> For the complete documentation index, see [llms.txt](https://bluurdoc.bluur.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://bluurdoc.bluur.ai/en/features/working-with-a-document/stages/ai-classification.md).

# AI classification

This section describes the automatic detection of data in documents. Here you will find information about data categories and editing marked fields.

### Document classification

After a document is added, the system automatically starts its classification.

The classifier uses data search and recognition algorithms developed by BTC as well as artificial intelligence-based mechanisms. It analyzes the document's content and structure, then marks the recognized elements directly on its pages.

After classification is complete, the user should review the detected fields. They can remove incorrect markings and change their position and size before proceeding to anonymization.

Classification supports finding data, but does not replace the user's final verification. Information about how the model works and document processing can be found in the section [**AI model security**.](/en/getting-started/quick-start/key-features/ai-model-security.md)

{% hint style="info" %}
**Tip:** Classification time depends on the document size and the number of areas containing data that needs to be recognized. The analysis progress is visible on the loading bar. For documents containing up to about 1000 such fields, classification usually takes no longer than 30 seconds.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://bluurdoc.bluur.ai/en/features/working-with-a-document/stages/ai-classification.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.