> 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/faq.md).
# FAQ
Answers to common questions about what N-Assistant does, how it handles data and how access works.
This page answers common questions about N-Assistant: what it can do, how it handles data, who can use it and how your conversations are stored. For setup steps, see [Get started with N-Assistant](/netmera-user-guide/ai-features/n-assistant/get-started-with-n-assistant.md). For the full security overview, see [Security and privacy](/netmera-user-guide/ai-features/n-assistant/security-and-privacy.md).
### General
What is N-Assistant?
N-Assistant is Netmera's marketing intelligence assistant. It reads your Netmera data, interprets it and offers data-based action recommendations for your marketing and engagement strategy. You ask in plain language, and it answers with insights, key figures, charts and recommended next steps.
What kind of questions can I ask?
Ask business questions about your campaigns, audience and engagement, and get more than numbers. N-Assistant does not stop at reporting what happened. It explains why, and it recommends what to do next: how to improve a campaign, how to increase clicks, how to bring performance back up.
Ask for an analysis, such as “Analyze the performance of the push notification campaigns I sent recently.” Or ask for direction, such as “Look at the click rates of my emails. How can I increase clicks?” or “How can I improve the performance of this campaign?”
Each answer combines findings with prioritized recommendations that are based on your own Netmera data, so you know where to start. Whether to apply a recommendation is your decision. See [Use cases and example requests](/netmera-user-guide/ai-features/n-assistant/use-cases-and-example-requests.md) for more examples.
Which Netmera data can N-Assistant work with?
N-Assistant uses the Netmera MCP toolset. Analytics, campaign reports and A/B tests, workflows and automations, and event and profile attributes are all available from a single conversation.
Can I keep the insights from a conversation?
Yes. Turn the insights you receive into a custom dashboard in your panel. You can also return to any previous conversation from your chat history.
### Actions and control
Can N-Assistant send campaigns?
No. N-Assistant works with read-only permission, and the write tools in Netmera MCP are locked for security reasons. It cannot send campaigns, change segments or workflows, or communicate with end users.
Does N-Assistant apply its recommendations automatically?
No. N-Assistant recommends and does not apply. Whether to use a recommendation is always your decision.
### Data and privacy
Is my customers’ personal data shared with AI providers?
No. Personal data of your customers is not shared with any AI provider based outside Turkey, including OpenAI.
Can the model see the identity, email address or phone number of a specific user?
No. 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.
Does the model know which brand I work for?
Information that identifies your brand is not passed to the model in tool results.
What is sent to the LLM provider?
Your questions and the results of the tools that N-Assistant calls are sent to the LLM provider through Netmera. Personal data of your customers is not part of these results, because analyses run on anonymized data. Describe what you want to analyze in business terms, and do not type personal data of your customers into a question.
### Access and permissions
How does N-Assistant connect to my Netmera data?
N-Assistant uses tools that run on the Netmera MCP server, the same server that connects AI clients such as Claude to Netmera. It goes through the same role check: you see only the tools that your role allows, and your role is verified again on every call. Unlike an external AI client, N-Assistant authenticates with a signed token instead of OAuth, and it works with read-only permission.
What can I see in N-Assistant?
Access is based on your role. N-Assistant uses the tools that your Netmera role allows. Tools that are closed to your role are not shown to you, and data of an app you are not a member of cannot be accessed.
How often is my access checked?
Your permission is verified again on every call, so a change to your role applies to your next question.
Why can a colleague see results that I cannot?
N-Assistant follows the role of each person. If two roles have different access in Netmera, the same question can return different results.
### Conversations
Are my conversations saved?
Yes. Every conversation is saved automatically, and your chat history is stored in Netmera.
Can I continue a previous conversation?
Yes. Open a previous conversation from your chat history and pick up where you left off. N-Assistant keeps the context of the conversation.
Can I rename, pin or delete a conversation?
Yes. You can edit conversation titles, pin important conversations and delete the ones you no longer need. See [Chat history](/netmera-user-guide/ai-features/n-assistant/chat-history.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 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/faq.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.