AI
When your agent extensions fight each other
This is the fourth 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 shipped your extension, measured it, confirmed it creates lift. Then a developer installs it alongside 14 other extensions, and outcomes get worse. Not because your extension is broken, but because extensions don't exist in isolation: they compete. In the previous article, we covered how to me...
Competing against yourself
You shipped a new CLI: better developer experience, modern architecture, and optimized for agents. You deprecated the old one, updated the docs, and blogged about it. Developers are migrating. Then someone asks an AI coding agent to scaffold a project, and the agent... uses the old tool. Training data gravity Models learn from the internet. If your technology has been around for a decade, there are thousands of blog posts, Stack Overflow answers, tutorials, and GitHub repos that document the old way of doing things. Your new CLI? A handful of announcement posts and maybe some updated docs. So what happens wh...
GitHub Copilot for JetBrains is moving to Copilot CLI as the default agent harness
Copilot CLI is becoming the default agent harness in GitHub Copilot for JetBrains, and our local harness will be deprecated. This change provides greater consistency across all GitHub Copilot surfaces and is an important step toward faster feature parity and higher-quality results in GitHub Copilot for JetBrains. Copilot CLI sessions run independently in the background on your machine and use the Copilot CLI agent harness, while the IDE starts, monitors, and steers them. This is the same architecture used across GitHub Copilot today and adopting it in JetBrains lets us ship the same capabilities to JetBrain...
Your agent just scaffolded a project from 2020
Your agent ran a scaffold command. Project generated, dependencies resolved, no errors. Everything looks fine. Except it's based on the project structure from 2020, and neither you nor the agent noticed. How npx picks the right-but-wrong version When an agent scaffolds a project or runs a CLI tool, it often reaches for without specifying a version. Something like: Notice, that there's no version pinned anywhere. The agent typed the package name and assumed it'd get the latest. That's where things break. When you run without a version, npm resolves the latest version that's compatible with your current Nod...
Is your agent extension actually working?
This is the third 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 shipped your skill, wrote clear instructions, developers install it, and agents discover it. Everything looks like it's working. But is the generated code actually better because of your extension? Or would the agent have produced the same result without it? In the first article, we introdu...
Join us for .NET Day on Agentic Modernization Livestream
Announcing the .NET Day of Agentic Modernization Livestream
Spec-Driven Development: A Spec-First Approach to AI-Native Engineering
AI has made software delivery faster, but speed alone does not guarantee better outcomes. As teams adopt AI-native development, the real challenge is keeping requirements, design, implementation, and validation aligned so the final result still reflects the original intent.Ā Spec-Driven Development (SDD) addresses this by making structured specs the shared source of truth for both humans and AI. Instead of prompting first and aligning later, teams align first and let AI accelerate execution from a clear spec. Why AI-assisted development still breaks down Teams often ship software that works but still misses the ...
Distributed multi-agent systems with Aspire and Microsoft Agent Framework
Learn how Aspire, Microsoft Agent Framework, and Microsoft Foundry model, run, observe, and publish a distributed multi-agent AlpineAI ski resort demo.
Microsoft Build 2026 recap: vision, launches, and top sessions
Catch up on Microsoft Build 2026 with the vision lead-off, top developer announcements, and must-watch sessions across the Microsoft developer ecosystem.
.NET at Microsoft Build 2026: Must watch sessions
Catch up on all the .NET sessions from Microsoft Build 2026 covering .NET 11, union types in C#, AI building blocks, the agentic web, .NET MAUI, and more!