Evaluation
Create Evaluation Criteria
Create a criteria mapped to an evaluation config.
POST
Create evaluation criteria
Create a criteria mapped to an evaluation config.
eval_id is required.
Updating an existing one: see Update Evaluation Criteria.
Scoring fields
Each call gets a score from 0 to 100 for this criteria. The thresholds decide the result:
With the UI defaults (
pass_above 70, fail_below 40) a score of 85 passes, 55 is “Review” and 30 fails. review_below is the top of the Review band, so it should be pass_above - 1 (69 here). The UI sets it for you, and you can leave it out.
Keep
fail_below lower than pass_above.
Criteria
Pickcriteria from this list (send the name exactly). If you do not send evaluation_prompt when creating, the default prompt below is used.
Body
application/json
Criteria to score, picked from the list. When creating and evaluation_prompt is not sent, the default prompt of this criteria is used.
Available options:
Empathy, Language Switch, Turn Taking, Context Awareness, Recovery From Errors, Intent Recognition, Greeting Accuracy, Intent Confirmation, Probing Questions, Call Closing, No Offensive Content, No Misrepresentation, Privacy Compliance, Confidence Level, Input Metadata Consistency Response
200 - application/json
Success
The response is of type object.

