{"id":"rec-scorecard-summary-evidence-only","audience":"managers","category":"people-work","track":"people","level":"intermediate","technique":"grounding","title":"Summarize interviewer notes for the hiring manager, evidence only","free":false,"task":"Summarize the interviewers' written notes for hiring manager Ken Ortiz in plain text, under 130 words. Use these labels on separate lines: Evidence for:, Evidence against:, Not covered:, Conflicts:. Quote or closely paraphrase only what the interviewers wrote. Do not rank, score, compare to other candidates, or recommend hiring or rejecting. The hiring panel decides. HR reviews before it is shared.","materialLabel":"Interviewer notes for one candidate (attached to your prompt automatically)","material":"Candidate: Aisha Rahman, Account Manager. Interviews Nov 9.\n\nPriya (client skills): \"Aisha gave a clear example of saving an at-risk client by agreeing a phased price. Strong on listening. Struggled to give numbers for her renewal rate.\"\n\nJorge (analytics): \"Aisha explained how she tracks pipeline in a spreadsheet; no experience with our CRM. Reasoned well through the forecast case but ran out of time on part 2.\"\n\nLinh (values): \"Collaborative, spoke respectfully about former colleagues. I'd say she's a great culture fit, she reminds me of me. Also she mentioned she is expecting a baby in spring.\"\n\nNot covered by any interviewer: negotiation of multi-year contracts (listed as a requirement on the scorecard).\n\nConflict: Priya says Aisha could not give renewal numbers; Jorge says she was precise on forecast numbers.","rules":[{"type":"maxWords","max":170},{"type":"plainText"}],"mistakes":[{"title":"Including personal details","why":"The AI repeats the pregnancy comment.","fix":"Say: \"Leave out anything not about job-related evidence.\"","checks":["r2"]},{"title":"Recommending","why":"The AI ends with 'Recommend moving forward'.","fix":"Say: \"Do not rank, score or recommend. The panel decides.\"","checks":["r2"]},{"title":"Missing gaps","why":"The AI skips what was not covered.","fix":"Say: \"Include Not covered: and Conflicts: lines.\"","checks":["r1"]},{"title":"Free-form structure","why":"The AI writes paragraphs with its own headings.","fix":"Say: \"Use exactly these four labels 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":"Named reader","patterns":["ken","hiring manager"]},{"label":"Four labels","patterns":["evidence for:","evidence against:","not covered:","conflicts:"]},{"label":"Evidence only","patterns":["only what","evidence"]},{"label":"No recommendation","patterns":["do not (rank|recommend)","panel decides"]},{"label":"Word cap","patterns":["under \\d+ words"]}],"hint":"Give the four labels, limit it to the interviewers' evidence, and forbid ranking or recommending.","mission":"Summarize interview notes for Ken Ortiz, evidence only.","musts":["Quote what they wrote","No ranking or recommending","Show conflicts"],"rubricLabels":["Uses the labels Evidence for:, Evidence against:, Not covered:, Conflicts: on separate lines in that order","Evidence is limited to what the interviewers wrote (phased price save, listening, no numbers for renewal rate, no CRM experience, ran out of time), Not covered names multi-year contract negotiation, and Conflicts names the renewal numbers versus forecast numbers difference","Does not include the baby, culture fit or 'reminds me of me', and does not rank, score or recommend hiring or rejecting"]}