Rate an assistant answer
The assistant.messages.rate operation: POST /api/v1/assistant/conversations/{conversationId}/messages/{messageId}/rating in the REST API and the assistant_messages_rate tool in the MCP server.
/api/v1/assistant/conversations/{conversationId}/messages/{messageId}/ratingRates one of the assistant's answers in your own conversation: thumbs up or down, with an optional comment
(at most 1,000 characters). Rating again replaces the earlier rating. Rated answers help Ownrecord test the
assistant; they are anonymised before they leave your organization.
Who can call it: the conversation's owner, signed in.
At a glance
- REST:
POST /api/v1/assistant/conversations/{conversationId}/messages/{messageId}/rating - MCP tool:
assistant_messages_rate - Operation ID:
assistant.messages.rate - Scope: Platform
- Permission:
account:write - Risk tier:
write - Dry run: Supported (send
Ownrecord-Dry-Run: true) - Idempotency:
Idempotency-Keyrequired - Modes: Test and live
- Authentication: API key with the
account:writescope - Since: M11
Request
Path parameters
| Field | Type | Description |
|---|---|---|
conversationId | aconv_… ID | The conversation (aconv_…). |
messageId | amsg_… ID | The assistant's answer (amsg_…). |
Body
A JSON object (Content-Type: application/json):
| Field | Type | Required | Description |
|---|---|---|---|
rating | one of up, down | Yes | |
comment | string | No |
Response
200 OK with a JSON object:
| Field | Type | Description |
|---|---|---|
id | amsg_… ID | |
object | "assistant_message" | |
role | one of user, assistant, tool | |
content | string | |
parts | array of object | The answer's citations, tool activity, action cards, results and refusals (the assistant protocol). |
rating | object or null | |
createdAt | date-time |
Examples
Thumbs up
POST /api/v1/assistant/conversations/aconv_01jbz3k6q2e8w1m0v9r7t5y4x3/messages/amsg_01jbz3k6q9h8g7f6e5d4c3b2a1/rating
Authorization: Bearer or_test_…
Idempotency-Key: 3f1c9a52-7d0e-4b8f-9a61-0c2d5e8b7f14
Content-Type: application/json
{
"rating": "up"
}
Response (200):
{
"id": "amsg_01jbz3k6q9h8g7f6e5d4c3b2a1",
"object": "assistant_message",
"role": "assistant",
"content": "I've prepared the coupon. Review the preview on the card, then click **Confirm** to run it.",
"parts": [
{
"type": "action_card",
"card": {
"proposalId": "amsg_01jbz3k6q9h8g7f6e5d4c3b2a1:1",
"operationId": "coupons.create",
"inputHash": "4f6c1f0e3b2a9d8c7b6a5f4e3d2c1b0a9f8e7d6c5b4a39281706f5e4d3c2b1a0",
"title": "Create a coupon",
"effect": "Create a coupon (name: 20% off, percentOffPpm: 200000, duration: repeating), in test mode.",
"riskTier": "write",
"preview": {
"kind": "generic",
"result": {
"name": "20% off",
"percentOffPpm": 200000
}
},
"requiresFreshAuth": false,
"status": "executed"
}
}
],
"rating": {
"value": "up",
"comment": null
},
"createdAt": "2026-10-26T09:16:10.000Z"
}
Errors
| Code | HTTP status | When | What to do |
|---|---|---|---|
validation_failed | 400 | An ID is malformed, or the comment is too long. | Fix the fields listed in details.issues and send the request again. |
conversation_not_found | 404 | No such conversation of yours. | Start a new conversation. Conversations are deleted after the organization's retention period, and only their owner can open them. |
resource_not_found | 404 | The message isn't an answer of this conversation. | Check the ID and that your credentials are scoped to the right organization, entity, brand and mode. |
permission_denied | 403 | The caller isn't a signed-in person (an API key or OAuth token). | Ask an organization owner or admin for a role or scope that allows this action. |
It can also return these common errors: api_version_unsupported, invalid_json, unsupported_media_type, authentication_required, api_key_invalid, idempotency_key_required, idempotency_key_reused, idempotency_in_progress, rate_limited, internal_error.