The Microsoft Stack
Start Here
Overview and approach
Foundry
The production AI platform
Building Agents
Pro-code and low-code
Data and Retrieval
What grounds the agents
Operating in Production
Running it safely

Foundry IQ

Foundry IQ is the knowledge layer behind Foundry agents: SLA-backed retrieval that unifies enterprise data sources behind one endpoint, built on Azure AI Search. It matters because it replaces the RAG plumbing most projects otherwise build by hand, and agents in Foundry Agent Service consume it directly.

What Foundry IQ Replaces

Without Foundry IQ, building RAG requires: chunking, embedding, indexing, retrieval pipeline, source integration, permission sync - all custom code.

With Foundry IQ: connect data sources, create a knowledge base, wire it to your agent. Foundry handles ingestion, indexing, retrieval, and permissions.

Architecture

Knowledge Sources
SharePoint
Azure Blob
Azure SQL
Fabric Data
Web
Live
Foundry IQ
Ingestion
Layout-aware, image serving
AI Search Index
Vector plus hybrid
Knowledge Bases
SLA-backed retrieval
Agentic Retrieval
Multi-step reasoning
Consumers
Foundry Agents
Copilot Studio
Custom Apps
Over MCP

IQ Components

ComponentStatusDescription
Foundry IQ Knowledge BasesGASLA-backed retrieval over connected data sources
Foundry IQ ServerlessPreviewNo infrastructure provisioning required
Work IQPreviewGrounding in Microsoft 365 data (email, docs, calendar)
Fabric IQPreviewGrounding in Fabric data (semantic models, ontology)
Web IQLimited accessLive web grounding, sub-200ms, zero data retention
Agentic RetrievalGAMulti-step retrieval with reasoning
File SearchGADirect file upload and search

Knowledge Base Setup

from azure.ai.projects import AIProjectClient
from azure.identity import DefaultAzureCredential

client = AIProjectClient(
    credential=DefaultAzureCredential(),
    endpoint="https://my-foundry.services.ai.azure.com"
)

# Create knowledge base connected to Azure AI Search
kb = client.knowledge_bases.create(
    name="product-docs",
    data_sources=[
        {"type": "azure_blob", "connection": "my-blob-connection"},
        {"type": "sharepoint", "connection": "my-sp-connection"}
    ]
)

# Wire to agent
agent = client.agents.create(
    model="gpt-5",
    name="docs-agent",
    tools=[{"type": "foundry_iq", "knowledge_base_id": kb.id}]
)

MCP Access

Knowledge bases are queryable via MCP (Model Context Protocol). Any MCP-compatible client can connect:

Endpoint: https://my-foundry.services.ai.azure.com/mcp

Data Pipeline Features

  • Layout-aware ingestion - understands document structure (headers, tables, lists)
  • Image serving - extracts and serves embedded images
  • Broad SharePoint indexing - libraries, lists, pages
  • Permission sync - respects source ACLs via Purview
  • Sensitivity labels - governance flows through from source to retrieval

Foundry IQ vs Custom RAG

DimensionFoundry IQCustom RAG
Setup timeMinutesDays-weeks
InfrastructureManagedSelf-managed
Permission syncAutomatic (Purview)Manual
Multi-sourceBuilt-inCustom per source
SLAYesDepends on implementation
FlexibilityOpinionatedFull control
Best forStandard enterprise knowledgeCustom retrieval logic, non-Azure sources

Key Takeaways

  • Foundry IQ turns days or weeks of custom RAG plumbing into a managed knowledge base you connect and wire to an agent.
  • Permission sync through Purview means retrieval respects source ACLs without custom code.
  • Knowledge bases are queryable over MCP, so clients outside Foundry can use them too.
  • Build custom RAG only when you need retrieval logic Foundry IQ does not support, or sources outside Azure. Otherwise the managed option wins on setup time and SLA.
  • Serverless, Work IQ, and Fabric IQ are in preview and Web IQ is limited access. Knowledge Bases, Agentic Retrieval, and File Search are GA.

Next: Foundry Tools - IQ gives agents knowledge; Foundry Tools give them pre-built capabilities over documents, speech, and images.