> ## 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. # Text analysis feedback > Sends [feedback](/en/api-reference/concepts#feedback) on a classification returned by [`POST /analyze/v1/text`](/api-reference/analyze/analyze-a-text-message) that you judge incorrect for a given message, 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 [text taxonomy](/en/documentation/taxonomy/text-classifications) to understand the classifications you can add or remove. ## OpenAPI ````yaml /openapi/feedback.openapi.yaml post /feedback/v1/text 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/text: post: tags: - Feedback summary: Text analysis feedback description: > Sends [feedback](/en/api-reference/concepts#feedback) on a classification returned by [`POST /analyze/v1/text`](/api-reference/analyze/analyze-a-text-message) that you judge incorrect for a given message, 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 [text taxonomy](/en/documentation/taxonomy/text-classifications) to understand the classifications you can add or remove. operationId: bodyguard.feedback.v1.CreateTextFeedback requestBody: required: true content: application/json: schema: $ref: >- #/components/schemas/bodyguard.feedback.v1.CreateTextFeedbackRequest examples: removeClassification: summary: Remove a classification that does not apply value: analyzeRequest: channelId: __YOUR_CHANNEL_ID__ text: Einstein is an asshole publishedAt: '2026-04-23T10:30:00.000Z' reference: comment-12346 classificationsToRemove: - INSULT notes: Quoting a well-known joke, not an insult directed at anyone. confidence: HIGH addAndRemove: summary: Replace a classification value: analyzeRequest: channelId: __YOUR_CHANNEL_ID__ text: Einstein is an asshole publishedAt: '2026-04-23T10:30:00.000Z' language: en reference: comment-12346 author: username: johndoe reference: user-987 countryCode: US classificationsToRemove: - INSULT classificationsToAdd: - CRITICISM notes: Criticism of a public figure, not a personal insult. confidence: MEDIUM responses: '200': description: Feedback recorded. content: application/json: schema: $ref: >- #/components/schemas/bodyguard.feedback.v1.CreateTextFeedbackResponse examples: recorded: summary: Feedback recorded value: id: 018f3b04-9c11-7a52-8e0d-3b7c9a1f4e62 components: schemas: bodyguard.feedback.v1.CreateTextFeedbackRequest: type: object required: - analyzeRequest description: >- Feedback on a text 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.AnalyzeTextRequest' description: >- The analyze request body you originally sent to `POST /analyze/v1/text`. 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 message belongs to, and your own `reference` for the message when you sent one. classificationsToRemove: type: array description: >- Classifications Bodyguard returned that you judge do not apply to this content. See the [text taxonomy](/en/documentation/taxonomy/text-classifications) for the full list. items: type: string example: - INSULT classificationsToAdd: type: array description: >- Classifications you judge apply to this content but that Bodyguard did not return. See the [text taxonomy](/en/documentation/taxonomy/text-classifications) for the full list. items: type: string example: - CRITICISM notes: type: string description: >- Free-text comment explaining why you judge the content differently. Helps Bodyguard's moderation teams understand the context behind your feedback. 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.CreateTextFeedbackResponse: type: object required: - id properties: id: type: string format: uuid description: Bodyguard's identifier for this feedback. bodyguard.analyze.v1.AnalyzeTextRequest: type: object required: - channelId - text properties: channelId: type: string format: uuid description: >- Identifier of the [channel](/en/api-reference/concepts#channel) the text belongs to. Provided by Bodyguard. text: type: string maxLength: 10000 description: The text content that was analyzed. example: I love this product! publishedAt: type: string format: date-time description: >- [Publication date](/en/api-reference/concepts#publication-date-publishedat) of the message. reference: type: string maxLength: 256 description: Your own stable identifier for this piece of content. permalink: type: string format: uri description: A public URL pointing to the content, if available. language: type: string minLength: 2 maxLength: 2 description: >- Hint about the content language as an ISO 639-1 code (e.g. `en`, `fr`). example: en post: $ref: '#/components/schemas/bodyguard.analyze.v1.AnalyzeTextRequest.Post' author: $ref: '#/components/schemas/bodyguard.analyze.v1.AnalyzeTextRequest.Author' 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 bodyguard.analyze.v1.AnalyzeTextRequest.Post: type: object required: - title description: >- Metadata about the post the analyzed content belongs to, as sent in the original analyze request. properties: title: type: string maxLength: 2048 description: Title or short description of the post. reference: type: string maxLength: 256 description: Your own stable identifier for this post. publishedAt: type: string format: date-time description: >- [Publication date](/en/api-reference/concepts#publication-date-publishedat) of the post. permalink: type: string format: uri description: Public URL of the post. countryCode: type: string minLength: 2 maxLength: 2 description: >- Country the post is aimed at, as an uppercase ISO 3166-1 alpha-2 code (e.g. `US`, `FR`). example: US bodyguard.analyze.v1.AnalyzeTextRequest.Author: type: object required: - username description: >- Metadata about the author of the content, as sent in the original analyze request. properties: username: type: string maxLength: 255 description: Display name / username of the author. reference: type: string maxLength: 256 description: Your own stable identifier for this author. permalink: type: string format: uri description: Public URL of the author's profile. profilePictureUrl: type: string format: uri description: URL of the author's profile picture. countryCode: type: string minLength: 2 maxLength: 2 description: >- Country the author is located in, as an uppercase ISO 3166-1 alpha-2 code (e.g. `US`, `FR`). example: US 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 ``` ````