AI
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 (coming soon), 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 ...
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.
Teaching a Vision Model to See Like a Human Annotator—and Catching It When It Lies
A multimodal LLM enrichment pipeline that extracts structured metadata from visual assets, constrains output to predefined values to minimize hallucinations, and uses a ground truth evaluation template to measure quality—all as a plug-and-play module.
Building AX evals that actually work
This is the eighth and final article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can't control in the agent stack, how to measure whether your extensions are helping or hurting, and how to iterate toward better outcomes. You've read seven articles about what to measure, why benchmarks don't transfer, and what hidden variables can do to your results. Now you actually have to build the thing. Most teams build an eval, run it, get scores, and feel good about the numbers. The trouble is that these evals produ...
Microsoft Agent Framework for Go public preview
Microsoft Agent Framework for Go is entering public preview, bringing Agent Framework concepts to Go developers building agents and multi-agent workflows.
