A question that I always try to think about when looking at great AI Demos : What went behind making this production ready? How would they actually measure and optimise the AI Agent beyond evals?
Share this post
Tracking Conversation Trees: Measure and…
Share this post
A question that I always try to think about when looking at great AI Demos : What went behind making this production ready? How would they actually measure and optimise the AI Agent beyond evals?