Microsoft Foundry Blog
Your source for learning and building with our models, agents, and tools.
Featured posts
Build and run agents at scale with Microsoft Foundry at Build 2026
Learn how Microsoft Foundry helps developers build, deploy, and operate production-ready agents with Agent Framework, Toolboxes, hosted agents, Microsoft 365 di...
Foundry IQ: Build smarter agents faster with unified knowledge and serverless retrieval
Learn how Foundry IQ helps developers ground agents with unified enterprise knowledge, serverless retrieval, improved agentic retrieval quality, and production-...
What’s new in Microsoft Foundry | Build Edition
Microsoft Build 2026 brings a major set of Microsoft Foundry updates for developers building agents: hosted runtimes, Toolboxes, memory, Voice Live, Foundry IQ,...
Latest posts
Building Agents that Act on Your Behalf with Toolboxes in Foundry
How Toolboxes in Foundry simplify user delegation At some point, many agents move from answering questions to taking action. And when it does, the question becomes: whose identity is it acting with? Imagine you are building an internal employee agent. It needs to call a private, Entra-protected MCP server for orders, and it also needs to use Microsoft’s managed Work IQ MCP server to reason over the employee’s Microsoft 365 context. In both cases, the agent can’t run as a managed identity or service account. It has to act as the real signed-in user — with that user’s permissions, access boundaries, and data pr...
What’s New in Microsoft Foundry | June 2026
Claude is now generally available in Microsoft Foundry. Here's everything else that shipped between Build 2026 and the end of June — autopilot agents, expanded Toolboxes and Routines, Agent Optimizer's private preview, and more.
Outcome-driven learning systems: Enterprise RL with OpenEnv and Foundry
We shipped a lot at Build 2026: hosted agents, Toolboxes, Foundry IQ, Memory, Managed Compute, fine‑tuning, Frontier Tuning, and a new evaluation and optimization stack. Read as a feature list, it is a lot to hold in your head. So here is a simpler way to see it: these are the parts you need to build a learning system, with agents that get measurably better at your work over time, not a chatbot that answers once and forgets. This post is about assembling those parts into one loop you own, and the science that makes a small, owned model worth training. It builds on two pieces worth reading first. Jay Pari...
Accelerate Edge AI Development with Foundry Local
Why edge AI development is still hard AI is no longer confined to cloud experiments. Developers are increasingly expected to deliver AI inside apps, devices, and edge systems where responsiveness, privacy, resilience, and local control are essential. But building those experiences for production is still difficult. Teams often have to solve model packaging, runtime fragmentation, hardware differences, and deployment complexity before they can ship a single reliable feature. That slows iteration and makes it harder to move from prototype to product. At Microsoft Build 2026, we’re announcing updates acros...
Build 2026: From observability to ROI for AI agents on any framework
9 min read · June 3, 2026 · Sebastian Kohlmeier Shipping an AI agent is the easy part. Keeping it accurate, safe, and accountable in production is where teams get stuck. Agents are non-deterministic. Their behavior shifts as models update, tools change, and traffic patterns evolve and most of that drift happens silently, long after the demo. End-to-end observability covering the full development lifecycle is how you close that gap: See every step an agent takes, evaluate quality and safety against criteria you define, optimize what isn’t working, and prove the business value of what is. This spring w...
Expanding the Reach of Document Translation – New Capabilities Announced at Microsoft Build
Learn how new Document Translation capabilities in Azure Translator, available in Foundry Tools, help developers translate images, PDFs, Office files, DITA, XLIFF, and future LLM-powered document workflows.
Announcing Foundry Managed Compute: Run open models in Microsoft Foundry
Microsoft Foundry Managed Compute is a new GPU platform-as-a-service for hosting open-source and custom AI models behind the same endpoint, SDKs, and bill as frontier models.
Introducing Agent Optimizer in Foundry Agent Service
With hosted agents, we made it straightforward to build and deploy agents on Foundry. You write your logic, run azd deploy, and your agent is live. But “live” and “production-ready” aren’t the same thing. The gap shows up quickly. Your customer support agent handles requests, but it forgets to ask for an order number before looking up status. It answers warranty questions without checking the purchase date. It gives electrical wiring advice when it should decline and recommends a professional. Each fix means rewriting your system prompt, testing by hand, and hoping you didn’t break something else in the proces...
Making agent memory more reliable, transparent, and production-ready
Memory has always mattered for personalization and continuity. But as customers move agents from demos into production, another requirement becomes just as important: reliability. Enterprise teams need agents that not only remember facts, but also apply what they have learned to follow procedures consistently, recover from repeated failure modes, and complete tasks with greater confidence over time. Memory in Foundry Agent Service is built for this shift, with new procedural memory capability, management experiences, and a set of new features such as time-to-live that give developers more visibility and cont...