The Week AI Tooling Got More Opinionated
This week’s clearest signal for .NET and Azure engineers is less “new shiny model” and more “the platform layers are getting stricter, cheaper, and more operational.” GitHub is steering users away from GitHub Models, Microsoft Foundry keeps absorbing more of...
GitHub Just Made Code Scanning a Little Smarter About AI
GitHub’s latest code-scanning update is a meaningful shift for teams shipping AI-adjacent software: AI-powered detections now surface directly on pull requests, widening coverage beyond what CodeQL currently handles in some languages and frameworks. For .NET and Azure teams, that means...
Why GPT-5.6 in GitHub Copilot Matters More Than the Model Name
GitHub Copilot now offers GPT-5.6 in three distinct flavors—Sol, Terra, and Luna—which is less about marketing confetti and more about giving teams a real control surface for reasoning depth, latency, and cost. For engineers shipping on .NET and Azure, the...
The Week AI Models Moved Closer to Production Reality
AI tooling for developers keeps getting less “science fair demo” and more “please don’t wake me up when this is on-call.” The big theme for .NET and Azure teams is clear: model choice, agent hosting, and repo-native assistance are converging...
Kimi K2.7 Code Lands in GitHub Copilot — and the Economics of AI Coding Just Shifted
GitHub has made Kimi K2.7 Code generally available in Copilot, and that matters because it’s the first open-weight model in the Copilot model picker. For .NET and Azure engineers, this isn’t just a model-name change; it’s a pricing, latency, and...
Kimi K2.7 Code Lands Where Developers Actually Work
The latest Copilot and Foundry updates point to a simple, slightly inconvenient truth: model choice is now an engineering decision, not a vendor checkbox. Kimi K2.7 Code is available in GitHub Copilot and in Microsoft Foundry, which gives .NET and...
AI for .NET and Azure: the model buffet keeps getting cheaper, safer, and slightly more complicated
If you ship AI features on .NET or Azure, the current signal is clear: the platform is moving toward more choice, tighter cost controls, and more production-grade plumbing. The last few days brought a notable Copilot model addition, fresh usage...
Claude Sonnet 5 Lands in Microsoft Foundry, and Azure Engineers Get a New Default Choice
Claude Sonnet 5 is now generally available in Microsoft Foundry, which matters because it gives .NET and Azure teams another production-grade model option with enterprise controls instead of yet another “just call the API and hope” experience. Microsoft’s rollout landed...
Copilot Just Got Faster, and That Changes the Shape of Agentic Development
GitHub Copilot’s new Claude Opus 4.8 fast mode preview is a small-sounding release with big engineering implications: faster output, the same model family, and usage-based billing that makes every token visible on the bill. For teams shipping AI features on...
The Week AI Agents Became a Platform Decision
AI news for .NET and Azure teams is no longer just about “which model is best.” The more interesting story is that the platform layer is hardening: agent runtimes, observability, trust controls, SDKs, and governance are now the things that...