Introducing flow-1, our new model trained with RL to find errors in agent traces. It matches GPT-6-sol in trace intelligence while being 23x cheaper. It also c…
Notes
Introducing flow-1, our new model trained with RL to find errors in agent traces. It matches GPT-6-sol in trace intelligence while being 23x cheaper. It also costs 25% less to run than GPT-6-luna. flow-1 finally makes it possible to monitor and understand every agent run,
Matched by shared tags first, then by kind.
Find@haaarshsingh
created a live agent trace waterfall that you can zoom and inspect 🔍 →
Find@flohoeller
Agent graph component, every call in real time