> 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/getting-started/quick-start/key-features/ai-classification.md).

# AI classification

AI classification is used to automatically recognize and mark data that may require protection from further use of the document.

The system uses search and data recognition algorithms developed by BTC, as well as mechanisms based on artificial intelligence. The classifier analyzes the content and structure of the document, identifies selected types of information, and indicates the places where they were detected.

The recognized elements are marked directly in the document view and grouped by category. This allows the user to review the analysis result before proceeding to anonymization.

### Classification scope

The system classifies, among others:

**Personal data**\
First name, last name, PESEL number, document number, face photo, fingerprints.

**Organization data**\
Tax identification number, REGON, KRS, position.

**Contact details**\
Phone number, email address.

**Financial data**\
IBAN, credit card, amount, amount written in words.

**Signatures**\
Handwritten signature, stamp, stamp with signature, writing.

**Address data**\
Street and number, postal code, city.

**Identification numbers**\
Land and mortgage register number, ISBN, ISSN, license plate, VIN number.

**Other elements**\
Date, URL, barcode, QR code.

### Verification of results

After the classification is complete, the user should check all detected fields and make sure that the data requiring protection has been correctly marked.

If necessary, you can:

* delete an incorrectly detected field,
* change its position,
* adjust the size of the selection,
* save the changes made before proceeding to anonymization.

AI classification supports the user in finding data, but does not replace final verification.

{% hint style="info" %}
At the classification stage, the user can edit fields detected by the system. Custom areas intended to be hidden can only be added at the anonymization stage. 
{% endhint %}

### Next stage

After reviewing and correcting the classification results, the user can proceed to the anonymization stage and decide which data categories should be permanently removed from the resulting version of the document.

More information can be found in the sections [**Document view**](/en/functions/working-with-a-document/stages/ai-classification/saving.md) and [**Anonymization**.](/en/functions/working-with-a-document/stages/anonymization.md)


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://bluurdoc.bluur.ai/en/getting-started/quick-start/key-features/ai-classification.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.