Comment by Jinyibruceli

I'm curious how you're handling the self-evolving part in practice. When I built browser automation agents with Claude API last year, the hardest problem wasn't the initial task execution - it was knowing when to stop iterating vs when the agent had legitimately improved its approach. Does autodidact have any safeguards against the agent just spinning in circles rewriting its own prompts, or do you rely on the user to define success criteria upfront?