Skip to main content
POST
Image analysis feedback

Authorizations

Authorization
string
header
default:ApiKey <your-api-key>
required

API key authentication. Provide your key in the Authorization header with the ApiKey scheme:

Body

application/json

Feedback on an image analysis. Provide at least one of classificationsToAdd, classificationsToRemove, or notes — a request with none of the three is considered invalid.

analyzeRequest
object
required

The analyze request body you originally sent to POST /analyze/v1/image. Send it unchanged so Bodyguard can identify the exact analysis your feedback refers to. It already carries the channel the image belongs to. If you analyzed the image by inline bytes, send the same base64 payload in imageData.

classificationsToRemove
string[]

Classifications Bodyguard returned that you judge do not apply to this content. See the image taxonomy for the full list.

Example:
classificationsToAdd
string[]

Classifications you judge apply to this content but that Bodyguard did not return. See the image taxonomy for the full list.

ocrIssue
boolean

Whether there is an issue with OCR or not. Can be omitted if your feedback does not concern OCR at all

notes
string

Free-text comment explaining why you judge the content differently. Counts on its own: a feedback carrying only notes, with no classification change, is valid.

confidence
enum<string>

How confident you are about the classifications you submitted. Bodyguard uses it to prioritise which feedback to review first. You can base it on who flagged the content on your side — for example LOW or MEDIUM for a report from an end-user, HIGH or VERY_HIGH for a decision from your Trust & Safety team. Optional — omit it if you cannot qualify your confidence.

Available options:
LOW,
MEDIUM,
HIGH,
VERY_HIGH

Response

200 - application/json

Feedback recorded.

id
string<uuid>
required

Bodyguard's identifier for this feedback.