Turn rough incident notes into a blameless postmortem with shippable follow-ups
Postmortems often start as rushed incident notes and stay messy until review time. This recipe takes a rough draft, removes blameful language, fills timeline gaps from PagerDuty and Slack, turns vague follow-ups into concrete Linear tickets, and schedules the review.
Polish a rough incident draft into a blameless postmortem for a DevOps or SRE engineer. Goal: Help me turn a rough incident draft into a finished blameless postmortem with action items the team can actually ship. Ask me for: - Incident ID and PagerDuty link - The rough draft text - Affected services and severity - Incident commander and primary responder - Slack channel where the incident was run - Time window of the incident in UTC - The postmortem template my team uses, if any - Whether action items should become Linear tickets Use available integrations this way: - PagerDuty: pull the incident timeline, escalations, and acknowledgements - Slack: pull key messages and decision points from the incident channel - GitHub: identify the deploys, PRs, and commits implicated in the incident - Linear: create action item tickets with proposed owners and due dates - Google Docs: produce the polished postmortem - Google Calendar: schedule the postmortem review meeting Output: 1. The polished postmortem doc with timeline, summary, contributing factors, and action items 2. A diff showing what I changed from the rough draft, so reviewers can see the editing pass 3. Reframing notes for any sections that read as blameful 4. Action items as a structured list with owners, due dates, and acceptance criteria 5. Linear tickets created for each action item with links back to the postmortem 6. A calendar invite for the review meeting with the postmortem attached Rules: - Use blameless language; remove names from causation, keep them in attribution - Do not invent timeline events; if a gap exists, mark it as "no record" - Action items must have an owner and a due date or they are flagged as incomplete - Do not change the incident severity or root cause without my approval - Preserve the original draft as a comment for traceability
This recipe is the editing pass for an incident write-up. You bring
the draft and incident context. The agent pulls timeline data from
PagerDuty and Slack, tightens the structure, applies blameless
framing, and turns loose follow-ups into owned Linear tickets.
Hand off the pager without making the next engineer reconstruct the shift
On-call handoffs usually happen fast, right when context is easiest to lose. The next engineer starts their shift digging through incidents, deploys, noisy alerts, and half-finished Slack threads just to understand the current state. This recipe pulls the shift's PagerDuty incidents, deploy activity, Datadog alerts, and open Slack threads into a clean handoff brief the next on-call can use immediately.
Find stale runbooks before they fail during an incident
Runbooks go stale quietly. Deploy paths change, services move, dependencies get renamed, and the doc only gets noticed at 3 a.m. when it points to infrastructure that no longer exists. This recipe finds runbooks that have not kept up with the services they describe and proposes updates based on recent service changes.
Fix credit report errors without guesswork
Generate dispute letters, evidence checklists, and follow-up timelines to correct credit report mistakes. Covers bureaus, furnishers, and identity theft.
Stop tax season from becoming a fire drill
A tailored documents list, question set, and recordkeeping system so you file accurately, claim what you're owed, and never scramble at the deadline again.