← All thoughts
ThoughtAI @Work

When my agents fail

If my agents fail, first I need to check if I’ve set them up for success.

And when they do fail, I add new guardrails + evals to make sure it doesn’t happen again and I catch it if it does.

Join the exploration

Thriving with AI newsletter

A roughly weekly newsletter where I share what I'm learning and building at the frontier of working with AI @Work and @Home.

Join now for early access to what launches in October and November.

Free, with a 100% money-back guarantee within 90 days.