AI
Build Locally, Ship to Cloud for $0: Azure SQL for Modern App Developers
As app developers, our primary focus is building great user experiences, designing APIs, and shipping features quickly. What we don't want is database friction—wasting hours configuring local DB instances, writing verbose migration scripts by hand, or worrying about unexpected cloud bills while prototyping. Today, we are making database development fast, intelligent, and completely free. By combining the Azure SQL Developer Container for local offline development, AI Agent Skills to automate your ORM and data layer, and the Azure SQL Database Free Tier, you can build locally and ship to production in minutes f...
Beyond Chat: live Speech-to-Text with Foundry Local and C#
Build a live speech-to-text app in C# with Foundry Local, a compact Nemotron model, and local model lifecycle management.
From generated code to trusted code with a unit-test agent
Meet the open-source polyglot testing agent that learns from a repository, writes unit tests, and checks that they build and pass.
Announcing v2.0 of the official MCP C# SDK
MCP C# SDK v2.0 implements the 2026-07-28 specification with a stateless-first protocol, standardized HTTP headers, and Multi Round-Trip Requests for interactive tools, all while staying backward compatible.
Analyze MSBuild Binary Logs with Copilot in VS Code
Meet the MSBuild Binlog Analyzer for VS Code - a Copilot-powered way to read MSBuild binary logs, explain and fix build failures with one click, compare builds, and catch regressions, backed by the Microsoft.AITools.BinlogMcp MCP server.
Native Agent Memory for Microsoft Agent Framework, Powered by Azure Cosmos DB
Recently we introduced the Agent Memory Toolkit and the Agentic Retrieval Toolkit for Azure Cosmos DB. The Agent Memory Toolkit gives your agents durable, Cosmos-backed memory: it stores raw conversation turns and then distills them into higher-value derived memories (thread summaries, extracted facts, and cross-thread user profiles), all searchable with vector, full-text, and hybrid search in the one database you already use. Today we're taking the next step. With the latest release of Microsoft Agent Framework, you can now drop that memory into an agent with a single object: the , shipped in the new  package f...
Introducing the ETW MCP: AI-assisted ETL trace analysis, headless and in your terminal
If you’ve ever opened an ETL trace with hundreds of data tables and wondered “where do I even start?” This post is for you. We’re releasing an early preview of the ETW MCP, a Model Context Protocol server that lets GitHub Copilot, or any MCP-aware AI assistant, read, query, and reason over Event Tracing for Windows (ETW) traces the same way an experienced engineer would. No UI required. This is a companion to the WPA MCP, which brings the same AI-assisted experience inside Windows Performance Analyzer. The ETW MCP server is the headless sibling, same data layer, no WPA needed, works anywhere you can run Copilo...
How to test agent experience changes without shipping them
Most changes you think will improve AI agent behavior won't. We tested a dozen hypotheses on a real project upgrade scenario and the majority failed. Learn how to emulate documentation, API, and MCP server changes locally so you can validate what works before shipping anything to production.
AI agents, meet the Azure Cosmos DB vNext emulator
If you use the Azure Cosmos DB vNext emulator, you probably know the local development loop: start the emulator, connect to it, create some resources, load test data, run queries, and inspect the results. Each step is straightforward, but together they add setup work before you can test the application you are actually building. How agents work with the emulator The emulator includes the Azure Cosmos DB Shell, an open-source CLI for working with databases, containers, and items. It runs inside the emulator container and handles the local endpoint and well-known key, giving developers a direct, scr...
How to test agent skills without hitting real APIs
Your agent skill calls an API. The moment you start evaluating it, every run either costs money or mutates production data. Learn how to mock APIs transparently so you can run evals without changing your skill or hitting real endpoints.
