You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
A controlled benchmark comparing 10 AI agent workflow patterns on a shared structured business dataset. Every pattern runs the same 25 tasks against the same data using the same LLM — results are directly comparable.
Learning repository for testing ML workflow patterns through iterative experiments. Documents what works and what fails to enable research and citizen science initiatives.
A Claude cowork skill for designing AI agent architectures via Socratic deep interviewing. Five-phase pipeline: interview → recommendation → blueprint → modules → prototype. Based on Anthropic's Building Effective Agents framework.