Incident summaries
The postmortem writes its own first draft.
An agent reconstructs the timeline from your incident channel and the deploys around it, identifies the triggering change, and drafts the write-up with the facts already assembled.
How it works
Three steps to a standing task
- Step 01
Point it at the incident channel
Give the agent the Slack channel and the repositories involved. It reads the whole conversation, including threads, and pulls the commits and deploys inside the impact window.
- Step 02
Hand it the task
Run it manually when the incident closes, or on a schedule that sweeps for channels created since the last run. It builds the timeline and names the triggering change.
- Step 03
Edit a draft instead of a blank page
The postmortem lands in Notion with the timeline, the contributing factors, and the action items people already agreed to in the channel.
The run
What the agent actually does
Every step below is a real tool call: the agent reaches for the API it needs, reads what it finds, and acts.
Draft a postmortem from the #incident channel and the deploys around it.
- slack·read #incident-2025-03-06 in full
- github·list deploys and reverts in the window
- github·read the diff for the suspect deploy
- code·build the minute-by-minute timeline
- notion·create the postmortem draft
Postmortem drafted
- 41-minute impact window reconstructed
- Triggering deploy identified as #2833
- Detection took 12 minutes; alerting gap noted
- 5 action items pulled from the discussion
Reach
The tools this agent touches
Each one connects once, and the agent gets its complete API.
This task belongs to Engineering. See the rest of what that team hands off.
Templates
Start from a working agent
Each template carries the prompt, the trigger, and the integrations it needs.
Engineering
Incident postmortem drafter
Reconstructs the incident timeline from Slack and GitHub, names the triggering change, and drafts the write-up in Notion.
Engineering
Pull request reviewer
Reviews every pull request against your conventions, leaves inline comments, and posts a weekly digest of review load and CI health.
Engineering
CI cost & speed report
Attributes build spend to the workflows driving it, finds the jobs that got slower, and names the change responsible.
FAQ
Questions, answered
Put an agent on incident summaries.
Describe the task, attach a trigger, and let it run around the clock.