First hour with Claude's browser extension: I pointed it at our LLC registration and watched it work...
Developer built browser extension with Claude: discipline beat speed. Testing caught bulk edits, false claims, undocumented rules before ship. For CTOs: AI scales production bugs without guardrails. Rigorous testing, documented rules, proof-before-ship prevent disasters from cheap claims.
First hour with Claude's browser extension: I pointed it at our LLC registration and watched it work through the forms, finding the right pages, filling the fields, moving on. I sat there holding a coffee, contributing nothing.
I thought: I'm going to ship so many products.
I shipped one. Here's what happened in between.
Everything below was caught before launch. None of it was caught by being clever. It was caught by a process that got built slowly, mostly after being burned.
What went wrong
What happens when you let an AI write a browser extension I've been building Chrome...
I spent the last few months building a Chrome extension that detects HTML code blocks inside ChatGPT,...
A real log of an autonomous Claude agent going from zero to its first product — written from the...
I've been a software engineer for a while and I kept noticing the same friction points in my daily...
My extension had a bug that's the worst kind: it looked like it worked. You'd save a Claude...
I tried to build a SaaS. I'm shipping tiny libraries instead. For 7 days I poured energy...
