How to Write a Status-Page Incident Update from Monitoring Facts
Status pages fail when the update invents back by noon and a cloud-provider outage. You had a latency alert and an ack. That is all you can say until the next fact arrives.
The matching generator is the Status-Page Incident Update from Monitoring Facts Only prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).
Stay on the status page, not in an apology email
Write a status-page incident update from monitoring facts you paste. No invented ETAs, customer counts, or root causes. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.
Paste these fields before you hit run:
Product and status-page name: [Page]
Incident title already in the tool (or NONE): [Title]
Current status (investigating / identified / monitoring / resolved): [Status]
Impacted components from the page catalog: [Components]
Monitoring facts with timestamps in UTC: [Facts]
What we already told customers: [Prior]
Actions in flight I can prove: [Actions]
Next update window I can commit: [Next or NONE]
Words I must not use: [Banned]
Word budget: [Budget or 180]
That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.
Quote UTC facts and mark components you cannot prove
Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.
Walk the Generate list in order:
- Honesty ledger: timestamps, components, statuses, and actions from Inputs. Forbidden: ETAs, percentages, root causes, and regions not listed.
- Incident title (80 chars max). Reuse Title if given. Print the count.
- Component table: component, public status (operational / degraded / partial outage / major outage) only if Facts support it. Else NOT IN INPUTS.
- Update body for Status: 80-180 words. Quote Facts with UTC times. No customer count.
- Actions line: only Actions. Do not claim a fix unless Actions say a fix shipped.
- Next update: only Next. If NONE, write next update time not committed.
- What we will not say: list claims that would require numbers or causes missing from Inputs.
- Compliance pass: quote Banned words, invented ETAs, apology-email tone. Cut them. Print word count vs Budget.
If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.
Do not promise the next clock unless you committed one
Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.
Honor the constraints as hard stops, not vibes:
- Status-page component update, not a customer apology email and not a PIR.
- Never invent an ETA, user count, or root cause.
- Timestamps stay UTC as pasted. Do not convert unless Inputs give a zone.
- Stay under Budget words.
- No emojis unless the status-page voice in Inputs uses them.
When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.
Leave root cause and user counts off the post
Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.
Tags on the card (status page incident update, monitoring facts only, no invented eta) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.
Fill the card, then run
Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.