# Sensitivity Classification

### Sensitivity classification ensures that your most confidential data is only accessible to users with the appropriate clearance.

Each document in Katara can be assigned a sensitivity level that reflects the confidentiality of its content. This classification acts as a secondary gate for document [visibility](/about/corpuses/what-is-a-corpus/visibility.md) and [sharing](/about/corpuses/what-is-a-corpus/sharing.md).

### Four Sensitivity Levels

The system uses four standard sensitivity levels to categorize documents:

* **Level 0: Public**: Documents intended for a wide audience.
* **Level 1: Internal**: Standard organizational data used for day-to-day work.
* **Level 2: Confidential**: Sensitive information restricted to users with explicit clearance.
* **Level 3: Highly Confidential**: The most sensitive data, requiring the highest level of clearance.

### How Classification Works

When a user or application attempts to view a document, Katara performs a sensitivity check:

* **Rule**: A user or application can only view a document if its clearance level is greater than or equal to the document's sensitivity level.
* **Automatic Enforcement**: This check is applied across the entire platform, including search, document lists, and AI agent retrieval.
* **Shared Access**: Sharing a document does not bypass its sensitivity classification.

### Managing Classification

[Document owners](/about/corpuses/what-is-a-corpus/document-ownership.md) are responsible for assigning and maintaining the sensitivity level of their content.

* **Defaults**: New documents default to "Public" (Level 0) unless a different level is specified at creation time.
* **Updates**: Owners can re-classify their documents as the sensitivity of the content changes over time.
* **Legacy Documents**: Documents without an assigned owner follow their original organizational visibility rules until they are assigned an owner and classified.

### User Clearance Levels

Users and applications can each have a clearance level. This level determines the highest sensitivity of documents they are authorized to view.


---

# Agent Instructions: 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:

```
GET https://docs.katara.ai/about/corpuses/what-is-a-corpus/sensitivity-classification.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.