Post-Incident Review · Sentry, Linear & Slack

What you can do

A few things this template does well out of the box.

• Generate post-mortem documents from Sentry error data automatically
• Create Linear issues with root cause, timeline and remediation steps
• Post incident summaries to Slack with severity, impact and resolution
• Identify recurring error patterns across incidents

How it works

Three steps to go from template to a live chat.

MCP servers used

The endpoints this template connects to by default. You can swap any of them in Agent Studio.

Getting your access token

A quick walkthrough for the credential this template needs.

1. 1Sentry → **Settings** → **Auth Tokens** → create a token with project:read and event:read scopes.
2. 2Linear → **Settings** → **API** → create a personal API key.
3. 3Slack → **api.slack.com** → your app → **OAuth** → copy the Bot User token.

Try these prompts

Copy one into the studio to see the agent in action.

• We just resolved an outage. Pull the last 2 hours of errors from Sentry, identify the root cause, and create a post-mortem issue in Linear.

• Summarise the Sentry errors from today's incident — timeline, affected services, stack traces — and post it to #incidents on Slack.

• Create a P0 Linear issue for today's database connection timeout. Include the Sentry error link, root cause hypothesis, and 3 remediation action items.

• Look at our Sentry errors from the past week. Are there any recurring patterns that we should file as tech debt in Linear?

System prompt

The default instructions the model starts with. Edit it any time inside Agent Studio.

You are an incident response assistant connected to Sentry, Linear and Slack.

Use the available tools to:
- Pull error events, stack traces, breadcrumbs and affected users from Sentry
- Construct a timeline of the incident from first error to resolution
- Create structured post-mortem issues in Linear with: summary, timeline, root cause, impact, remediation steps and action items
- Post incident summaries to Slack with severity level, duration, affected services and resolution status

Use a blameless tone — focus on systems and processes, not individuals. Include links to relevant Sentry issues. Confirm severity and channel before posting to Slack.