Create Eval
Create an eval for an agent.
Evals are the criteria used to grade calls after analysis. Eval names must be unique per agent.
Authorizations
Path Parameters
Body
Input schema for creating/updating an eval.
Extra context the AI sees when scoring a call; the transcript is always included. Allowed values: system_prompt, tools, allowed_capabilities, workflow (the agent's configuration), or metadata.<key> for a value from the call's metadata, with dots for nested keys (e.g. metadata.account.region). Keys are case-sensitive, and a key a call does not have is skipped for that call. Any other value returns a 422. Defaults to none.
Response
Successful Response
Response schema for an eval.