# Microsoft for Developers > Get the latest information, insights, and news from Microsoft. ## Topics - [AI](https://devblogs.microsoft.com/blog/category/ai/): 47 posts - [Microsoft for Developers](https://devblogs.microsoft.com/blog/category/msfordevs/): 19 posts - [GitHub Copilot](https://devblogs.microsoft.com/blog/category/github-copilot/): 18 posts - [Announcement](https://devblogs.microsoft.com/blog/category/announcement/): 11 posts - [Developer Events](https://devblogs.microsoft.com/blog/category/developer-events/): 11 posts - [Visual Studio](https://devblogs.microsoft.com/blog/category/visual-studio/): 9 posts - [Microsoft for Developers](https://devblogs.microsoft.com/blog/category/microsoft-for-developers/): 8 posts - [Azure](https://devblogs.microsoft.com/blog/category/azure/): 7 posts - [Visual Studio Code](https://devblogs.microsoft.com/blog/category/visual-studio-code/): 7 posts - [GitHub](https://devblogs.microsoft.com/blog/category/github/): 6 posts - [Security](https://devblogs.microsoft.com/blog/category/security/): 5 posts - [MCP](https://devblogs.microsoft.com/blog/category/mcp/): 3 posts - [Azure DevOps](https://devblogs.microsoft.com/blog/category/azure-devops/): 2 posts - [Package Management](https://devblogs.microsoft.com/blog/category/package-management/): 2 posts - [Extensions](https://devblogs.microsoft.com/blog/category/extensions/): 1 posts - [Supply Chain Security](https://devblogs.microsoft.com/blog/category/supply-chain-security/): 1 posts - [Mobile Apps](https://devblogs.microsoft.com/blog/category/mobile-apps/): 1 posts - [Customer Zero Stories](https://devblogs.microsoft.com/blog/category/customer-zero-stories/): 1 posts ## Recent Posts - [Knowledge cutoff is a poor proxy for model capability](https://devblogs.microsoft.com/blog/knowledge-cutoff-is-a-poor-proxy-for-model-capability/): A model can fail on features released before its knowledge cutoff, then succeed on ones released after it. We tested hundreds of product changes and found that the date tells you far less than the work does. - [Your AI coding agent evaluation is only as good as its sandbox](https://devblogs.microsoft.com/blog/your-ai-coding-agent-evaluation-is-only-as-good-as-its-sandbox/): Your AI coding agent passed the eval. But did the model know the answer, or did it find it somewhere on your machine? A correct answer can still invalidate your measurement. - [Build an interview coach app with the GitHub Copilot SDK](https://devblogs.microsoft.com/blog/build-an-interview-coach-app-with-the-github-copilot-sdk/): An interview coach has to do more than ask questions. It needs to read a resume, follow up on an... - [Your work might not need the smartest model](https://devblogs.microsoft.com/blog/your-work-might-not-need-the-smartest-model/): The smartest model can cost five times more and deliver the same result, or even a worse one. See how evaluating your own work helps you get more value from your agent budget. - [Start here: Azure SQL Foundations series](https://devblogs.microsoft.com/blog/start-here-azure-sql-foundations-series/): Most developers I talk to aren't asking whether Azure SQL Database can handle their next app. They're asking where to... - [Try Azure SRE Agent with no always-on charges](https://devblogs.microsoft.com/blog/try-azure-sre-agent-with-no-always-on-charges/): We are happy to announce a 30-day trial experience for Azure SRE Agent. New customers can create and configure the... - [The Microsoft 365 Copilot Agent’s Playbook: A Practical Livestream Series for Building Better Agents](https://devblogs.microsoft.com/blog/the-microsoft-365-copilot-agents-playbook-a-practical-livestream-series-for-building-better-agents/): Building on Microsoft 365 Copilot? Here's your playbook. Declarative agents are quickly becoming one of the most exciting ways to... - [How to test agent experience changes without shipping them](https://devblogs.microsoft.com/blog/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. - [How to test agent skills without hitting real APIs](https://devblogs.microsoft.com/blog/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. - [Building AX evals that actually work](https://devblogs.microsoft.com/blog/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... - [Let’s Learn GitHub Copilot App - Free Virtual Training Event](https://devblogs.microsoft.com/blog/lets-learn-github-copilot-app-free-virtual-training-event/): Join us for a free online event series kicking off July 16 to learn how to get started with the GitHub Copilot App! - [The hidden variables in your agent eval](https://devblogs.microsoft.com/blog/the-hidden-variables-in-your-agent-eval/): This is the seventh article in a series about Agent Experience (AX): the practice of making AI coding agents work... - [Don't rewrite your CLI for agents](https://devblogs.microsoft.com/blog/dont-rewrite-your-cli-for-agents/): There's advice making the rounds: replace your CLI args with a single --json payload so agents can use your tool... - [Not all model upgrades are upgrades](https://devblogs.microsoft.com/blog/not-all-model-upgrades-are-upgrades/): A new model drops with lower per-token pricing and better benchmarks. You switch. A week later someone asks why the... - [What AI benchmarks are not telling you](https://devblogs.microsoft.com/blog/what-ai-benchmarks-are-not-telling-you/): This is the sixth article in a series about Agent Experience (AX): the practice of making AI coding agents work... - [Your agent already has a plan](https://devblogs.microsoft.com/blog/your-agent-already-has-a-plan/): If an agent isn't doing the right thing, the obvious move is to make the docs clearer. Add a tip,... - [Learn from Microsoft: Transform software development through an agentic platform](https://devblogs.microsoft.com/blog/learn-from-microsoft-transform-software-development-through-an-agentic-platform/): See how Microsoft is transforming software development with agentic workflows, AI-powered automation, and specialized agents across the engineering lifecycle. - [When the model has never seen your code](https://devblogs.microsoft.com/blog/when-the-model-has-never-seen-your-code/): This is the fifth article in a series about Agent Experience (AX): the practice of making AI coding agents work... - [Models don't have preferences, they have context](https://devblogs.microsoft.com/blog/models-dont-have-preferences-they-have-context/): You open a fresh chat, type "What framework should I use for a web app?", and the model says "React."... - [Stop overloading your skills](https://devblogs.microsoft.com/blog/stop-overloading-your-skills/): You built a skill for your technology. API references, authentication flows, SDK patterns, error handling, version info, all packed into... - [How to diagnose conflicts between AI agent extensions](https://devblogs.microsoft.com/blog/when-your-agent-extensions-fight-each-other/): Your extension works in isolation. You measured it, confirmed it creates lift. Then a developer installs it alongside 14 other extensions, and outcomes get worse. The symptoms look like a bug in your code, but the problem is elsewhere: extensions fighting each other for the same context window and model attention. - [Why AI coding agents keep using deprecated CLIs and SDKs](https://devblogs.microsoft.com/blog/competing-against-yourself/): You deprecated the old CLI and shipped something better. Developers are migrating, but AI coding agents aren't. They keep reaching... - [Your agent just scaffolded a project from 2020](https://devblogs.microsoft.com/blog/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... - [How to measure AI agent extension effectiveness](https://devblogs.microsoft.com/blog/is-your-agent-extension-actually-working/): You shipped your skill. Everything looks like it's working. But is the generated code actually better because of your extension? You can't tell without measuring, and measuring agent extension impact is harder than it looks. - [Stop skillmaxxing, save your tokens](https://devblogs.microsoft.com/blog/stop-skillmaxxing-save-your-tokens/): You built a dozen skills for your technology: authentication, CRUD, error handling, deployment, testing, monitoring. Then you installed a cloud... - [Spec-Driven Development: A Spec-First Approach to AI-Native Engineering](https://devblogs.microsoft.com/blog/spec-driven-development-ai-native-engineering/): AI has made software delivery faster, but speed alone does not guarantee better outcomes. As teams adopt AI-native development, the... - [Microsoft Build 2026 recap: vision, launches, and top sessions](https://devblogs.microsoft.com/blog/build-recap/): Catch up on Microsoft Build 2026 with the vision lead-off, top developer announcements, and must-watch sessions across the Microsoft developer ecosystem. - [Improve your agentic developer tools by grounding in Microsoft Learn](https://devblogs.microsoft.com/blog/improve-your-agentic-developer-tools-by-grounding-in-microsoft-learn/): Development workflows span terminals, IDEs, background agents, and custom assistants. What matters is whether they draw from the same current... - [How AI coding agents actually use your technology](https://devblogs.microsoft.com/blog/how-ai-coding-agents-actually-use-your-technology/): You ship an SDK, a CLI, an API, and developers use it. Now AI coding agents use it too, except... - [How to improve AI coding agent support for your SDK, API, or CLI](https://devblogs.microsoft.com/blog/the-ax-stack-whats-fixed-where-you-can-win/): AI coding agents use your SDK, API, or CLI, but often get it wrong. The stack has layers you can't change and one you can: agent extensions. Learn how to measure whether yours are helping or hurting. ## Pages - [Home](https://devblogs.microsoft.com/) - [Microsoft for Developers Blog](https://devblogs.microsoft.com/blog/) - [DevBlogs](https://devblogs.microsoft.com/devblogs-landing-page/) - [Privacy on Dev Blogs](https://devblogs.microsoft.com/privacy-on-devblogs/) - [Dev Blogs FAQs](https://devblogs.microsoft.com/faq/) - [Search](https://devblogs.microsoft.com/search/) - [Principles for AI generated content](https://devblogs.microsoft.com/principles-for-ai-generated-content/) - [VS Code Blog](https://devblogs.microsoft.com/vscode-blog/) - [Newsletter](https://devblogs.microsoft.com/newsletter/) - [DevBlogs RSS Feed](https://devblogs.microsoft.com/landing/) ## Optional - [Full content version](https://devblogs.microsoft.com/llms-full.txt)