← All templates

Engineering

Run on demand

Incident postmortem drafter

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

5,000 free credits to start.

The prompt

The workflow prompt

Copy this prompt into a new workflow, connect the listed integrations, and configure its trigger.

prompt.md
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.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 a summary, impact, timeline, contributing factors, what went well, and action items.Pull the action items from what people agreed to in the channel, with owners.State your assumptions wherever the channel is unclear.

Trigger

What starts this workflow

Run on demand

Runs when you start it. From the workflow page, from chat, from the CLI, or over the API.

Integrations it uses

Connect each service once. Helios stores the credential encrypted and injects it at the network layer on every run. The agent never holds the token.

Example output

What you get back

Every run keeps its full transcript. The steps the agent took, each tool call, and the result.

Postmortem drafted

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

New to Helios? Start with Run your first workflow.

Run Incident postmortem drafter on your tools.

Connect the integrations, paste the prompt, and pick the trigger.