{"id":"cs-expansion-timing-decision","audience":"managers","category":"support-work","technique":"constraints","track":"support","level":"intermediate","title":"Decide whether to pitch an expansion now, with a one-line call","free":false,"task":"Decide whether to pitch a seat expansion to Harbor Dental now. Write exactly four lines starting \"Usage:\", \"Blocker:\", \"Timing:\" and \"Recommendation:\". Recommendation is exactly one of: Ask now, Fix first then ask, Do not ask this year. Team rule: no expansion pitch while a P1 bug older than 14 days is open for the account. Plain text, under 80 words.","materialLabel":"Your material (attached to your prompt automatically)","material":"ACCOUNT: Harbor Dental (40 seats, renews May 31)\nUsage: 38 of 40 seats active last 30 days (95%). Two of the 38 are on the new front-desk team.\nSponsor: Dr. Ruiz is very happy; asked on Oct 22 'what would 15 more seats cost?'\nOpen issues: P1 bug 'appointment reminders not sending' opened Oct 16 (21 days ago), engineering ETA Nov 20. One P3 cosmetic issue.\nBudgeting: Harbor finalizes next year's budget on Dec 1. After that, new spend waits until May.\nPricing: seats are $30 per seat per month.\n\nSales rep note: 'He asked for a price, just send the quote today, we need the number this quarter.'","rules":[{"type":"plainText"},{"type":"maxWords","max":80}],"mistakes":[{"title":"Following the sales rep","why":"The note says send the quote today, and the AI agrees.","fix":"Say: \"The team rule decides, not the rep's deadline.\"","checks":["r2"]},{"title":"Missing the budget date","why":"The AI says wait without noticing the Dec 1 window.","fix":"Ask: \"Timing must use the bug ETA and the budget date.\"","checks":["r1"]},{"title":"Free-form advice","why":"The AI gives a long memo with options.","fix":"Name the four labels and the three allowed recommendations.","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":"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+"]},{"label":"Names labels and options","patterns":["usage:","blocker:","recommendation"]},{"label":"Applies the rule","patterns":["14 days","p1","rule"]}],"hint":"Decisions need the rule, the dates and fixed answer choices. Give all three so the AI cannot hedge.","rubricLabels":["Usage cites 38 of 40 seats (95%) and Blocker cites the P1 reminder bug open 21 days, over the 14-day rule","Timing mentions the bug ETA of Nov 20 and the Dec 1 budget deadline","Recommendation is exactly \"Fix first then ask\" and the output has exactly the four labeled lines"]}