Microsoft's unified AI platform — formerly Azure AI Foundry — for building, deploying, and managing AI apps and agents across 11,000+ models, with enterprise-grade observability, security, and governance.
Foundry is a layered platform: models at the bottom, agents and tools in the middle, knowledge and governance wrapping everything. A single Azure resource provider unifies it all.
A unified catalog of more than 11,000 models — flagship frontier models from Microsoft and partners, plus open and specialized models. Browse, benchmark, fine-tune, and deploy through one consistent inference API.
Call models through a managed endpoint without provisioning infrastructure. Single inference API across providers — switch models with a config change, not a rewrite.
Deploy to dedicated GPU clusters when you need predictable performance, custom fine-tunes, or model formats that don't fit serverless. Provisioned throughput available.
A fully managed runtime for AI agents. Choose your build path — no-code, declarative workflow, or fully custom code — and let Foundry handle hosting, scaling, identity, observability, and enterprise security.
Defined entirely through configuration — instructions, model selection, and tools. Build no-code in the Foundry portal in minutes, or via SDK / REST API.
Orchestrate sequences of actions or coordinate multiple agents using declarative definitions. Visual designer or code-first API. Power Fx expressions for control flow.
Code-based agents built with Agent Framework, LangGraph, or your own framework, deployed as containers. You write logic; Foundry manages runtime and scaling.
From the Foundry catalog. Provides reasoning and language capabilities.
Define goals, constraints, and behavior — prompt-based, workflow-defined, or code.
Provide access to data and actions — search, files, code, custom APIs, MCP servers.
RAG, reimagined as a reasoning task. Foundry IQ treats retrieval as a multi-step plan — query decomposition, source selection, parallel search, and reflection — instead of a one-shot vector lookup. Permission-aware by default.
An LLM analyzes the question and decomposes it into optimal sub-queries.
Routes each sub-query to the right knowledge source — multi-source by default.
Runs hybrid search (vector + keyword + semantic rerank) across selected sources at once.
Honors document ACLs and Purview sensitivity labels under caller's Entra identity.
Evaluates results — re-queries if context is insufficient. Reasoning-style retrieval.
Returns extractive content with citations so agents can trace answers to source documents.
Organizational knowledge — documents, files, web content. The general-purpose knowledge base for any agent.
Semantic layer for Microsoft Fabric — ontologies, semantic models, and graphs over business data.
Contextual layer for Microsoft 365 — collaboration signals from documents, meetings, chats, workflows.
Tools turn LLMs into agents that can act. Foundry provides ready-to-use built-in tools and a unified Toolbox that exposes any custom tool — including remote MCP servers — through a single endpoint to any compatible agent runtime.
Configured in minutes through the Foundry portal. Some are GA, others in preview — most agents need only basic configuration to start.
Wire in any external API, internal service, or remote MCP server. Foundry handles auth, identity, and routing through unified endpoints.
Single MCP-compatible
endpoint · versioned
Foundry separates management from development. IT teams configure security and policy at the Foundry resource level; development teams build inside project containers. One unified portal, one resource provider, one set of controls.
Unified RBAC across models, agents, tools, and knowledge bases. Microsoft Entra-backed identity end-to-end.
Virtual network injection, private endpoints, public network disable for sensitive workloads.
Built-in content safety, prompt injection mitigation (XPIA), and Task Adherence guardrails for agentic workflows.
Tracing, monitoring, and evaluation — all under Azure Monitor. LangChain & LangGraph traces supported natively.
Bring your own storage, Azure SQL, Cosmos DB, AI Search. Customer-managed encryption keys supported.
Inherits Azure's compliance posture — 50+ region-specific certifications. Responsible AI guidance built in.
Run Foundry models on your own hardware — laptops, edge servers, sovereign clouds. Same model catalog, same APIs, no data leaves your environment. For when latency, privacy, or sovereignty rules out the cloud.
Healthcare, defense, finance — where data sovereignty is non-negotiable.
Field operations, retail kiosks, manufacturing floors with intermittent connectivity.
Real-time interactions — voice agents, live coding assistants, gaming NPCs.
Heavy local workloads where per-token cloud pricing breaks the budget.
Iterate on agents and prompts without round-tripping the cloud or burning quota.
Deploy in sovereign or air-gapped clouds where Azure isn't an option.
Microsoft Foundry is the AI app and agent factory — six natively integrated components, one Azure resource, one portal.