--- title: Build Intelligent Agents with Work IQ, Foundry IQ, and... description: A walkthrough of Microsoft's suite of knowledge layers - Work IQ, Foundry IQ, Fabric IQ, and Web IQ - and how they feed into building intelligent agents. Work... canonical: https://daily.dev/posts/build-intelligent-agents-with-work-iq-foundry-iq-and-fabric-iq-yrnu99yim twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Build Intelligent Agents with Work IQ, Foundry IQ, and Fabric IQ | daily.dev og:description: A walkthrough of Microsoft's suite of knowledge layers - Work IQ, Foundry IQ, Fabric IQ, and Web IQ - and how they feed into building intelligent agents. Work... og:url: https://daily.dev/posts/build-intelligent-agents-with-work-iq-foundry-iq-and-fabric-iq-yrnu99yim og:image: https://api.daily.dev/og/posts/YRNu99yIm.png og:image:alt: Build Intelligent Agents with Work IQ, Foundry IQ, and Fabric IQ og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Build Intelligent Agents with Work IQ, Foundry IQ, and Fabric IQ **[Microsoft Developer](https://daily.dev/sources/microsoftdeveloper)** · 28 min read · 1 upvotes · 0 comments ## Summary A walkthrough of Microsoft's suite of knowledge layers - Work IQ, Foundry IQ, Fabric IQ, and Web IQ - and how they feed into building intelligent agents. Work IQ surfaces data from Microsoft 365 (email, chat, meetings, memory), Foundry IQ enables agentic retrieval across enterprise sources beyond M365 (blob storage, SQL, Cosmos DB) improving on classic RAG's single-source limitations, and Fabric IQ handles structured data with ontologies and knowledge graphs, converting natural language into SQL via data agents. Web IQ adds internet-sourced insight. The session demonstrates building a sales briefing agent in Copilot Studio that combines all four IQ layers - pulling sales stats from Fabric, product improvement details from Foundry IQ-indexed documents, and competitor research from the web - all accessible through Microsoft Teams. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is the difference between Foundry IQ's agentic retrieval and traditional RAG in Azure AI Search? Foundry IQ's agentic retrieval fetches and federates answers across multiple knowledge sources simultaneously, such as Azure Blob Storage, SQL tables, and other line-of-business systems, with permissions enforced at the source level. Traditional RAG, by contrast, is limited to one-shot vector similarity search against a single indexed source, and implementing granular permissions is harder to achieve. _Developers evaluating retrieval architectures can compare RAG and agentic retrieval patterns through daily.dev._ ### How does Fabric data agent convert natural language questions into SQL queries? A Fabric data agent takes a natural language query, automatically converts it into an underlying SQL statement to run against connected SQL tables, and then returns the result back in natural language by combining the agent instructions with the user prompt. This lets a sales agent ask things like top-selling products without writing SQL manually. _Teams building natural-language data agents can follow related implementation patterns on daily.dev._ ### What are Work IQ, Foundry IQ, Fabric IQ, and Web IQ in the Microsoft agent stack? Work IQ reasons over Microsoft 365 data like email, meetings, files, and chat with per-user persistent memory and security trimming. Foundry IQ provides agentic retrieval across enterprise sources such as Azure Blob Storage, SQL, and Cosmos DB. Fabric IQ handles structured and unstructured data with ontologies, knowledge graphs, and data agents. Web IQ retrieves information from the public internet. _Architects comparing Microsoft's knowledge layers for agent design can track these updates on daily.dev._ ## Similar posts on daily.dev - [Work IQ: The Foundational Intelligence Layer for Modern Enterprise AI](https://daily.dev/posts/work-iq-the-foundational-intelligence-layer-for-modern-enterprise-ai-klpdox7df) · C\# Corner · 1 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#microsoft-fabric](https://daily.dev/tags/microsoft-fabric) [View this post on daily.dev](https://daily.dev/posts/build-intelligent-agents-with-work-iq-foundry-iq-and-fabric-iq-yrnu99yim) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Build Intelligent Agents with Work IQ, Foundry IQ, and Fabric IQ","url":"https://daily.dev/posts/build-intelligent-agents-with-work-iq-foundry-iq-and-fabric-iq-yrnu99yim","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/build-intelligent-agents-with-work-iq-foundry-iq-and-fabric-iq-yrnu99yim"},"datePublished":"2026-08-24T21:28:47.857Z","dateModified":"2026-09-14T08:37:58.965Z","description":"A walkthrough of Microsoft's suite of knowledge layers - Work IQ, Foundry IQ, Fabric IQ, and Web IQ - and how they feed into building intelligent agents. Work...","image":"https://i.ytimg.com/vi/1FfowsCdnxQ/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/1FfowsCdnxQ/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Microsoft Developer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Microsoft Developer","logo":"https://media.daily.dev/image/upload/s--xZzU3zUq--/f_auto/v1746714872/logos/microsoftdeveloper","url":"https://daily.dev/sources/microsoftdeveloper"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/build-intelligent-agents-with-work-iq-foundry-iq-and-fabric-iq-yrnu99yim","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,microsoft-fabric","timeRequired":"PT28M","video":{"@type":"VideoObject","name":"Build Intelligent Agents with Work IQ, Foundry IQ, and Fabric IQ","description":"A walkthrough of Microsoft's suite of knowledge layers - Work IQ, Foundry IQ, Fabric IQ, and Web IQ - and how they feed into building intelligent agents. Work...","thumbnailUrl":"https://i.ytimg.com/vi/1FfowsCdnxQ/sddefault.jpg","uploadDate":"2026-08-24T21:28:47.857Z","duration":"PT28M","url":"https://api.daily.dev/r/YRNu99yIm","embedUrl":"https://www.youtube.com/embed/1FfowsCdnxQ"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Microsoft Developer","item":"https://daily.dev/sources/microsoftdeveloper"},{"@type":"ListItem","position":3,"name":"Build Intelligent Agents with Work IQ, Foundry IQ, and Fabric IQ"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/build-intelligent-agents-with-work-iq-foundry-iq-and-fabric-iq-yrnu99yim#faq","mainEntity":[{"@type":"Question","name":"What is the difference between Foundry IQ's agentic retrieval and traditional RAG in Azure AI Search?","acceptedAnswer":{"@type":"Answer","text":"Foundry IQ's agentic retrieval fetches and federates answers across multiple knowledge sources simultaneously, such as Azure Blob Storage, SQL tables, and other line-of-business systems, with permissions enforced at the source level. Traditional RAG, by contrast, is limited to one-shot vector similarity search against a single indexed source, and implementing granular permissions is harder to achieve. Developers evaluating retrieval architectures can compare RAG and agentic retrieval patterns through daily.dev."}},{"@type":"Question","name":"How does Fabric data agent convert natural language questions into SQL queries?","acceptedAnswer":{"@type":"Answer","text":"A Fabric data agent takes a natural language query, automatically converts it into an underlying SQL statement to run against connected SQL tables, and then returns the result back in natural language by combining the agent instructions with the user prompt. This lets a sales agent ask things like top-selling products without writing SQL manually. Teams building natural-language data agents can follow related implementation patterns on daily.dev."}},{"@type":"Question","name":"What are Work IQ, Foundry IQ, Fabric IQ, and Web IQ in the Microsoft agent stack?","acceptedAnswer":{"@type":"Answer","text":"Work IQ reasons over Microsoft 365 data like email, meetings, files, and chat with per-user persistent memory and security trimming. Foundry IQ provides agentic retrieval across enterprise sources such as Azure Blob Storage, SQL, and Cosmos DB. Fabric IQ handles structured and unstructured data with ontologies, knowledge graphs, and data agents. Web IQ retrieves information from the public internet. Architects comparing Microsoft's knowledge layers for agent design can track these updates on daily.dev."}}]} ```