Visual Studio 2026 Version 18.7.2 Release Notes | Microsoft Learn

https://learn.microsoft.com/visualstudio/releases/2026/release-notes#18.7.2

#visualstudio #vs2026 #releasenotes #dotnet #githubcopilot #productivity

Released cARL v0.4.0 today: 𝗰𝗔𝗥𝗟 𝗶𝘀 𝗧𝗵𝗲 𝗥𝗲𝗮𝗹 𝗦𝗵𝗶𝗺 𝗦𝗵𝗮𝗱𝘆.
(Yes, I used an Eminem reference. No, I’m not sorry!)

This release introduces adapter shims for cARL, my repo-native governance model for coding agents.
Different tools expect instructions in different places:
• GitHub Copilot: .github/copilot-instructions.md
• Claude Code: CLAUDE.md
• Codex: AGENTS.md
• Cursor: .cursor/rules/carl.mdc
• Antigravity: .agents/rules/carl.md

Rather than duplicating the full governance model into every file, v0.4.0 makes .github/copilot-instructions.md the shared cARL loader.
Every other harness gets a tiny shim that points back to it.
Same law. Different doorbells.

Tiny grumpy senior engineer as code continues.
https://github.com/goldjg/cARL/releases/tag/v0.4.0
#AI #AgenticAI #DevSecOps #GitHubCopilot #ClaudeCode

Application modernization has traditionally been slow, expensive, and difficult to scale.

At Nebraska.Code(), Vaibhav Gujral shares how AI-powered modernization agents can accelerate upgrades, reduce risk, and help teams modernize legacy applications faster.

🔗 https://nebraskacode.amegala.com/

#NebraskaCode #AI #ApplicationModernization #DotNet #GitHubCopilot

#GitHub just dropped the new #GitHubCopilot app - a desktop control center for agent-native development.

Instead of letting #AIagents run as opaque background processes, this app gives developers a dedicated place to direct, monitor, and manage AI coding agents.

The goal? Keep engineers in control as AI takes on heavier development tasks.

👉 Read on #InfoQ: https://bit.ly/3QFK35k

#SoftwareDevelopment

One of the more interesting cARL (https://github.com/goldjg/cARL) releases wasn’t a new feature.
It was discovering that one of my assumptions was wrong.

Originally, cARL treated AI coding harness support as a simple binary state (and for all harnesses except GitHub Copilot which I actually use, the harness implementation was assumed to be similar):
✅ Supported
❌ Not Supported

After some end-to-end testing in Claude (first harness I’ve tried other than Copilot), I discovered reality was more nuanced.

Different coding agents handle instructions, context loading, skills, settings, memory, and repository guidance in very different ways. Some behaviours I assumed would be automatic turned out not to be.

So instead of quietly updating the docs and moving on, cARL v0.2.3 introduces harness validation tiers:
✅ Production - Tested and validated end-to-end
⚠️ Experimental - Partially validated, under investigation
🧪 Theoretical - Adapter exists, but not yet validated

The lesson isn’t really about AI coding agents.
It’s about engineering.

      Assumptions have teeth.

If testing disproves one of your assumptions, the answer isn’t to defend the assumption. It’s to update the model.

One thing I’ve criticised vendors for over the years is “shadow fixing” - quietly changing behaviour or documentation without acknowledging what was learned.
Can’t really complain when others do it if I’m willing to do the same. 🤣

So here’s the public record:
I assumed all harnesses were effectively equal.
I tested it.
They weren’t.

#cARL #GitHubCopilot #ClaudeCode #AgenticAI #Engineering #SoftwareDevelopment #AssumptionsHaveTeeth