High performance agents are built on intelligence that brings together context, enterprise data, orchestration, and governance. Learn how Foundry IQ, Fabric IQ, and Work IQ provide the enterprise intelligence layer for AI agents. Design agents that can search across organizational knowledge, reason over business data, and operate with awareness of people and work signals. Take action within trusted boundaries, providing a practical foundation for building scalable and reliable agents.
The demo source code for this session lives in the microsoft/iq-samples repository.
- Browse the demo source code at github.com/microsoft/iq-samples
- Clone the repository and follow the setup instructions in its README
- Explore each demo to see how Foundry IQ, Fabric IQ, and Work IQ compose into a single agent
By the end of this session, you will be able to:
- Understand how Foundry IQ, Fabric IQ, and Work IQ form the enterprise intelligence layer for AI agents
- Design agents that search across organizational knowledge, reason over business data, and operate with awareness of people and work signals
- Apply context, orchestration, and governance so agents take action within trusted boundaries at scale
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!
- Understand the core idea:
Explain how context-aware agents work and how an intelligence layer of context, enterprise data, orchestration, and governance makes them reliable at scale.
- Go deeper:
How does Foundry IQ use knowledge bases and agentic retrieval to ground an agent in enterprise knowledge? Walk me through the key pieces.
- Bring in work context:
How does Work IQ give agents context from Microsoft 365 — people, files, meetings, and workflows — and how is it built for agents rather than humans?
- Build something:
Using the samples at github.com/microsoft/iq-samples, walk me through how the refund agent combines Foundry IQ, Fabric IQ, and Work IQ.
- Microsoft Foundry IQ — reusable knowledge bases and agentic retrieval to ground agents in enterprise knowledge
- Fabric IQ — semantic models and ontologies that give agents a unified view of how your business operates
- Work IQ — workplace intelligence over Microsoft 365 people, files, and workflows, built for agents
- Microsoft Foundry — platform for building, evaluating, and deploying AI agents
- Microsoft Fabric — unified data platform underpinning Fabric IQ
- Agent 365 — control plane to observe, secure, and govern AI agents across your organization
| Resource | Description |
|---|---|
| Microsoft IQ | Learn more about the Microsoft IQ platform |
| Foundry IQ | Knowledge platform and agentic retrieval for agents |
| Fabric IQ | Semantic models and ontologies for business context |
| Work IQ | Workplace intelligence for agents over Microsoft 365 |
| microsoft/iq-samples | Source code for the demos shown in this session |
| microsoft/iq-series | Series of videos and hands-on tutorials on Microsoft IQ |
| Join the conversation | Microsoft IQ community discussions |
The Microsoft Learn MCP Server gives your AI agent direct access to Microsoft's official documentation — grounded, up-to-date answers about the products and services covered in this session.
VS Code — One click installation:
GitHub Copilot CLI — Run this to install the Learn MCP Server as a plugin:
/plugin install microsoftdocs/mcp
For more info, other clients, and to post questions, visit the Learn MCP Server repo.
Want to go deeper with a guided, self-paced walkthrough? Build Lab 532 — From Data to Context: Agent-Ready Knowledge with Foundry IQ takes you from raw data to a grounded, agent-ready knowledge base step by step.
| Resource | Description |
|---|---|
| Build Lab 532 | The full hands-on lab |
| Self-deployment guide | Deploy and run the lab yourself, at your own pace |
 Marco Casalaina GitHub · LinkedIn |
 Amanda Silver GitHub · LinkedIn |
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.
