{"id":"cx-escalate-or-solve-first-rule-table","audience":"customer-support","category":"support-work","technique":"constraints","track":"support","level":"advanced","title":"Decide solve or escalate for five tickets with ordered triggers","free":false,"task":"Start with the line \"TRIAGE RUN - Nov 6\". Then output a table with the header \"Ticket | Action | Rule\" and five rows T1 to T5. Action is Escalate or Solve. Rule is the first trigger that applies (A, B or C, checked in that order) or \"none\" for Solve. Plain text, under 60 words.","materialLabel":"Your material (attached to your prompt automatically)","material":"ESCALATION TRIGGERS (check in order)\nA: the customer mentions a chargeback or disputing the charge with their bank.\nB: the refund or credit amount is over $200 (exactly $200 is not over).\nC: this is the customer's second or later contact about the same issue within 7 days.\n\nTICKETS\nT1: wants a $250 refund for a broken desk; first contact.\nT2: \"I'll just dispute this with my bank\" about a $50 charge; first contact.\nT3: asks for a $150 credit; they wrote about the same issue 5 days ago.\nT4: asks for a $200 refund; first contact.\nT5: wants $300 back and says they will start a chargeback; second contact this week.","rules":[{"type":"plainText"},{"type":"maxWords","max":60}],"mistakes":[{"title":"Escalating exactly $200","why":"The AI treats $200 as over $200.","fix":"Say: \"Exactly $200 is not over.\"","checks":["r2"]},{"title":"Reporting the wrong rule for T5","why":"The AI says B or C.","fix":"Say: \"Report the first trigger in order A, B, C.\"","checks":["r2"]},{"title":"Missing the title line","why":"The AI starts with the table.","fix":"Quote the title 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","r1"]}],"promptHints":[{"label":"Quotes the title","patterns":["triage run - nov 6"]},{"label":"Gives the header","patterns":["ticket \\| action \\| rule"]},{"label":"Says first trigger in order","patterns":["first trigger","in order","a, b"]},{"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":"Quote the title, give the header and say the first trigger in order decides.","rubricLabels":["The first line is exactly \"TRIAGE RUN - Nov 6\" and the next line is the header \"Ticket | Action | Rule\"","T1 Escalate (B), T2 Escalate (A), T3 Escalate (C)","T4 Solve (none) because $200 is not over $200, and T5 Escalate (A) because A is checked first"]}