Edit

Run your first investigation with Azure SRE Agent

Estimated time: 5 minutes

Ask the agent to investigate an issue by using the context connected to your agent.

Tip

New customers can evaluate SRE Agent without paying the always-on charges for the first 30 days. For more information, see Evaluate SRE Agent.

What you accomplish

By the end of this guide, you:

  • Ask the agent to investigate a live issue in chat
  • Watch it use the code, logs, and Azure resources available to it
  • Review a diagnosis grounded in the connected sources

Prerequisites

Requirement Details
Completed Steps 1–2 Create and set up and Team onboarding.
Recommended context Connect code, logs, and Azure resources for richer results. You can still investigate with partial setup.

Tip

You can still run an investigation without all data sources connected, but the results are richer with code and telemetry. Optional Azure resource access can add live resource context. To complete your setup, see Complete your setup.

Start the investigation

Open a new chat thread and describe the problem you want the agent to investigate.

  1. Select New thread in the left sidebar.

  2. Describe the problem you want investigated. Be specific about which service or resource group is affected. For example:

    "Users report that the Add to Cart feature on our app is broken. The cart API returns errors. Can you investigate the container apps in the resource group?"

  3. Select Send.

Screenshot of the chat input with an investigation request describing a broken cart API.

Watch the agent work

The agent builds an investigation plan and executes it step by step. You can watch each phase in real time.

Phase 1: Read context: The agent reads the knowledge files it built during onboarding, including architecture docs, team context, and runbooks, to orient itself.

Phase 2: Explore code: If you connect a code repository, the agent reads relevant source files, searches for code paths related to the issue, and traces the call chain.

Screenshot of the agent reading source code files and identifying a memory leak in CartController.cs.

Phase 3: Query Azure resources: If you connect Azure resources and logging providers, the agent checks the live resource state and available telemetry.

Phase 4: Deliver the diagnosis: Based on the available evidence, the agent can present the following details:

  • Root cause: The specific code bug or configuration issue, with file and line number references.
  • Evidence: Code snippets, logs, and resource details that support the finding.
  • Recommended fix: Exactly what to change, with a code diff showing lines to remove or modify.

Screenshot of the agent presenting root cause analysis with a code fix and crash log evidence.

Checkpoint: The response identifies the sources used and explains the diagnosis or the next data source needed. When you connect code, logs, and Azure resources, the response can include code references, telemetry evidence, and a recommended fix.

Tip

Try asking about something real in your environment:

  • "Check the health of the container apps in resource group X."
  • "We're seeing 5xx errors on our API. Can you investigate?"
  • "What recent changes were deployed to our backend service?"

Next step