# Bodyguard

> Bodyguard Product Documentation

## Documentation

### Getting started

- [Introduction](https://docs.bodyguard.ai/en/documentation/introduction.md): Bodyguard protects your platform from toxic content using contextual AI. Get severity ratings, classifications, and recommended actions in real time.

### Taxonomy

- [Text classifications](https://docs.bodyguard.ai/en/documentation/taxonomy/text-classifications.md): A complete reference to Bodyguard's text taxonomy: the signals we use to describe content and the classifications we detect.
- [Image classifications](https://docs.bodyguard.ai/en/documentation/taxonomy/image-classifications.md): A complete reference to Bodyguard's image taxonomy: the classifications we detect in visual content.
- [Username classifications](https://docs.bodyguard.ai/en/documentation/taxonomy/username-classifications.md): A complete reference to Bodyguard's username taxonomy: the classifications we detect in username strings.

## API Reference

### API Documentation

- [Introduction](https://docs.bodyguard.ai/en/api-reference/introduction.md): Learn how to authenticate, handle errors, and understand rate limits for the Bodyguard API.
- [Key concepts](https://docs.bodyguard.ai/en/api-reference/concepts.md): Understand the core building blocks of the Bodyguard API: organizations, sources, channels, references, and publication dates.
- [Reseller Guide](https://docs.bodyguard.ai/en/api-reference/reseller.md): Advanced request fields available exclusively to Bodyguard reseller partners.

### Reference

#### Analyze

- [Analyze a text message](https://docs.bodyguard.ai/api-reference/analyze/analyze-a-text-message.md): Analyzes a text message/comment and returns its moderation classification, severity, target, detected language, and a recommended moderation action.
- [Analyze an image](https://docs.bodyguard.ai/api-reference/analyze/analyze-an-image.md): Analyzes an image by URL or by inline image bytes. Returns a list of classifications for the image and, when OCR is enabled, the text extracted from the image along with its own text analysis.
- [Analyze a username](https://docs.bodyguard.ai/api-reference/analyze/analyze-a-username.md): Analyzes a username string to detect inappropriate, offensive, or otherwise undesirable content and returns a list of classifications.

#### Feedback

- [Text analysis feedback](https://docs.bodyguard.ai/api-reference/feedback/text-analysis-feedback.md): 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.
- [Image analysis feedback](https://docs.bodyguard.ai/api-reference/feedback/image-analysis-feedback.md): 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.
- [Username analysis feedback](https://docs.bodyguard.ai/api-reference/feedback/username-analysis-feedback.md): Sends [feedback](/en/api-reference/concepts#feedback) on a classification returned by [`POST /analyze/v1/username`](/api-reference/analyze/analyze-a-username) that you judge incorrect for a given username, with the classifications you would have expected instead.

## OpenAPI Specs

- [analyze.openapi](/openapi/analyze.openapi.yaml)
- [feedback.openapi](/openapi/feedback.openapi.yaml)
- [stats.openapi](/openapi/stats.openapi.yaml)

> The links below point to documentation indexes. Follow each `/_llms/` index recursively until you reach documentation pages.

## Indexes

- [French (13 pages)](https://docs.bodyguard.ai/_llms/fr.txt): Documentation for French.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.