In this hands-on lab, you'll build Azure AI Search knowledge bases using agentic retrieval and extend them with multiple source types. Through 5 progressive notebook exercises, you'll build a multi-source document-backed knowledge base, extend it with web search through MCP, add Fabric IQ and Work IQ, and finish by combining Work IQ and Fabric IQ in one KB. By the end, you'll have flexible agentic knowledge bases that blend multiple source types.
To get started in a guided lab session:
- Open the lab environment and sign in with the provided credentials
- Open the notebooks/ folder in Visual Studio Code
- Start with part1-standard-foundry-iq-kb.ipynb and work through all 5 notebooks sequentially
Follow the steps in the self-deployment guide.
By the end of this session, you will be able to:
- Build a multi-source knowledge base over indexed enterprise content using Azure AI Search agentic retrieval
- Extend a knowledge base with Web IQ, Fabric IQ, and Work IQ knowledge sources
- Combine multiple source types (indexed, structured, workplace, and web-grounded) in a single knowledge base
- Query knowledge bases with citation-backed answer synthesis
- Foundry IQ (Azure AI Search)
- Azure OpenAI (gpt-5.4-mini, text-embedding-3-large)
- Model Context Protocol (MCP)
- Microsoft Fabric IQ and Work IQ
- Python and Jupyter Notebooks
| Resource | Description |
|---|---|
| Azure AI Search | Full capabilities of Azure AI Search |
| Design an index for agentic retrieval | Best practices for structuring data for agentic retrieval |
| Create a knowledge base | Step-by-step guide to creating and configuring knowledge bases |
| Answer synthesis | Generate grounded answers with citations |
| https://aka.ms/build26-next-steps | Take the next step in your learning journey after Build 2026 |
Find other developers, like you, building on Microsoft Foundry in Discord
 Pamela Fox 📢 |
 Matt Gotteiner 📢 |
 Ayca Bas 📢 |
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.
