AI coding agents are getting better fast, but I kept running into the same failure modes: they skip...
AI coding agents are getting better fast, but I kept running into the same failure modes:
they skip repository discovery
they invent APIs, flags, or config keys
they ignore existing project conventions
they add unnecessary infrastructure
Why AI Coding Agents Fail Senior Engineers (And What I Built to Fix It) AI coding agents...
How I built an engineering toolkit for AI coding agents I spend most of my day working...
I run several coding agents — Claude Code, Codex, and Gemini CLI — against the same repositories....
I’ve been thinking a lot about a failure mode in AI-assisted development that does not fit neatly...
Everyone loves a 10-minute demo of an AI agent building a snake game. But try to build a...
The problem isn't that agents are bad. It's that they fail the same way every time. AI...
