Note
Access to this page requires authorization. You can try signing in or changing directories.
Access to this page requires authorization. You can try changing directories.
Azure SRE Agent automates operational work and reduces toil, so developers and operators can focus on high-value tasks.
Typical operational tasks often include managing multiple Azure resources along with on-premises and SaaS systems. These tasks are often repetitive or require orchestrating together multiple tools to provide the insights you need. SRE Agent gives you an AI-driven platform to connect systems together and automate the workflow end-to-end.
What is SRE Agent?
SRE Agent is a service that brings automation and intelligence to site reliability engineering practices. It helps you reduce manual effort, improve system uptime, and deliver consistent operational outcomes. As the agent integrates with both Azure services and external systems, it executes operational tasks with minimal human intervention.
Primary use cases
Automate incidents: Connect to incident management platforms to automate triage, mitigation, and resolution, reducing mean time to recovery (MTTR) and improving service availability.
Automate scheduled workflows: Set up proactive alerting and actions to automate routine and repetitive tasks that run on a defined schedule.
To see SRE Agent in action, watch the following video.
How does SRE Agent work?
SRE Agent combines fine-tuned Azure expertise with full customization capabilities. Out of the box, SRE Agent understands and manages Azure resources for specific services, providing intelligent defaults for common operational tasks. At the same time, it offers flexibility to incorporate domain-specific knowledge, custom runbooks, and integrations with tools and data sources such as observability and monitoring platforms. This extensibility ensures that SRE Agent can adapt to your environment and operational requirements.
Integrations
Azure SRE Agent integrates with your operational ecosystem in the following ways:
Monitoring and observability:
- Azure Monitor (metrics, logs, alerts, workbooks)
- Application Insights
- Log Analytics
- Grafana
Incident management:
- Azure Monitor Alerts
- PagerDuty
- ServiceNow
Source control and CI/CD:
- GitHub (repositories, issues)
- Azure DevOps (repos, work items)
Data sources:
- Azure Data Explorer (Kusto) clusters
- Model Context Protocol (MCP) servers
Get started
Get started working with Azure SRE Agent by scheduling a task, handling an incident, or building a subagent.
Create a scheduled task to run on a schedule you define.
Select the Schedule tasks tab.
Enter task details.
Define the schedule to run your task.
Craft custom agent instructions for the task.
Select Create scheduled task.
Considerations
Keep the following considerations in mind as you use Azure SRE Agent:
- English is the only supported language in the chat interface.
- For more information on how data is managed in Azure SRE Agent, see the Microsoft privacy policy.
- Availability varies by region and tenant configuration.
When you create an agent, the following resources are also automatically created for you:
- Azure Application Insights
- Log Analytics workspace
- Managed Identity