{"id":"hr-review-comment-bias-check-table","audience":"managers","category":"people-work","track":"people","level":"intermediate","technique":"verification","title":"Check draft review comments for vague or biased wording","free":false,"task":"Check the manager's five draft review comments and return a table with the header Comment | Problem | Neutral rewrite. One row per comment, same order. Problem is exactly one of: Vague, Personality label, Personal trait, OK. Neutral rewrite is exactly \"Add a dated example\" for Vague and Personality label rows, exactly \"Remove\" for Personal trait rows, and exactly \"No change\" for OK rows. Do not rate or rank the employee, and do not suggest a rating. Plain text. The manager and HR make the final call.","materialLabel":"Draft comments for one employee (attached to your prompt automatically)","material":"Employee: Alex Brandt, Operations Coordinator, mid-year review. Draft comments from manager Pat Kowalski:\n\n1. \"Alex is bossy in meetings.\"\n2. \"Alex needs to step up.\"\n3. \"Alex closed 46 of 50 tickets inside the 2-day target in Q2 and flagged two backlog risks early.\"\n4. \"Not really a culture fit, seems older than the rest of the team's approach.\"\n5. \"Alex missed the Sept 18 handoff deadline twice.\"\n\nContext: the scoring scale is managed in a separate HR system; nothing in this task is about the score. Pat asked for Alex to be considered for a stretch assignment; that is a separate decision.","rules":[{"type":"maxWords","max":170},{"type":"plainText"}],"mistakes":[{"title":"Wrong labels","why":"The AI invents its own categories.","fix":"Say: \"Problem is exactly one of Vague, Personality label, Personal trait, OK.\"","checks":["r1"]},{"title":"Rating the employee","why":"The AI suggests a score or comments on the assignment.","fix":"Say: \"Do not rate, rank or suggest a rating.\"","checks":["r2"]},{"title":"Different table","why":"The AI adds columns or merges rows.","fix":"Say: \"Header exactly Comment | Problem | Neutral rewrite, five rows in order.\"","checks":["r0"]},{"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 part instead, for example: \"each line under 15 words.\"","checks":["maxWords"]},{"title":"Markdown","why":"The AI bolds words or adds headings.","fix":"Say: \"Plain text, no bold, no headings.\"","checks":["plainText"]}],"promptHints":[{"label":"Exact header","patterns":["comment \\|","problem","neutral rewrite"]},{"label":"Allowed labels","patterns":["vague","personality label","personal trait"]},{"label":"Fixed rewrite text","patterns":["add a dated example","remove","no change"]},{"label":"No rating","patterns":["do not rate","rank"]},{"label":"One row per comment","patterns":["one row"]}],"hint":"Give the header, the exact allowed labels and a limit for the rewrite.","mission":"Flag vague or biased wording in five draft review comments.","musts":["Fixed Problem categories","Exact rewrite wording","No ratings"],"rubricLabels":["Has the header Comment | Problem | Neutral rewrite and exactly five rows in the order of the comments","Problem values are exactly one of Vague, Personality label, Personal trait, OK and are right: 1 Personality label, 2 Vague, 3 OK, 4 Personal trait, 5 OK","Neutral rewrite cells follow the rule: Vague and Personality label rows say exactly Add a dated example, the Personal trait row says exactly Remove, OK rows say exactly No change, and the output gives no rating, ranking or decision about the stretch assignment"]}