Sign in
latestOpenAPI 3.1.02026-08-10466368560.6 KB

2b2bab8b9017

chat

Evaluate Scenario

Evaluate a character's response to a benchmark scenario using LLM-as-judge

post/chat/evaluate-scenario

Request body

character_idstring uuid required
scenario_idstring required
scenario_titlestring required
scenario_tagsstring[] required
test_promptstring required
character_responsestring required
judge_modelstring

Response

Successful Response

{"stackTrail":"paths:/chat/evaluate-scenario:post:responses:200:content:application/json:schema","oasType":"schema","type":"unknown"}