AI Agents Need Artifacts, Not Activity
I got tired of AI agents sounding busy and leaving nothing behind. Here's the boring rule I now use before calling agent work done.
I got tired of AI agents sounding busy and leaving nothing behind. Here's the boring rule I now use before calling agent work done.
You've done it. Your teammate just pushed a new env var to .env.example and now nothing works. Here's the fix — and why AI coding agents need it even more than you do.
AI agents aren't magic. They're a loop. Here's the full picture — with a live dashboard you control.
Spoiler: you probably don't need to. Here's what actually happens after you integrate an LLM API, from whispering to a dragon to raising one from an egg.
I built a zero-cost markdown blog. Then I got bored. So I taught it to render React components without MDX.
You spin up a new Docker Compose stack and port 8080 is already taken. Again. Here's a tiny Bash tool that catches conflicts before your containers even start.