SRE Agent documentation

Investigate alerts, fix incidents and keep work tracked with SRE Agent.

SRE Agent is a hosted incident platform. Your monitoring tools send it alerts, an AI agent investigates each one against the metrics and logs you connect, and the result lands in Slack, on a board and, when you want one, in a pull request. It also covers on-call schedules, SLOs, runbooks and a public status page. These guides show you how to set it up and use it day to day.

Quickstart

Go from sign-up to your first investigated alert.

Respond to incidents

Triage an alert, find the cause and track the response.

Fix with pull requests

Turn a diagnosis into a reviewed pull request.

API and MCP

Read and change your organization’s setup over HTTP or from an MCP client.

Where to go next

• On-call engineer: start with Triage alerts, then Run and read an investigation and Set up on-call.
• Team lead: read What is SRE Agent, then Set up SLOs, Write and run runbooks and Track work on the ops board.
• Admin: begin with the Quickstart and Connect your data, then Manage people and roles and Choose a plan and manage billing.

If something is not working, see Troubleshooting.