{"id":"cx-oncall-page-one-line-confirmed-numbers","audience":"it","category":"support-work","technique":"constraints","track":"support","level":"advanced","title":"Write a one-line on-call page with confirmed numbers only","free":false,"task":"Write the page as one line with five parts separated by \" | \" in this order: severity, account, impact, what has been tried, the ask. Use only confirmed numbers from monitoring, not the customer's estimate. Plain text, one line, under 45 words.","materialLabel":"Your material (attached to your prompt automatically)","material":"TICKET #9921 - Harlow Freight (enterprise, 340 seats)\nCustomer wrote: \"Nobody on my team can load shipments. About 500 users are affected, probably the whole company!\"\n\nMONITORING (confirmed)\n- Shipment API returning errors for Harlow only; 120 users hit errors in the last 15 minutes.\n- Other customers: normal.\n- Started 13:42 UTC.\n\nAGENT ACTIONS\n- Cleared Harlow's cache at 13:55: no change.\n- Restarted their worker at 14:01: no change.\n- Last deploy to the shipment service was at 13:30 UTC.\n\nON-CALL GUIDE\nPage format: severity | account | impact | tried | ask. Severity P1 means a single enterprise customer is down for a core function.","rules":[{"type":"plainText"},{"type":"maxWords","max":45}],"mistakes":[{"title":"Using the customer's 500","why":"The AI repeats the customer's estimate.","fix":"Say: \"Use confirmed monitoring numbers only.\"","checks":["r1"]},{"title":"Wrong order or separators","why":"The AI uses bullets or commas.","fix":"Say: \"Five parts separated by ' | ' in this order.\"","checks":["r0"]},{"title":"Vague ask","why":"The AI says 'please investigate'.","fix":"Say: \"The ask names the 13:30 deploy.\"","checks":["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":"Lists the five parts in order","patterns":["severity","account","impact","tried","ask"]},{"label":"Uses confirmed numbers","patterns":["confirmed","monitoring","not the customer"]},{"label":"Sets a tight length","patterns":["30 words","under 30","one line"]},{"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":"List the five parts in order, say which numbers to trust and give a tight word cap.","rubricLabels":["The output is a single line with five parts separated by \" | \" in the order severity, account, impact, tried, ask","The first part is P1, the second is Harlow Freight, and the impact says 120 users (not 500) with errors since 13:42 UTC","The tried part mentions the cache clear and the worker restart, and the ask refers to the 13:30 deploy (such as a rollback check)"]}