Microsoft's July release adds a Copilot Chat agent preview, workload-specific skills, shared instructions, branch context and C++ build controls.

Good documentation is important for any application, and it starts with documenting your code. It helps you and it helps your users. It's no secret that I believe documentation is a crucial element of ...

"The gap between C# and Java never has been so small," says the latest edition of the TIOBE Index of programming language popularity. "Currently, the difference is only 1.2 percent, and if the trends ...

VS Code forks are diverging rapidly, not just in features, but in how they structure AI-assisted development workflows. Cursor emphasizes speed and visual polish, Windsurf leans toward dynamic ...

Microsoft's new Azure Skills Plugin bundles curated Azure skills, the Azure MCP Server, and the Foundry MCP Server into a single install for AI coding agents. The package is designed to help agents ...

A new GitHub repo serves as a lab for creating a Model Context Protocol (MCP) Server and using it in Microsoft Copilot Studio. The MCP, originated by AI leader Anthropic and taken open source, is a ...

"GitHub Spec Kit is an experiment-- there are a lot of questions that we still want to answer, and if community feedback is an indicator, there are quite a few features we can still add to make the ...

OpenAI's "Codex" AI model is back, in a new form from the 2021 offering that powered the original GitHub Copilot and kickstarted the GenAI craze. Rather, the new Codex, now in research preview, is ...

Microsoft today announced new learning benefits to subscribers of its flagship Visual Studio IDE, including discounts for Visual Studio Live! developer conferences and other educational opportunities.

Production telemetry from millions of GitHub Copilot users shows that 87 percent of LLM calls are initiated by the agent itself after a developer starts a turn, while failures can trigger lengthy ...

C# expert Mark Michaelis explores what .NET developers still need to learn for themselves as AI takes on more coding work, highlighting DevOps, testing, technical debt and the engineering discipline ...