-
Introduction: When Valid JSON Is Not Enough 100% of our outputs were valid JSON. 0% met the data contract. We prototyped an LLM-powered system that converts operational shift logs into structured summaries consumed by dashboards, compliance workflows, and incoming crews. The output schema required specific operational …
Read More -
How AI coding models calibrate effort, token cost, and tool use on even the simplest task, and what that means for model selection and cost. Read the full article Link to article: https://devblogs.microsoft.com/vscode-blog/what-50,000-runs-of-a-5-line-eval-taught-us
Read More -
We shipped a lot at Build 2026: hosted agents, Toolboxes, Foundry IQ, Memory, Managed Compute, fine‑tuning, Frontier Tuning, and a new evaluation and optimization stack. Read Link to article: https://devblogs.microsoft.com/foundry/outcome-driven-learning-systems-enterprise-rl-with-openenv-and-foundry
Read More -
From May 12 to June 2, 2026, builders from around the world put their Agent Academy learning to the test by designing, building, and shipping real, working AI agents with Copilot Studio. After two weeks of judging, we’re thrilled to announce the Agent Academy Hackathon winners. 🏆 The Winners Recruit Track Th Link to …
Read More -
At this year’s GDC, we shared our vision for bringing console‑level GPU developer tools to Windows. As part of that announcement, we introduced DirectX Dump Files as a major step forward in GPU crash debugging on Windows. Today, we’re excited to make our DirectX Dump Files public preview available to developers! If you …
Read More -
Today we released PIX 2606.18-preview, available here. This PIX release coincides with the preview availability of DirectX Dump Files (.dxdmp). The PIX UI can open DirectX Dump Files directly for analysis, and the PIX API can be used to analyze them programmatically. Please visit Link to article: …
Read More -
Today we are excited to announce the Release Candidate of TypeScript 7.0! If you haven't been following TypeScript 7.0's development, this release is significant in that it is built on a completely new foundation. Over the past year, we have been porting the existing TypeScript codebase from TypeScript (as a …
Read More -
You built a skill for your technology. API references, authentication flows, SDK patterns, error handling, version info, all packed into one skill. The agent calls it, gets all that context, and generates code. The kicker? You've just wasted a lot of tokens. It already knows Models have ingested your documentation, …
Read More -
A customer had a Windows NT service process, and from that service process, they wanted to obtain the last input time for all signed-in users. Their strategy was to use WTSQueryUserToken() to get the token for each user, use that token to impersonate the user, and then call GetLastInputInfo() to get the Link to …
Read More -
Learn how to use bring your own key (BYOK) in VS Code to add models from providers like Azure, Anthropic, Gemini, OpenAI, Huggingface, OpenRouter, or use a local model with Ollama, Foundry Local, and more. Read the full article Link to article: …
Read More -
MSBuild binary logs (.binlog files) contain a wealth of information about your build — every property evaluation, target execution, task invocation, error, and warning. But navigating that data manually can be overwhelming, especially when you're debugging a complex multi-project solution. What if your AI coding …
Read More -
Learn what's new in Visual Studio Code 1.125 Read the full article Link to article: https://devblogs.microsoft.com/vscode-blog/visual-studio-code-1.125
Read More -
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. …
Read More -
Learn how we're improving token efficiency for GitHub Copilot to reduce costs and latency for VS Code users. Read the full article Link to article: https://devblogs.microsoft.com/vscode-blog/improving-token-efficiency-for-github-copilot-in-vs-code
Read More -
Boosting Adobe Photoshop’s Performance with MSVC and SPGO Adobe and Microsoft worked together to improve Photoshop performance and responsiveness on Windows by combining MSVC’s peak-performance build settings with Sample-based Profile-Guided Optimization (SPGO). The collaboration focused Link to article: …
Read More -
Visual Studio Code consistently ranks as the most popular IDE for developers, and its flexibility and extension marketplace make it possible for developers using any technology or language to build and debug their applications. In 2026, we've brought Aspire support to Link to article: …
Read More -
MSIX has several core principles underlying its design and implementation. Engineers half-jokingly call these The Rules of MSIX. The Third Rule of MSIX is arguably the most important and certainly the most foundational: Package identity is unique across space and time Link to article: …
Read More -
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 Link to …
Read More -
Today, we're excited to announce the general availability of the Azure Cosmos DB built-in connector for Azure Logic Apps Standard. This connector gives you a native, high-performance way to integrate Azure Cosmos DB into your Standard logic app workflows, with better throughput, lower latency, and richer functionality …
Read More