Skip to main content
Stand up an always-on SRE on-call by wiring Devin to your incidents channel. When someone reacts with 🚨 to a Slack message, Devin jumps in — cross-references Datadog metrics, Sentry exceptions, and recent deploys, then drops a root-cause summary back in the thread before a human even finishes their first cup of coffee.

Use this template

Open SRE Incident Response in Devin and create the automation with the default configuration. You can customize it before saving.

​
What this automation does

This automation is built around the universal 🚨 emoji reaction — the fastest way to flag “this is an incident.” When Devin sees the reaction land in #incidents (or whichever channel you designate), it reads the full message thread for context, pulls the last hour of Datadog alerts and Sentry errors, checks recent merges for suspicious changes, and posts a structured postmortem draft. A human can take it from there or send a follow-up in-thread to steer the investigation.

​
How it works

Trigger: Slack event — reaction.added
  • Event: slack:reaction_added
    • Conditions:
      • reaction eq rotating_light
      • channel eq #incidents
What Devin does: Starts a session with full event context, executes the prompt below, and (optionally) notifies you on failure.

​
Prerequisites

​
Example prompt

The template ships with this prompt. You can edit it after clicking Use template, or leave it as-is.

​
Setting it up

  1. Open Automations → Templates in Devin.
  2. Click SRE Incident Response. The create page opens with this template pre-filled.
  3. Connect any required integrations and install MCP servers if you haven’t already.
  4. Replace any placeholder values in the trigger conditions (for example, swap your-org/your-repo for your actual repo).
  5. Review the prompt and adjust it for your team’s language, conventions, and guardrails.
  6. Click Create automation.
Most automation templates include suggested ACU and invocation limits to bound cost during early rollout. Keep them as-is until you’re confident in the automation’s behavior, then raise them to fit your workload.

​
When to use this template

  • Drastically shortening mean time to investigation (MTTI) on production alerts
  • Giving on-call engineers a baseline investigation report before they even open their laptop
  • Auto-generating incident postmortem drafts from live threads
  • Triaging alerts across dozens of services without a dedicated SRE on every shift

​
Customization ideas

  • Change the reaction emoji (e.g. :fire:, :warning:, team-specific custom emoji)
  • Scope to specific channels per service or region
  • Add the Sentry MCP and Datadog MCP to widen investigation coverage
  • Attach a runbook playbook so Devin follows your team’s standard incident flow

​
See also