{"id":"cx-incident-severity-matrix-lookup-page-now","audience":"it","category":"support-work","technique":"constraints","track":"support","level":"advanced","title":"Classify three incidents with a severity matrix and decide who to page","free":false,"task":"Start with the line \"SEV CHECK - Nov 6 shift\". Then output a table with the header \"Incident | Sev | Page now?\" and three rows INC1 to INC3, then a last line \"Page: INC#, INC#\" (or \"Page: none\"). Use the matrix; Sev1 and Sev2 are paged immediately. Plain text, under 50 words.","materialLabel":"Your material (attached to your prompt automatically)","material":"SEVERITY MATRIX (scope x impact)\nImpact down, scope all customers: Sev1\nImpact down, scope some customers: Sev2\nImpact degraded, scope all customers: Sev2\nImpact degraded, scope some customers: Sev3\nImpact down or degraded, scope one customer: Sev3\nAny confirmed data loss, any scope: Sev1 (overrides the rows above)\nSev1 and Sev2 are paged immediately; Sev3 goes to the next-business-day queue.\n\nINCIDENTS\nINC1: Search is slow for all customers (still works, but takes 8 seconds).\nINC2: Exports fail completely for 15% of customers.\nINC3: One customer cannot log in. No data is affected.\n\nNOTE: On Nov 5 a similar INC to INC1 was marked Sev3 by mistake.","rules":[{"type":"plainText"},{"type":"maxWords","max":50}],"mistakes":[{"title":"Copying the Nov 5 mistake","why":"The AI marks INC1 Sev3.","fix":"Say: \"Use the matrix: degraded for all customers is Sev2.\"","checks":["r1","r2"]},{"title":"Treating degraded as down","why":"The AI marks INC1 Sev1.","fix":"Say: \"Impact degraded, scope all: Sev2.\"","checks":["r1"]},{"title":"Missing the exact lines","why":"The AI skips the title or last line.","fix":"Quote the title and last line.","checks":["r0","r2"]},{"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":"Quotes the title","patterns":["sev check - nov 6 shift"]},{"label":"Gives the header","patterns":["incident \\| sev"]},{"label":"Says Sev1 and Sev2 are paged","patterns":["sev1 and sev2","paged"]},{"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 state which severities are paged.","rubricLabels":["The first line is exactly \"SEV CHECK - Nov 6 shift\" and the next line is the header \"Incident | Sev | Page now?\"","INC1 Sev2 Yes, INC2 Sev2 Yes, INC3 Sev3 No","The last line is exactly \"Page: INC1, INC2\""]}