Foundry IQ launches a developer-focused IQ Series with episodes, notebooks, cookbooks, and visual recaps explaining knowledge-centric AI: ingesting sources, building pipelines, organizing multi-source knowledge bases, querying across sources, and applying samples to build knowledge-driven agent applications.
The IQ Series launches with Foundry IQ on March 18, 2026. It bundles episodes, notebooks, doodle recaps, and cookbooks for developers.
Main feature and impact
Foundry IQ provides a knowledge-centric layer for AI agents. Developers define reusable knowledge bases that connect to documents and data sources. Agents query these bases during multi-step reasoning rather than performing ad hoc retrieval. This reduces duplicated retrieval logic and centralizes context management across applications. The impact is faster prototyping and clearer maintenance of knowledge-driven systems.Practical implications
The series details pipeline, sources, and querying across multi-source knowledge bases. Episode one introduces core concepts and components. Episode two covers ingest from SharePoint, Fabric, OneLake, Blob Storage, Azure AI Search, and the web. Episode three shows how to query and synthesize across combined knowledge sources. Samples and cookbooks are available in the IQ Series repository.“Foundry IQ helps AI systems work with knowledge in a more structured and intentional way.”The IQ Series provides code, notebooks, and visual recaps to apply Foundry IQ concepts. Developers should review the repository, run sample cookbooks, and adapt knowledge bases to their data landscape. Expect iterative updates as feedback arrives and the community shares patterns.
Key points from the article:
Related Coverage:
- Microsoft at NVIDIA GTC: New solutions for Microsoft Foundry, Azure AI infrastructure and Physical AI
- From Prototype to Production: Building a Hosted Agent with AI Toolkit & Microsoft Foundry
- Microsoft Agent Framework, Microsoft Foundry, MCP, Aspire를 활용한 실전 예제 만들기
From the Microsoft Developer Community Blog articles
