microsoft/iq-series

The IQ Series is a hands-on learning experience for Microsoft IQ: Microsoft's unified intelligence layer for the enterprise, spanning Foundry IQ, Work IQ, and Fabric IQ. The series includes video episodes, Jupyter notebooks, and Azure deployment templates.

What it solves

AI agents often lack the context to understand a business, its knowledge, and current web information. The IQ Series addresses this by introducing Microsoft's unified intelligence layer—Fabric IQ, Foundry IQ, Work IQ, and Web IQ—which together give agents the grounding they need to reason, retrieve, and act effectively. It goes beyond traditional RAG to provide enterprise-grade intelligence.

How it works

The series combines short video episodes (around 15–20 minutes each) with hands-on Jupyter notebook cookbooks or markdown labs. Each episode covers a specific topic, such as building data pipelines, querying multi-source knowledge bases, or using protocols like A2A and MCP. Learners can follow along with the cookbooks step by step, and by completing all cookbooks for an IQ they can earn a community badge.

Who it’s for

This is for developers, AI engineers, and enterprises building AI agents that need to understand business semantics, internal knowledge, work patterns, and live web data. It’s also useful for anyone wanting to learn Microsoft’s IQ services through practical exercises.

Highlights

  • Four core intelligence services: Fabric IQ (business), Foundry IQ (knowledge), Work IQ (work), and Web IQ (web).
  • Episodes premiering weekly on Microsoft Developer YouTube, with Foundry IQ and Work IQ available now.
  • Hands-on cookbooks and labs in Jupyter notebooks or markdown format.
  • Community badges for completing each IQ’s cookbooks, issued by the Global AI Community.
  • Complementary resources: Microsoft IQ Deep Dive and Microsoft IQ Live for further learning.

Related

  • Project
    YangDai2003/Kori

    A cross-platform note-taking app with support for Markdown, LaTeX, and Mermaid diagrams, featuring an optional AI co-writer that connects to various LLM providers.

  • Project
    Softlandia-Ltd/vision-is-all-you-need

    A Vision RAG (V-RAG) demo that embeds PDF pages as images using a VLM to eliminate the need for text chunking during document retrieval.

  • Project
    Ed1s0nZ/PrivHunterAI

    A local permission detection workbench that captures HTTP traffic and uses LLMs to analyze credential replacement tests to find authorization vulnerabilities.

  • Project
    imbue-ai/bouncer

    Bouncer is a browser extension that uses AI to semantically filter and hide unwanted posts from your Twitter/X feed based on natural language topics.