Azure AI Foundry Blog
Your source for learning and building with our models, agents, and tools.
Latest posts
Introducing Microsoft Agent Framework: The Open-Source Engine for Agentic AI Apps
Why agents need a new foundation Over the last year, developers have been experimenting with AI agents in every imaginable form. Agents are not just chatbots or copilots — they are autonomous software components that can reason about goals, call tools and APIs, collaborate with other agents, and adapt dynamically. Whether it’s a retrieval agent for research, a coding agent embedded in a dev workflow, or a compliance agent ensuring policy enforcement, agents are becoming the next layer of application logic. Yet despite the excitement, the path from prototype to production has been fraught with obstacles. Many ...
Foundry Local Meets More Silicon
Foundry Local is a high-performance local AI runtime stack that brings Azure AI Foundry’s power to client devices. Foundry Local lets you build and ship cross-platform AI apps that run models with acceleration on a wide range of hardware. The Evolution of AI Acceleration On-device AI has progressed rapidly. Early workloads ran on CPUs, but performance and power limits made real-time inference difficult. GPUs improved things with parallelism, faster inference. The latest breakthrough is NPUs (Neural Processing Units), designed specifically for neural networks. NPUs deliver far greater efficiency and throughput...
AI-Assisted Development powered by Local Models
Developers have long struggled with concerns about data privacy, restrictive cloud dependencies, and limited control over their AI tools—especially when working on sensitive projects or within regulated industries. Now, with the excitement surrounding local models, you can harness AI directly on your device, ensuring your data stays private and your workflow remains fully customizable. The big breakthrough: Foundry Local empowers you to use local AI models seamlessly with GitHub Copilot in Visual Studio Code, giving you privacy, flexibility, and offline capabilities without compromise. Foundry Local is a cutti...
Ground Your Agents Faster with Native Azure AI Search Indexing in Foundry
Instantly create a production-ready Azure AI Search vector index directly inside Azure AI Foundry when grounding your agent—no prior search setup required.
Announcing Computer Use tool (Preview) in Azure AI Foundry Agent Service
Overview We are excited to announce Computer Use—are now available in preview in Azure AI Foundry Agent Service. It brings feature parity with the Azure OpenAI Responses API, but with the added advantage of seamless integration into the Foundry agent runtime and enterprise security. With this release, developers can create agents that not only reason over text, retrieve knowledge, or call APIs, but also directly interact with computer interfaces through natural language instructions. At launch, it is accessible through REST API and SDK, giving developers the flexibility to embed them directly into their applica...
What’s new in Azure AI Foundry | August 2025
August 2025 highlights GPT‑5 arrives in Foundry, Model Router adds GPT‑5 support, Responses API is GA, Browser Automation enters public preview, plus Sora updates, Mistral Document AI, FLUX image models, OpenAI gpt‑oss with Foundry Local, and SDK/documentation updates.
Unlocking GPT-5’s Freeform Tool Calling: A New Era of Seamless Integration
GPT-5 models are now available in Azure AI Foundry via Azure OpenAI. Designed for advanced reasoning and generation. One of the core capabilities of the model is tool calling, which enables it to interact with external systems by generating and sending raw text directly to tools. What Is Freeform Tool Calling in GPT-5? Freeform tool calling is a powerful capability in GPT-5 that allows the model to send raw text payloads like Python scripts, SQL queries, or configuration files directly to external tools without needing to wrap them in structured JSON. This means the model can generate code or text in the ...
Announcing the Browser Automation Tool (Preview) in Azure AI Foundry Agent Service
Overview Today, we are excited to announce the Browser Automation Tool (Preview) as the newest action tool in Azure AI Foundry Agent Service through API and SDK. This tool enables developers to build agents capable of performing real-world browser tasks—such as searching, navigating, filling forms, booking appointments, and more—through natural language prompts. Powered by Playwright Workspaces, Browser Automation Tool brings isolated, cloud-hosted browser automation to your AI agents, supporting multi-turn interactions that mimic a real user’s browsing experience. Key Benefits ...
What’s new in Azure AI Foundry | July 2025
July 2025 brings Deep Research Agent (public preview), GPT-image-1 model enhancements, new developer tools, and platform, security, and SDK updates to Azure AI Foundry.