All templates

Engineering

Incident postmortem drafter

Reconstructs the incident timeline from Slack and GitHub, names the triggering change, and drafts the write-up in Notion.

The prompt

This is the whole configuration

Paste it into a workflow and edit it in plain English. There is nothing else to wire up.

The prompt
I will give you the name of an incident Slack channel. Read the entire channel including every thread. Work out when impact started, when we detected it, when we mitigated it, and when it fully resolved, and cite the message that tells you each. Then look at GitHub for every deploy, merge, and revert in the two hours before impact started, and read the diffs of the likely candidates. Build a minute-by-minute timeline. Draft a postmortem in the Notion Postmortems database with: summary, impact, timeline, contributing factors, what went well, and action items. Pull the action items from what people actually agreed to in the channel, with owners. State your assumptions explicitly wherever the channel is ambiguous.

Trigger

What starts this agent

Run on demand

Runs when you ask for it, from the app, from chat, or over the API.

Integrations required

Authorize each service once. Helios stores the credential envelope-encrypted and attaches it server-side on every run.

Example output

What you get back

Every run leaves a readable record: the steps the agent took and the result it produced.

Postmortem drafted

  • 41-minute impact window reconstructed
  • Triggering deploy identified as #2833
  • 5 action items pulled from the discussion

New to Helios? Start with Run your first agent.

Run Incident postmortem drafter on your stack.

Connect the integrations, paste the prompt, attach the trigger. The agent takes it from there.