Learn how Windows 365 delivers secure and preconfigured computing environments for AI agents, and how you can combine that with computer use to accelerate the creation and deployment of AI agents in enterprise environments. Through technical demos, this session shows how to set up Cloud PCs and how agentic AI interacts with live apps and UIs, while keeping governance, identity, and enterprise controls built in.

Navigate to https://labondemand.com/Event/Room/dbbd79bd-ce56-4884-9075-ff9891e73051 Select Lab 550.

Some of these steps require time to get set up, such as:

• Join the Security group to request an Azure subscription for your tenant.
• After joining, request the Azure subscription (manager approval is required).
• In your tenant, request the Copilot Studio add-on, which can take up to 24 hours.

Ensure your tenant includes:

• An Azure subscription attached to the tenant
• The ability to set up Microsoft 365 Copilot pay-as-you-go (PayGo) configuration in Azure (resource group + security group)
• Copilot Studio author access
• A Dataverse database in the target environment
• Global or tenant admin credentials for the demo tenant (or equivalent permissions to complete tenant + Power Platform admin tasks)
• Ability to complete MFA (Multi‑Factor Authentication) enrollment for each user.

Follow the Microsoft Learn guidance as you go through these steps starting with number three by copying the commands into the PowerShell window: Use Cloud PC pool for computer user runs (preview) - Microsoft Copilot Studio | Microsoft Learn

Once you have set up your environment, you will be able to verify that your tenant is set up properly using this refeence checker: https://dweinerhls.github.io/windows365-cua-checker/ When you run this in your tenant, any issues will be found with options to remediate.

By the end of this lab session, you will be able to:

(Aligned with Bloom’s Taxonomy verbs and lab context) • Configure and use Computer Use Agents to empower intelligent and automated information retrieval. (Apply) • Implement CUA workflows to automate common tasks (Apply) • Understand the integration of Windows 365 for Agents with Copilot Studio to identify opportunities for AI-driven automation. (Analyze) • Design and publish a custom Copilot experience that interacts with Windows 365 services. (Create) • Validate that AI-driven workflows comply with organizational security and Zero Trust requirements. (Evaluate)

Try these prompts with GitHub Copilot to explore the topics from this session. Open Copilot Chat in VS Code (Ctrl+Alt+I on Windows/Linux, Cmd+Shift+I on Mac), paste a prompt, and see what you learn. Try connecting the Microsoft Learn MCP Server for the latest official documentation.

Use these as a starting point — or write your own!

"Where can I learn more about onboarding Agent 365-licensed agents linked to Windows 365 for Agents Provisioning Policies?"

"How can I create an agent from scratch that uses the Windows 365 for Agents MCP Server for computer use?"

1. Microsoft 365 Copilot - https://learn.microsoft.com/en-us/microsoft-365/copilot/
2. Microsoft Copilot Studio - https://learn.microsoft.com/en-us/microsoft-copilot-studio/
3. Windows 365 for Agents - https://learn.microsoft.com/en-us/windows-365/agents/
4. Python - https://www.python.org/

The Microsoft Learn MCP Server is a remote MCP Server that enables clients like GitHub Copilot and other AI agents to bring trusted and up-to-date information directly from Microsoft's official documentation. Get started by using the one-click button above for VSCode or access the mcp.json file included in this repo.

For more information, setup instructions for other dev clients, and to post comments and questions, visit our Learn MCP Server GitHub repo at https://github.com/MicrosoftDocs/MCP. Find other MCP Servers to connect your agent to at https://mcp.azure.com.

Note: When you use the Learn MCP Server, you agree with Microsoft Learn and Microsoft API Terms of Use.

@thomassx

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit Contributor License Agreements.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.