> 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/document-anonymization.md).
# Document anonymization
This article walks you through the basic process of anonymizing the first document in the Bluur system.
{% stepper %}
{% step %}
### Adding a document
To begin, add a document to the system. You can do this from [**Quick anonymization**](broken://pages/0c28754767bf79c3edf81e783574911e361b6976) on the dashboard or from the selected [**project.**](/en/features/projects.md) Select a file from your disk or drag it into the document upload field. After the file is added, the system will begin processing it.
{% hint style="info" %}
Supported file formats are: **PDF, JPG, JPEG, JPE, JIF, JFIF, JFI, PNG, TIFF, TIF, TXT, DOC and DOCX.**
The maximum size of a single document is **10 MB**. When adding multiple documents to a project, their total size cannot exceed **100 MB**.
{% endhint %}
{% endstep %}
{% step %}
### Automatic classification
After a document is uploaded, Bluur automatically starts classifying the data.
The system analyzes the document and marks elements that may require protection, such as personal data, contact data, financial data, address data, signatures, identification numbers, and other confidential information.
{% hint style="info" %}
The classification time depends on the document size and the number of areas containing data that need to be recognized. The analysis progress is visible on the loading bar. For documents containing around 1,000 such fields, classification usually takes no longer than 30 seconds.
{% endhint %}
{% endstep %}
{% step %}
### Field verification
After classification is complete, the document view with the marked fields will open.
Before anonymizing, check whether the system has correctly recognized the data that requires protection. If necessary, you can delete a mistakenly detected field, move it, or change its size.
**Delete field** – hover over the mark and press **Delete**.\
**Move the field** – click the field with the left mouse button and drag it to another place.\
**Resize the field** – drag the square on the edge of the mark.
A detailed description of working with detected fields can be found in the section [**AI classification**.](/en/features/working-with-a-document/stages/ai-classification.md)
{% endstep %}
{% step %}
### Proceeding to anonymization
After checking the fields, move on to the stage **Anonymization**.
You can do this from the top bar of the document view, the menu on the left, or using the button **Select fields**.
{% endstep %}
{% step %}
### Data selection
At the anonymization stage, the user can decide which data categories should be hidden in the document.
The sliders visible next to the individual data categories are used for this. If a category is turned off, the fields assigned to that category will not be anonymized.
If you want to hide an additional part of the document that was not marked by the system, you can manually select your own area for anonymization.
{% endstep %}
{% step %}
### Performing anonymization
To perform anonymization, click the button **Anonymize**.
The system will overlay black boxes on all active areas selected for anonymization. This means that the fields detected by the system and additional areas manually selected by the user will be hidden.
{% hint style="warning" %}
At this stage, the user can undo saved changes in the system and restore the document to the classification stage. The ability to undo changes does not apply to downloaded files. In the anonymized output file, anonymization is always irreversible.
{% endhint %}
{% endstep %}
{% step %}
### Downloading the document
After anonymization is complete, download the finished file.
The anonymized document does not overwrite the original file on the user's disk. The user downloads it as a new file with the suffix **\_redacted\_data** and the date of anonymization. E.g. contract\_redacted\_data\_2026\_03\_31.pdf.
{% endstep %}
{% step %}
### Archiving the document
After anonymization, you can archive the document.
Archiving removes the original source document from the system. Only the anonymized version of the document remains in the system.
More information about storing and deleting documents can be found in the section [**Document retention**.](/en/features/settings/anonymization/retention.md)
{% hint style="warning" %}
After archiving a document, it is no longer possible to return to editing it in the system. Before archiving, make sure you have the original file on your disk if you may need access again in the future to the data removed as a result of anonymization.
{% endhint %}
{% endstep %}
{% endstepper %}
### Summary
To anonymize your first document, add the file to the system, check the AI classification results, proceed to the anonymization stage, select the range of data to hide, and click **Anonymize**. After the process is complete, download the finished anonymized version of the document.
---
# 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/getting-started/quick-start/document-anonymization.md?ask=&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.
