{"id":"cx-status-posts-investigating-identified-monitoring","audience":"operations","category":"support-work","technique":"context","track":"support","level":"intermediate","title":"Write three status posts that do not name a cause too early","free":false,"task":"Write three status posts on three lines starting \"Investigating:\", \"Identified:\" and \"Monitoring:\", each under 22 words. Only the Identified post may name a cause, and only the confirmed one. The Monitoring post gives the next update time one hour after the failover finished. Plain text.","materialLabel":"Your material (attached to your prompt automatically)","material":"INCIDENT LOG - slow dashboards (all times local)\n10:05 Customers report dashboards loading slowly.\n10:20 Engineers still looking at it. Cause unknown.\n10:35 Someone in chat: 'could be yesterday's deploy?' Not confirmed, later ruled out.\n10:50 Cause confirmed: an overloaded database replica. Starting a failover to a fresh replica.\n11:30 Failover finished. Dashboards loading normally in tests. Watching for a while.\n\nSTATUS PAGE STYLE\nShort, plain, no jargon like 'replica' in the first two posts. Use the customer-facing word 'database'. No blame, no speculation.","rules":[{"type":"plainText"},{"type":"maxWords","max":75}],"mistakes":[{"title":"Naming the deploy","why":"The AI repeats the unconfirmed 'yesterday's deploy' guess.","fix":"Say: \"Only the confirmed cause; no speculation.\"","checks":["r1"]},{"title":"Cause too early","why":"The AI mentions the database in Investigating.","fix":"Say: \"Investigating names no cause.\"","checks":["r1"]},{"title":"No next update time","why":"The AI says 'we will update soon'.","fix":"Say: \"Give the next update as 12:30.\"","checks":["r2","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 three labels","patterns":["investigating:","identified:","monitoring:"]},{"label":"Controls when a cause may appear","patterns":["only the identified","no cause","confirmed"]},{"label":"Sets the next update time","patterns":["12:30","one hour after","next update"]},{"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 three labels, say which post may name a cause, and say how the next update time is set.","rubricLabels":["The output is exactly three lines starting Investigating:, Identified: and Monitoring:","Investigating names no cause; Identified names an overloaded database (not yesterday's deploy) and says a failover is under way","Monitoring says dashboards are loading normally again and gives 12:30 as the next update"]}