aft was my stab at having a way to understand what claude is doing and also having the language to reason about differences in model behavior when we make them do long agentic runs / change prompts / alter tools etc. The intention of the toolkit to provide an…
blog on why this exists
A Python toolkit for studying AI agent behavior without looking inside the model.
Disclaimer : this is a hobby project. I have a full time job and I am doing this because I … [+9402 chars]
