Please enable JavaScript.
Coggle requires JavaScript to display documents.
LangSmith, Agent Evaluation, Evaluators, Evaluation Dataset - Coggle…
-
Agent Evaluation
-
Evaluate Single step
Inputs
Iaw user input (e.g., a prompt and / or a set of tools)
-
Outputs
LLM response(e.g., tool call, actions)
Evaluate Trajectory
-
output
"exact" trajectory (e.g., an expected sequence of tool calls)
-
-
-