| [ Web Proxy ] |
| Viewing: https://devblogs.microsoft.com/foundry/ | [Back] [Original] |
[Microsoft]
Dev Blogs
AI
All .NET posts
.NET MAUI
ASP.NET Core
Blazor
Entity Framework
C++
C#
F#
TypeScript
NuGet
Servicing
.NET Blog in Chinese
Microsoft for Developers
Agent Framework
Develop from the cloud
Xcode
ISE Developer
TypeScript
PowerShell
Python
Java
Java Blog in Chinese
Go
Microsoft Edge Dev
Microsoft 365 Developer
Microsoft Entra Identity Developer
Microsoft Entra PowerShell
Visual Studio
Visual Studio Code
Aspire
All things Azure
Azure SDK
Azure VM Runtime Team
Microsoft Azure
Azure Cosmos DB
Azure DocumentDB
Azure Data Studio
Azure SQL
DevOps
DirectX
Microsoft Foundry
Power Platform
OData
Unified Data Model (IDEAs)
Windows Command Line
#ifdef Windows
Inside MSIX
MIDI and music
React Native
The Old New Thing
Windows Developer
Your source for learning and building with our models, agents, and tools.
Learn how Microsoft Foundry helps developers build, deploy, and operate production-ready agents with Agent Framework, Toolboxes, hosted agents, Microsoft 365 di...
Learn how Foundry IQ helps developers ground agents with unified enterprise knowledge, serverless retrieval, improved agentic retrieval quality, and production-...
Microsoft Build 2026 brings a major set of Microsoft Foundry updates for developers building agents: hosted runtimes, Toolboxes, memory, Voice Live, Foundry IQ,...
Structured outputs, web search, web fetch, MCP connector, and tool search are now available for Claude models hosted on Azure in Microsoft Foundry, turning a model endpoint into a production agent platform.
Enterprise content is no longer just something people read. AI apps and agents are only as useful as the information they can understand, yet much of the worlds enterprise knowledge is locked in documents, forms, tables, images, audio, and video. The latest Azure Content Understanding updates help developers turn that content into structured, grounded data with less custom processing. This release brings broader support for the GPT-5 model series, lower token usage, improved confidence scoring, new synchronous APIs for Read and Layout, advanced contextualization for higher-quality extraction, new tax-focused pre...
Enterprise content is no longer just something people consume. As organizations increasingly rely on AI to extract and act on information from documents, images, audio, and video, Azure Content Understanding is expanding support for the GPT-5 series and improving grounding and confidence to deliver greater flexibility, efficiency, and quality. This expanded model catalog enables organizations to choose the right level of intelligence for each workload, helping reduce costs for high-volume processing while preserving access to advanced reasoning capabilities where needed. It also provides optimized pipelines tu...
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: whoseidentity isitactingwith?Imagineyouare building aninternalemployeeagent.It needsto callaprivate, Entra-protectedMCP server for orders, and it also needs to use Microsofts managed Work IQ MCP server to reason over the employees Microsoft 365 context. In both cases, the agent cant run as amanaged identity or service account. It has to act as thereal signed-in user with that users permissions, access boundaries, and data pr...
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.
We shipped a lot at Build 2026: hosted agents, Toolboxes, Foundry IQ, Memory, Managed Compute, finetuning, 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...
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 oftenhave tosolve 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,wereannouncing updates acros...
9 min read June 3, 2026 Sebastian Kohlmeier Shipping an AI agent is the easy part. Keeping itaccurate, safe, and accountable in production is where teams get stuck. Agents arenon-deterministic. Their behavior shifts as models update, tools change, and traffic patternsevolveand most of that drift happens silently, long after the demo.End-to-end observabilitycovering the full development lifecycle is how you close that gap: See every step an agent takes, evaluate quality and safety against criteria you define,optimizewhatisntworking, and prove the business value of what is. This spring w...
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.
Securely design, customize, and manage AI applications and agents at scale with Microsoft Foundry.
Get started| Web Proxy Viewer | New URL | Original Page |
![[Build and run agents at scale with Microsoft Foundry at Build 2026]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/2026/06/Untitled-June-02-2026-at-00.14.50-1-1.webp){kind=link}
![[]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/2026/05/profile-circle-96x96.webp){kind=link}
![[Foundry IQ: Build smarter agents faster with unified knowledge and serverless retrieval]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/2026/06/Slide5.webp){kind=link}
![[]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/2026/05/MS-Execs-2021-07-Castro-Pablo-005-2-cropped-sub2M-96x96.webp){kind=link}
![[What’s new in Microsoft Foundry | Build Edition]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/2026/06/Slide3.webp){kind=link}
![[]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/2025/03/nick-brady-96x96.png){kind=link}
![[]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/2026/08/Image-3-96x96.webp){kind=link}
![[]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/2025/11/Peyton-Profile-Picture-OLD-96x96.webp){kind=link}
![[]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/2025/11/1697763773376-96x96.webp){kind=link}
![[]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/2025/11/me-2023-96x96.webp){kind=link}
![[]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/2025/06/LindaLi-96x96.jpeg){kind=link}
![[]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/2026/04/profile-96x96.webp){kind=link}
![[]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/2025/06/circle-profile-600-96x96.webp){kind=link}
![[]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/2025/05/me-96x96.jpg){kind=link}
![[]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/letter-avatar/f668c275998dced0c1f30fb8f293797d.svg){kind=link}
![[]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/2026/06/me3-96x96.webp){kind=link}
![[]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/2025/05/skohlmeier-96x96.jpeg){kind=link}
![[]](https://devblogs.microsoft.com/foundry/wp-content/uploads/sites/89/2026/05/swmachan_pic1-1-96x96.webp){kind=link}