Feedback - BeforeQuery

Submit an end-user rating for an assistant message.

POST https://api.agents.beforequery.com/api/v1/public/feedback

Auth: client key.

Request body

Field	Type	Required	Description
`message_id`	`string`	Yes	The assistant message being rated (`message_id` from the chat `done` event)
`rating`	`1–5`	Yes	Score — `5` = very helpful, `1` = not helpful
`comment`	`string`	No	Free-text comment

curl https://api.agents.beforequery.com/api/v1/public/feedback \
  -H "X-Client-Key: bq_pk_..." \
  -H "Content-Type: application/json" \
  -d '{"message_id": "msg_uuid", "rating": 5, "comment": "Spot on!"}'

Returns 2xx with no meaningful body.

Where feedback goes

Analytics — positive/negative ratios per project, per day.
Knowledge gaps — negatively-rated and unanswered questions feed the gap report (GET /api/v1/projects/:id/analytics/gaps), telling your team what to document next.
Retrieval boosting — feedback signals improve future ranking.
Evals — sampled answers are additionally scored by LLM judges for groundedness and faithfulness; see Analytics & Evals.

SDK equivalents

// @beforequery/sdk
await bq.feedback({ messageId: "msg_uuid", rating: 5, comment: "Spot on!" });

// @beforequery/react
await sendFeedback(messageId, 1, "Wrong answer");

The widget renders thumbs up/down on every answer automatically.