Microsoft Foundry
Microsoft's unified AI app and agent factory, formerly Azure AI Foundry.
About
Microsoft Foundry (formerly Azure AI Foundry, originally Azure AI Studio) is Microsoft's unified platform for building AI applications and agents. It consolidates Azure OpenAI Service, model catalog, agent runtime, and governance into one portal and SDK surface, with an 11,000+ model catalog including day-zero GPT-5.x access through Microsoft's OpenAI partnership.
The February 2026 update added multi-agent orchestration, Model Context Protocol support, hosted agents, Foundry Local for sovereign deployments, and one-click publishing to Teams and Microsoft 365 Copilot. The Microsoft Agent Framework (Semantic Kernel + AutoGen, MIT) provides the code-first SDK. Limitation: regional deployments can carry 25-50% price premiums over US rates, and the platform is most compelling for organizations already standardized on Microsoft's stack.
What it can do
- 11,000+ model catalog with managed inference
- Foundry Agent Service with hosted sandboxed agents
- Multi-agent orchestration and MCP/A2A support
- Evaluation, red-teaming, and observability tooling
Setup
Create a Foundry project in the Azure portal; install the SDK for Python or .NET.
Prerequisites
An Azure subscription; Entra ID for agent identity features.
Use cases
Works with
Trust score — 9/10
Scored 9/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 63; Trending score 87/100 from researcher assessment.
Sources
Every fact above was checked against these sources. Where a claim comes from the provider and couldn't be independently verified, the text says so.