AI

I've run over 11,000 AI agent tasks this year with a 99.4% success rate. Here's what actually works, what fails spectacularly, and why boring agents beat brilliant ones.

Eighty lines of TypeScript and an MCP server turn Terminal Bridge into a full AI terminal integration. Here's the code, the patterns, and the hard lesson about terminal naming I learned at 2 AM.

I run 6-10 Claude sessions at once. Dispatch and remote control are single-session tools. So I built a mobile PWA that wires into IntelliJ via Terminal Bridge and Tailscale — here's the architecture.

I built four IntelliJ plugins that give AI agents full IDE access — terminals, builds, notifications, project intelligence. Here's what happened when I stopped pasting Maven commands and started letting agents operate the IDE directly.

I shipped Run Configuration Bridge, then ripped out 430 lines of terminal polling code and replaced them with three API calls. Exit codes beat regex. Here's what happened when I ate my own dogfood.

Terminal Bridge started as survival code at 2 AM. Now it's a freemium IntelliJ plugin on the JetBrains Marketplace — built on new APIs, solving a real problem. Here's how it got there.

Terminal Bridge exposes your IntelliJ terminal tabs through a local REST API. I built it because AI coding assistants are blind to your terminal layout — and that needed to change.