List evaluation cases
The Agents' evaluation cases, newest first: WhatsApp replies or completed voice-call responses with explicit internal team feedback (authored) or a following team message (correction), and the originating Agent version when recorded (unknown for historical voice calls). Filter by agentId, replyMessageId, source or status (open, kept, dismissed). Requires conversation read authority as well as Agent read authority. Read the conversation with its own operations to judge a case. Not an AI tool.
- Scopes: any one of
raiz:agents:read,raiz:agents:write; some inputs also needraiz:conversations:read,raiz:conversations:write - Credentials: an API key, a client-credentials token or a person's access token
- Effect: read-only; safe to retry
- Limits: response up to 2 MB
- CLI:
arbol raiz eval-cases list· not available on MCP
GET
https://api.getarbol.com/v1/raiz/eval-casesAuthorization
Query parameters
Returns
200
Successful operation.
400
INVALID_INPUT: The request does not match the published schema.INVALID_CURSOR: The cursor is malformed or belongs to a different list.