> For the complete documentation index, see [llms.txt](https://user.netmera.com/netmera-user-guide/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://user.netmera.com/netmera-user-guide/ai-features/n-assistant/security-and-privacy.md).

# Security and privacy

How N-Assistant connects to your data, protects personal data and brand information, and controls access permissions.

N-Assistant is designed with data protection at the center. This page explains how N-Assistant connects to your Netmera data, what the model can and cannot see, how access is controlled, and why N-Assistant works with read-only permissions.

These controls let your team use AI-driven analysis while keeping customer data and brand information protected.

### Summary

<table><thead><tr><th width="240">Area</th><th>How it works</th></tr></thead><tbody><tr><td><strong>Connection</strong></td><td>N-Assistant reads your data through the Netmera MCP server, with the same role check that applies to AI clients such as Claude.</td></tr><tr><td><strong>Personal data</strong></td><td>Does not reach the model. Analyses run on anonymized data.</td></tr><tr><td><strong>Brand information</strong></td><td>Information that identifies your brand is not passed to the model.</td></tr><tr><td><strong>Access</strong></td><td>Your Netmera role decides which tools N-Assistant can use. Permissions are verified on every call.</td></tr><tr><td><strong>Actions</strong></td><td>Read-only. N-Assistant recommends, and you decide.</td></tr><tr><td><strong>Questions and results</strong></td><td>Your questions and tool results reach the LLM provider through Netmera.</td></tr><tr><td><strong>Conversation history</strong></td><td>Stored in Netmera.</td></tr></tbody></table>

### How N-Assistant connects to your data

The tools that N-Assistant uses run on the Netmera MCP server. Every tool call goes through the same role check:

* You see only the tools that your role allows.
* Your role is verified again on every call.

N-Assistant differs from an external AI client in a few ways:

<table><thead><tr><th width="231.859375">Area</th><th>How N-Assistant works</th></tr></thead><tbody><tr><td><strong>Authentication</strong></td><td>N-Assistant authenticates with a signed token instead of OAuth.</td></tr><tr><td><strong>App access</strong></td><td>Limited by the role check. If you are not a member of an app, you have no role in it, so N-Assistant cannot call tools for that app.</td></tr><tr><td><strong>Permission level</strong></td><td>Read-only. The write tools are closed.</td></tr><tr><td><strong>Questions and tool results</strong></td><td>Sent to the LLM provider through Netmera.</td></tr><tr><td><strong>Conversation history</strong></td><td>Stored in Netmera.</td></tr></tbody></table>

### Personal data does not reach the model

Personal data of your customers is not shared with any AI provider based outside Turkey, including OpenAI.

This applies to user-level queries as well. Even when a question is about a specific user, the model does not see the person’s identity, email address or phone number. Analyses run on anonymized data.

{% hint style="info" %}
Your questions are sent to the LLM provider through Netmera. Describe what you want to analyze in business terms, and do not type personal data of your customers into a question.
{% endhint %}

### Your brand is not visible to the model

Information that identifies your brand is not passed to the model in tool results.

### Your role decides what you can see

N-Assistant uses the tools that your Netmera role allows.

* Tools that are closed to your role are not shown to you.
* Your permission is verified again on every call.
* Data of an app you are not a member of cannot be accessed.

Two people who ask the same question can therefore get different answers if their roles have different access.

### N-Assistant recommends, you decide

N-Assistant works with read-only permission. The write tools in Netmera MCP are locked for security reasons.

<table><thead><tr><th width="253.96484375">N-Assistant can</th><th>N-Assistant cannot</th></tr></thead><tbody><tr><td>Analyze analytics, campaign reports and A/B tests</td><td>Send campaigns</td></tr><tr><td>Review workflows, automations, events and profile attributes</td><td>Change segments or workflows</td></tr><tr><td>Recommend next actions</td><td>Communicate with end users</td></tr></tbody></table>

Whether to apply a recommendation is always your decision.

### Conversation storage

Your conversation history is stored in Netmera. See [Chat history](/netmera-user-guide/ai-features/n-assistant/chat-history.md) to learn how to manage it.


---

# 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://user.netmera.com/netmera-user-guide/ai-features/n-assistant/security-and-privacy.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.