> ## Documentation Index
> Fetch the complete documentation index at: https://tyk-joancamostyk-patch-19.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Privacy Levels

> The privacy score system Tyk AI Studio uses to control which LLMs, Tools, and Data Sources can be used together.

## Availability

| Edition                                                                                                                               | Deployment Type      |
| :------------------------------------------------------------------------------------------------------------------------------------ | :------------------- |
| [Community](/ai-management/ai-studio/overview#community-edition) & [Enterprise](/ai-management/ai-studio/overview#enterprise-edition) | Self-Managed, Hybrid |

Tyk AI Studio assigns a privacy score to LLM configurations, Tools, and Data Sources. This score controls which resources can be used together, so that sensitive data cannot reach a less trusted LLM.

## The Privacy Score Scale

The UI presents four named privacy levels. Each maps to a fixed integer score:

| Level            | Score | Typical Use                                                                 |
| :--------------- | :---- | :-------------------------------------------------------------------------- |
| **Public**       | 25    | Safe to share, for example blogs or press releases.                         |
| **Internal**     | 50    | Limited to users within your organization, for example reports or policies. |
| **Confidential** | 75    | Sensitive business data, for example financials or strategies.              |
| **Restricted**   | 100   | PII or personal data, for example names, emails, or customer records.       |

<Note>
  Privacy scores are stored as plain integers. The four named levels above map to the code's internal scale, but the live create/edit forms for LLMs, Tools, and Data Sources currently show a raw 0-100 number field, not a named-level selector.
</Note>

## How the Comparison Works

A resource with a higher privacy score than the LLM it is used with cannot be attached to that LLM. For example:

* A **Restricted** (100) Data Source cannot be used with an LLM Configuration whose privacy score is only **Internal** (50).
* A **Public** (25) Tool can be used with any LLM Configuration, since 25 is the lowest score.

This check applies to:

* [Tools](/ai-management/ai-studio/tools) used with an LLM Configuration.
* [Data Sources](/ai-management/ai-studio/datasources-rag) used with an LLM Configuration in a RAG-enabled Chat.
* [Apps](/ai-management/ai-studio/admin-apps), when an admin approves or edits the App's associated resources.

If a user tries to combine resources that fail this check, Tyk AI Studio blocks the action and shows an error.

## Where You Set a Privacy Score

You set a privacy score when you create or edit:

* An LLM Configuration, under [LLM Management](/ai-management/ai-studio/llm-management).
* A Tool, under [Tools](/ai-management/ai-studio/tools).
* A Data Source, under [Data Sources](/ai-management/ai-studio/datasources-rag).

Community submissions to the [AI Portal](/ai-management/ai-studio/ai-portal) also carry a suggested privacy score from the submitter, which an admin can change before approving the submission.