Azure AI Foundry Blog
Your source for learning and building with our models, agents, and tools.
Latest posts
Enhancing Conversational Agents with Azure AI Language Conversational Language Understanding and Custom Question Answering
As we focus our work on empowering the agent design experience, a list of the new features in the we published earlier this week, including the intent triage agent and the exact question-answering agent, utilizing Conversational language understanding (CLU) and Custom question answering (CQA). We’re excited to share new enhancements to the customization experiences in CLU and CQA that are officially available today. Customization in AI Foundry We’re excited to announce that both Conversational Language Understanding (CLU) and Custom Question Answering (CQA) are now fully integrated into the AI Foundry, unlockin...
The Future of Semantic Kernel: A Commitment to Innovation and Collaboration
Semantic Kernel is Microsoft’s core framework for enterprise AI orchestration, remaining secure, stable, and rapidly evolving with unified multi-agent support and deep Azure integration, backed by ongoing investment and a clear long-term roadmap.
Go from prompt to playback with Sora from Azure OpenAI in the video playground in Azure AI Foundry
The video playground in Azure AI Foundry is a high-fidelity testbed for prototyping with cutting-edge video generation models like Sora from Azure OpenAI. It offers a controlled environment for developers to experiment with prompt structures, evaluate model consistency, and optimize outputs for industry use cases.
Code quicker with Azure AI Foundry playgrounds and Visual Studio Code
The "Open in VS Code" workflow, part of the Azure AI Foundry extension for Visual Studio Code, accelerates developer velocity by integrating agent or model API endpoints and code samples into a new workspace in VS Code for Web. This feature streamlines the development process, enabling rapid prototyping and deployment with just one click.
Azure AI Foundry MCP Server May 2025 Update: Adding Models, Knowledge & Evaluation
Major expansion of Azure AI Foundry MCP Server with new Models, Knowledge Management, and Evaluation capabilities joining the existing Agent Services, enabling developers to interact with Azure AI through natural language.
Introducing New Tools and Features in the Responses API in Azure AI Foundry
With the introduction of the Responses API, Microsoft is enabling a new standard for AI development within the Azure ecosystem. Originally launched by OpenAI and now natively supported in Azure AI Foundry, the Responses API combines the simplicity of the Chat Completions API with the advanced tool-calling capabilities of the Assistants API. It offers a streamlined way to build powerful agentic experiences by allowing developers to structure prompts, invoke tools, and manage outputs—all within a single API call. Today, we’re excited to roll out powerful new capabilities in the Responses API in Azure OpenAI, ena...
Foundry Local: A New Era of Edge AI
At Microsoft Build 2025, Microsoft unveiled its groundbreaking Foundry Local solution for edge devices—an efficient platform specifically designed for local AI inference. As a critical component of Microsoft's AI strategy, Foundry Local empowers developers to smoothly deploy and run Small Language Models (SLMs) on resource-constrained edge devices, opening new possibilities for the convergence of edge computing and artificial intelligence. Core Architecture and Technical Advantages Technical Foundation: The ONNX Ecosystem Foundry Local is built on ONNX (Open Neural Network Exchange)—a mature, open standa...
Unlock Instant On-Device AI with Foundry Local
You’re building a next generation AI-powered app. It needs to be fast, private, and work anywhere, even without internet connectivity. This isn’t just about prototyping. You’re shipping a real app to real users, with AI that delivers value and scales cost-effectively. Meet Foundry Local—the high-performance local AI runtime stack that brings Azure AI Foundry’s power to client devices. Now in preview on Windows and macOS, Foundry Local lets you build and ship cross-platform AI apps that run models, tools, and agents directly on-device. It is included in Windows AI Foundry, delivering best in class AI capabiliti...
How Azure AI Foundry and Partners Simplify Governance Without Slowing Developers Down
Read more about how Azure AI Foundry integrates with governance platforms like Saidot, Credo AI, and Microsoft Purview Compliance Manager to streamline AI governance. By embedding evaluation tools directly into development workflows, Azure AI Foundry helps users with governance requirements without compromising developer velocity, .