Ai agents
Evaluate a test conversation
POST
Evaluate a test conversation (from agents.test) against plain-language criteria with an AI judge. Used by resolido test. Uses AI credits.
bearer testingheader
AuthorizationBearer <token>API key (rsl_live_…) from Settings → Developers.
Scope: testing
conversationId*stringconversationId returned by agents.test (chat_…).
application/json- body
criteria*array<>What the AI replies must do, e.g. "Mentions the 14-day return period".
Items
1 <= items <= 10Success
application/json- response
results*array<>curl -X POST "https://example.com/test-conversations/string/judge" \ -H "Content-Type: application/json" \ -d '{ "criteria": [ "string" ] }'{ "results": [ { "criterion": "string", "pass": true, "reason": "string" } ]}