Writing

Most people think of AI as a chatbot. I think it's closer to a new operating system layer — and the teams building workflows on top of it will win.

OpenEvidence's moat isn't better models. It's that doctors share things with it they'd never tell ChatGPT — and that made me rethink where my own product's value actually comes from.

Sub-agents aren't about doing more things at once. They're about keeping your context clean.

When execution costs approach zero, the scarce input becomes real-world signal. Not more brainstorming. Actual conversations with actual people.