Microsoft Foundry Blog
Your source for learning and building with our models, agents, and tools.
Latest posts
Foundry Local comes to Android—plus on-device speech, on-prem support, and a simpler SDK
Today, we’re introducing a powerful new way to bring AI directly to your mobile apps: Foundry Local on Android. Starting now, you can build Android applications that run AI on-device—no cloud round trips required. Sign up for the gated preview here: https://aka.ms/foundrylocal-androidprp Most of us now carry a computer in our pocket. These devices are now powerful enough to run AI models locally, unlocking speed, privacy, and flexibility. With Foundry Local, you can easily deploy optimized open-source models from Microsoft Foundry directly on mobile devices. Why on-device AI matters: Foundry Local...
How to debug and optimize RAG agents in Microsoft Foundry
TL;DR Learn the best practices to evaluate and optimize the RAG quality of your agent using evaluations in Foundry Observability. This tutorial demonstrates these 2 best practices before deploying your RAG agent: 1. Evaluate and optimize end to end your RAG agent using reference-free RAG triad evaluators: Groundedness and Relevance evaluators; 2. For advanced search use case requiring ground truths and more precise measurement of retrieval quality, optimize your Search parameters using golden metrics such as XDCG and Max Relevance: Document Retrieval evaluator Framing Agent Observability Agents can be po...
Introducing GPT-4o Audio Models in Microsoft Foundry: A Practical Guide for Developers
How to get started with Azure OpenAI's next-generation GPT-4o audio models for transcription and text-to-speech applications.
Announcing Azure Language in Foundry Tools for deterministic, privacy-first agents
In today’s rapidly evolving AI landscape, developers are seeking reliable, secure, and predictable language capabilities to power the next generation of enterprise-grade agents. As agentic architecture becomes central to modern applications, teams need tools that deliver stronger privacy guarantees, deterministic behavior, and seamless integration across their AI stack. As part of the broader transition from Azure AI Services into unified Microsoft Foundry Tools, we’re excited to introduce the rebranded Azure Language in Foundry Tools with new enhancements purpose-built for agent development. Today’s release b...
Session Guide to Microsoft Foundry @ Microsoft Ignite: Must-See Developer Sessions
Microsoft Ignite 2025 is the ultimate opportunity for developers to dive deep into what’s new with Azure AI Foundry. We curated the top sessions designed for hands-on learning, practical demos, and expert insights. Whether you’re building AI apps, orchestrating multi-agent systems, or interested in exploring new developer tools, this guide will help you plan your event schedule whether you are attending in person or joining virtually! Don’t miss this Innovation Session Build and Manage AI Apps with Your Agent Factory | BRK1706 Step into the era of agentic AI with an open, modular platform for building and ma...
A Developer’s Guide to Fine-Tuning GPT-4o for Image Classification on Azure AI Foundry
Whether you’re a machine learning practitioner, app developer, or just curious about the latest in AI, this guide shows how you can quickly boost image classification accuracy using cutting-edge Vision-Language Models (VLM) on Azure—no deep learning expertise required. In this walkthrough, you’ll see how to fine-tune GPT-4o on Azure OpenAI for image classification using the Stanford Dogs dataset. Illustrations of some of dogs' breeds images presented on the dataset. We’ll use the Vision Fine-Tuning API and compare the results to a lightweight CNN baseline, so you can see the impact of modern Vision-Languag...
The Developer’s Guide to Smarter Fine-tuning: Unlock custom AI for every business challenge
Azure AI Foundry makes fine-tuning smarter, faster, and more accessible than ever. Whether you’re building agents that reason, tools that adapt, or workflows that scale, this is your launchpad for customizing models to solve real business challenges. Dive in to discover best practices, hands-on resources, and the latest innovations so you can build, test, and deploy specialized AI with confidence. What is Fine-tuning? Fine-tuning refers to customizing a pre-trained LLM with additional training on a specific task or new dataset for enhanced performance, new skills, or improved accuracy. So instead of building ...
What’s new in Azure AI Foundry | September 2025
GPT‑5‑Codex GA, Sora video‑to‑video preview, Grok 4 Fast, Browser Automation & Key Vault previews, new Search knowledge sources, Voice Live GA.
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 ...