> ## Documentation Index > Fetch the complete documentation index at: https://docs.bodyguard.ai/llms.txt > Use this file to discover all available pages before exploring further. # Image analysis feedback > Sends [feedback](/en/api-reference/concepts#feedback) on a classification returned by [`POST /analyze/v1/image`](/api-reference/analyze/analyze-an-image) that you judge incorrect for a given image, with the classifications you would have expected instead. Send the exact analyze request body you originally submitted in `analyzeRequest` so Bodyguard can reproduce the analysis your feedback refers to. Before diving in, we recommend reading the [image taxonomy](/en/documentation/taxonomy/image-classifications) to understand the classifications you can add or remove. ## OpenAPI ````yaml /openapi/feedback.openapi.yaml post /feedback/v1/image openapi: 3.1.0 info: title: Bodyguard Feedback API version: 1.0.0 servers: - url: https://api.bodyguard.ai security: - ApiKeyAuth: [] tags: - name: Feedback description: Classification feedback endpoints. paths: /feedback/v1/image: post: tags: - Feedback summary: Image analysis feedback description: > Sends [feedback](/en/api-reference/concepts#feedback) on a classification returned by [`POST /analyze/v1/image`](/api-reference/analyze/analyze-an-image) that you judge incorrect for a given image, with the classifications you would have expected instead. Send the exact analyze request body you originally submitted in `analyzeRequest` so Bodyguard can reproduce the analysis your feedback refers to. Before diving in, we recommend reading the [image taxonomy](/en/documentation/taxonomy/image-classifications) to understand the classifications you can add or remove. operationId: bodyguard.feedback.v1.CreateImageFeedback requestBody: required: true content: application/json: schema: $ref: >- #/components/schemas/bodyguard.feedback.v1.CreateImageFeedbackRequest examples: falsePositive: summary: Remove a classification that does not apply value: analyzeRequest: channelId: __YOUR_CHANNEL_ID__ publishedAt: '2026-04-23T10:30:00.000Z' imageUrl: https://cdn.example.com/uploads/photo.jpg classificationsToRemove: - PARTIAL_NUDITY notes: Swimwear on a beach, not nudity. confidence: VERY_HIGH responses: '200': description: Feedback recorded. content: application/json: schema: $ref: >- #/components/schemas/bodyguard.feedback.v1.CreateImageFeedbackResponse examples: recorded: summary: Feedback recorded value: id: 018f3b05-4d80-7b19-a6c2-71e4f0d8b331 components: schemas: bodyguard.feedback.v1.CreateImageFeedbackRequest: type: object required: - analyzeRequest description: >- Feedback on an image analysis. Provide at least one of `classificationsToAdd`, `classificationsToRemove`, or `notes` — a request with none of the three is considered invalid. properties: analyzeRequest: $ref: '#/components/schemas/bodyguard.analyze.v1.AnalyzeImageRequest' description: >- 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](/en/api-reference/concepts#channel) the image belongs to. If you analyzed the image by inline bytes, send the same base64 payload in `imageData`. classificationsToRemove: type: array description: >- Classifications Bodyguard returned that you judge do not apply to this content. See the [image taxonomy](/en/documentation/taxonomy/image-classifications) for the full list. items: type: string example: - PARTIAL_NUDITY classificationsToAdd: type: array description: >- Classifications you judge apply to this content but that Bodyguard did not return. See the [image taxonomy](/en/documentation/taxonomy/image-classifications) for the full list. items: type: string ocrIssue: type: boolean description: >- Whether there is an issue with OCR or not. Can be omitted if your feedback does not concern OCR at all notes: type: string description: >- 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: $ref: '#/components/schemas/bodyguard.feedback.v1.Feedback.Confidence' bodyguard.feedback.v1.CreateImageFeedbackResponse: type: object required: - id properties: id: type: string format: uuid description: Bodyguard's identifier for this feedback. bodyguard.analyze.v1.AnalyzeImageRequest: type: object required: - channelId properties: channelId: type: string description: >- Identifier of the [channel](/en/api-reference/concepts#channel) the image belongs to. Provided by Bodyguard. publishedAt: type: string format: date-time description: >- [Publication date](/en/api-reference/concepts#publication-date-publishedat) of the image. imageUrl: type: string format: uri description: >- Public URL of the image that was analyzed. Only one of `imageUrl` or `imageData` can be provided. imageData: type: string format: byte description: >- Base64-encoded image bytes. Only one of `imageUrl` or `imageData` can be provided. oneOf: - required: - imageUrl - required: - imageData bodyguard.feedback.v1.Feedback.Confidence: type: string description: >- 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. enum: - LOW - MEDIUM - HIGH - VERY_HIGH securitySchemes: ApiKeyAuth: type: apiKey in: header name: Authorization x-default: ApiKey description: | API key authentication. Provide your key in the `Authorization` header with the `ApiKey` scheme: ``` Authorization: ApiKey ``` ````