What can an AI agent do with Azure?

An AI agent can list and inspect your Azure resources, check VM health, pull cost and usage reports, and take actions like starting or stopping VMs and creating resource groups. Think of it as an AI agent that handles routine cloud ops tasks on demand - surfacing the right information and acting on your behalf, with your approval for any write operations.

Is it safe to connect Azure to an AI worker?

Yes. Read-only actions like listing VMs or fetching cost data are shown to you before they run, and any write action - such as stopping a VM or creating a resource group - requires your explicit approval before it executes. Your autonomous AI will never make infrastructure changes without you signing off.

Which Azure services does the integration support?

The integration currently covers core Azure Resource Manager services: resource groups, virtual machines, storage accounts, and cost management. This covers the most common cloud ops workflows for monitoring infrastructure health and controlling spend.

Can I use this across multiple Azure subscriptions?

Yes. You can configure the integration with credentials scoped to one or more subscriptions. Your AI agent can then query and act across whichever subscriptions you've granted access to, making it easy to get a unified view of your cloud environment.

Developer tools

Azure, run by an agent.

An AI agent that monitors, manages, and optimizes your Azure resources.

Connect Azure Book a demo

What needs your approval

Azure never changes anything without you.

Anything that creates, edits or deletes in Azure waits for your approval. Approve a recurring task once and it runs unattended after that.

Connecting Azure

About 5 minutes

Auth: API key
Setup: About 5 minutes

Where to get access

Create a service principal: az ad sp create-for-rbac. Paste as JSON: {"tenant_id": "...", "client_id": "...", "client_secret": "...", "subscription_id": "..."}

learn.microsoft.com