AI loves markdown tables and bold, which show up as clutter in an applicant tracking system note.","fix":"Add: \"Plain text, no bold, headings or tables.\"","checks":["plainText"]}],"promptHints":[{"label":"Mentions the recusal","patterns":["recus","ravi","drop|exclude|remove","conflict"]},{"label":"Asks to show the math","patterns":["show (the |your )?(math|work)","x \\$|\\bx\\b.{0,10}=","calculation","step"]},{"label":"Asks for the pick last","patterns":["advance","last line","then (pick|name)"]},{"label":"Sets a word limit","patterns":["\\d+\\s*words","word (limit|count)","under \\d+"]},{"label":"Asks for plain text","patterns":["plain","no bold","no markdown","no formatting","no (headings|tables)"]}],"hint":"The AI can't know about the conflict unless you say so. Tell it which score to drop, and ask it to show each average.","rubricLabels":["Marco's average leaves out Ravi's score: (4 + 4 + 3) ÷ 3 = 3.67, not 4.00","Tasha is (4 + 4 + 4 + 3) ÷ 4 = 3.75 and Lena is (3 + 4 + 4 + 3) ÷ 4 = 3.50, with the math shown","The last line advances Tasha Green, after the three score lines, with no intro or extra commentary"]}