{"id":"cx-feedback-situation-behavior-impact-facts","audience":"managers","category":"support-work","technique":"tone","track":"support","level":"intermediate","title":"Give factual Situation-Behavior-Impact feedback without labels","free":false,"task":"Write feedback to Rami as four lines starting \"Situation:\", \"Behavior:\", \"Impact:\" and \"Ask:\", then the line \"Next 1:1: Thu Nov 12\". State only observable facts from the log. Do not use words that judge him as a person, such as careless, lazy or sloppy. Plain text, under 90 words.","materialLabel":"Your material (attached to your prompt automatically)","material":"TEAM LEAD LOG (Rami, support agent)\n- Tue Nov 3, 10:20: customer Hollis Brandt reported a payment failing for 40 minutes (a P2 under our rules). Rami answered with a macro and did not escalate it to the on-call engineer.\n- The ticket was escalated by another agent at 11:45. That is 85 minutes after Rami's reply.\n- The customer wrote again at 11:30: 'Still waiting, this is costing me orders.' The final fix took 25 more minutes.\n- Rami told the lead afterward: 'I thought the macro would cover it.'\n- Team rule: P2s are escalated to on-call within 15 minutes of the first report.\n- Rami has had no other missed escalations in 7 months.\n\nNOTE: This is the first conversation about this; the goal is to help him do it next time.","rules":[{"type":"plainText"},{"type":"maxWords","max":90}],"mistakes":[{"title":"Judging the person","why":"The AI writes 'you were careless'.","fix":"Say: \"Observable facts only; no judging words.\"","checks":["r2"]},{"title":"Vague behavior","why":"The AI says 'you handled it poorly'.","fix":"Say: \"Behavior is what he did, with the time and rule.\"","checks":["r1"]},{"title":"Missing the last line","why":"The AI ends with the Ask.","fix":"Quote the final line.","checks":["r0"]},{"title":"Getting markdown back","why":"AI adds bold and headings by default, which show up as stray symbols where this is pasted.","fix":"Say \"plain text, no bold, no headings, no asterisks\".","checks":["plainText"]},{"title":"Trusting the AI to count words","why":"AI is bad at counting and usually runs long, so a vague \"keep it short\" lands well over the limit.","fix":"Cap each part instead of the total, for example \"each line under 15 words\".","checks":["maxWords"]}],"promptHints":[{"label":"Names the four labels","patterns":["situation:","behavior:","impact:","ask:"]},{"label":"Bans judging words","patterns":["careless","lazy","judg"]},{"label":"Quotes the final line","patterns":["next 1:1"]},{"label":"Asks for plain text","patterns":["plain","no bold","no markdown","no formatting","no headings"]},{"label":"Sets a length limit","patterns":["\\d+\\s*words","word (limit|count)","under \\d+"]}],"hint":"Name the four labels, forbid judging words and quote the final line.","rubricLabels":["The output has four lines starting Situation:, Behavior:, Impact: and Ask: followed by the line \"Next 1:1: Thu Nov 12\"","Situation and Behavior state the facts (Nov 3 payment failure P2, macro reply, no escalation within the 15-minute rule) and Impact states the customer waited until the 11:45 escalation and wrote again at 11:30","The feedback uses no words like careless, lazy or sloppy, and Ask requests a concrete next step such as escalating P2s to on-call within 15 minutes"]}