MCP vs Skills

A common question that I still see flying around is that: will skills replace MCP? I understand why people ask. Both can extend what an AI agent can do. A skill can include scripts that call APIs, while an MCP server can expose tools that call those same APIs. They can look like two ways … Continue reading MCP vs Skills →

How I run AI coding agents as a team with AI DevKit

I spend most of my time in the AI DevKit agent console. I start one agent as the manager, usually Codex, and brainstorm with it. Once an idea becomes concrete enough to execute, I ask the manager to create another agent and hand off the work. That executor might run in Codex, Claude Code, Pi, … Continue reading How I run AI coding agents as a team with AI DevKit →

I read every Claude Code hook so you don’t have to

When building AI DevKit, I had to look much deeper into different coding agent harnesses. Each one has its own structure, workflow, and mental model. In this post, I’ll share what I learned from digging into Claude Code hooks. Claude Code has 27 hook events. I went through all of them. Most are not worth … Continue reading I read every Claude Code hook so you don’t have to →

A practical roadmap to learn agentic engineering

A lot of engineers want to learn agentic engineering now. I think many of them are starting from the wrong end. They jump straight into MCP, multi-agent systems, autonomous workflows, and every shiny demo on X. It looks exciting and also feels like the future. But for most engineers, that is not the right place … Continue reading A practical roadmap to learn agentic engineering →

AI adoption is not AI maturity

I used to think the hard part was getting people to use AI. Now I think that is only the first step. AI is becoming part of how we write, build, research, design, analyze, and operate. That is a good thing. I use AI heavily myself, and I believe it can meaningfully increase the leverage … Continue reading AI adoption is not AI maturity →

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 →