Posts tagged with "AI"

Most AI tooling I've used in the last couple of years follows the same pattern. You send a prompt, get back text, and then write brittle code to turn that text into something your app can actually use. JSON mode helps. Function calling helps more. Even then, you are still asking a model trained to write for people to produce machine-readable output, and hoping it doesn't wrap the JSON in a markdown fence, drop a field, or invent a category that is not in your enum.

Two days ago I found TypeSafe and its model, Jev. It takes a different approach. Instead of generating text, it evaluates typed questions against a piece of input and returns structured, typed decisions. No parsing. No "please respond only with valid JSON." I liked the idea enough that I had GitHub Copilot with HydraFusion port TypeSafe's official TypeScript SDK to .NET 11 and C# 15. This post is part introduction to the model and part walkthrough of the ported TypeSafe .NET SDK, so you can try it in C# yourself.

I opened GitHub on my phone before my morning coffee had finished brewing. There it was — a pull request, freshly opened, titled "chore: upgrade astro to v6.1.2". I hadn't asked anyone to do it. I hadn't filed an issue, assigned a task, or written a single command. An agent had woken up, checked the npm registry, read the Astro changelog, inspected my codebase, applied the changes, run pnpm install, and handed me a PR to review. All I had to do was drink my coffee and click Merge.

This is the promise of what GitHub Next is calling Continuous AI — and it's already working on my blog.

For years, my git worktree setup was modest: two worktrees for active development, and one more for code reviews. Three worktrees, tops. It worked. I never questioned it.

Then AI coding agents arrived — tools that write code, run tests, and iterate autonomously — and suddenly three worktrees felt like a bottleneck. Each agent needs its own isolated workspace. Each task deserves its own branch, its own directory, its own terminal. The question shifted from "how many worktrees can I manage?" to "how many can I run in parallel?"

A few years ago, I wrote about how ReSharper's Search with Pattern feature helped me refactor a massive C# codebase in minutes. The technique was powerful, but creating those custom search and replace patterns meant using ReSharper to define them. Alternatively, you could hand-craft XML in DotSettings files—tedious work that required memorizing the exact structure, generating GUIDs, and configuring placeholder properties correctly.

Recently, I explored how Agent Skills are becoming an open standard that works across different AI coding assistants like GitHub Copilot, Cursor, and JetBrains Junie. This got me thinking: what if I could combine these two powerful developer tools? What if an Agent Skill could automate the tedious part of creating ReSharper and Rider patterns?

This post shows how I built exactly that—a practical Agent Skill that generates properly formatted DotSettings XML for custom search and replace patterns in Rider and ReSharper, just by describing what you want in natural language to your AI coding assistant.