{"id":"lead-sbi-two-examples-for-hr-review","audience":"managers","category":"leadership-work","track":"leadership","level":"advanced","technique":"verification","title":"Draft two SBI review comments from evidence and flag what is missing","free":false,"task":"Draft two review comments for Chen, one strength and one growth area, each in plain text with labeled lines Situation, Behavior, Impact (use the label \"Strength:\" or \"Growth:\" first). Use only dated evidence from the notes; if a claim has no dated evidence, do not use it and list it on a final line starting \"Needs evidence:\". End with the line: HR to review before sharing. No ratings or pay talk.","materialLabel":"Your notes about Chen (attached to your prompt automatically)","material":"Notes - Chen (Customer Success Manager), H2 review\n\nDated evidence\n- Aug 14: Chen led the Meridian Foods renewal call; the customer's CFO objected to price; Chen offered a phased start, and Meridian renewed for $96,000.\n- Sept 3 and Sept 17: Chen's QBR decks for two accounts went out 2 days after the deadline; both account owners had to chase.\n- Oct 9: Chen wrote the onboarding checklist the team now uses; two new hires used it and said they felt prepared.\n\nImpressions (no dates)\n- \"Seems disengaged lately.\"\n- \"I think customers like him.\"\n- \"Probably a flight risk.\"\n\nMy boss said ratings should be done separately by HR calibration.","rules":[{"type":"maxWords","max":190},{"type":"plainText"}],"mistakes":[{"title":"Using impressions as facts","why":"The AI writes 'disengaged' as behavior.","fix":"Say: \"Only dated evidence; list undated claims under Needs evidence.\"","checks":["r1"]},{"title":"Missing structure","why":"The AI writes narrative paragraphs.","fix":"Say: \"Labels Strength:/Growth: then Situation, Behavior, Impact.\"","checks":["r0"]},{"title":"No HR flag","why":"The AI ends with a friendly closing.","fix":"Say: \"Last line exactly: HR to review before sharing.\"","checks":["r2"]},{"title":"Markdown","why":"The AI bolds the labels.","fix":"Say: \"Plain text.\"","checks":["plainText"]},{"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 25 words.\"","checks":["maxWords"]},{"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 12 words.\"","checks":["maxWords"]}],"promptHints":[{"label":"SBI labels","patterns":["situation","behavior","impact"]},{"label":"One strength one growth","patterns":["strength","growth"]},{"label":"Dated evidence only","patterns":["dated","evidence","only (the )?facts"]},{"label":"Needs evidence line","patterns":["needs evidence"]},{"label":"HR line","patterns":["hr to review"]}],"hint":"Give the labels, say only dated evidence counts, and ask for the Needs evidence and HR lines.","rubricLabels":["Has exactly one entry starting \"Strength:\" and one starting \"Growth:\", each with Situation, Behavior and Impact lines using dates and facts from the notes (Aug 14 renewal or Oct 9 checklist for the strength, Sept 3 and Sept 17 late decks for the growth)","Does not use disengaged, customers like him or flight risk as evidence, and includes a line starting \"Needs evidence:\" that names at least one of these undated impressions","The last line is exactly \"HR to review before sharing\" and the draft gives no rating, pay or promotion comments"]}