Conversation-Level vs Trace-Level Online Evals: Which Failures Each Can See
DEV Community
Conversation-Level vs Trace-Level Online Evals: Which Failures Each Can See
Span and trace evals judge one model call or one request. Conversation-level evals judge the whole multi-turn session. Here is which agent failures each unit can and cannot see, and how to run both without double-counting.
0 comments
No comments yet.