I use AI DevKit to develop AI DevKit features

I built AI DevKit because I wanted a workflow that makes AI coding feel less random and more efficient. But I also know from experience that AI looks great when you demo it. The problem only surfaces when you rely on them to ship something non-trivial. I made a rule for myself. I would use … Continue reading I use AI DevKit to develop AI DevKit features →

Prompts are becoming Code, but we still treat them like Strings

Prompts used to be just text. You wrote a few sentences, pasted them into a chat box, tweaked the wording, and moved on. If the output was not good, you tried again. Nothing else depended on it. The cost of getting it wrong was close to zero. That phase did not last long. In The … Continue reading Prompts are becoming Code, but we still treat them like Strings →

Cursor 2.0 and Composer Model

Released on October 29, 2025, Cursor 2.0 is a major update to the AI-driven code editor that promises a new multi-agent interface and the debut of Cursor’s own coding model, Composer. As someone who uses Cursor every day, I couldn’t wait to try out the new 2.0 release. I spent some time exploring what’s new. … Continue reading Cursor 2.0 and Composer Model →

Why does MCP matter? A Deep Dive for Engineers

Everyone's talking about MCP (Model Context Protocol) and how it's supercharging workflows in tools like Claude Desktop, Cursor, and other desktop apps. And yeah, the integrations with desktop environments are cool. But honestly, MCP is way more than just these integrations for desktop applications. You’ve probably seen folks compare MCP to USB-C for AI. It’s … Continue reading Why does MCP matter? A Deep Dive for Engineers →