> For the complete documentation index, see [llms.txt](https://support.emarketeer.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://support.emarketeer.com/docs/docs_se/integrationer/ai-assistants/data-and-privacy.md).

# AI-assistenter: data och integritet

Vad en AI-assistent kan se i ditt eMarketeer-konto och vart datan tar vägen.

Vad en AI-assistent kan se i ditt eMarketeer-konto och vart datan tar vägen.

## Vad assistenten kan se

Assistenten läser från kontona du tillhör. Alla användare på ett konto kan läsa dess data via kopplingen, oavsett roll i eMarketeer. För att göra ändringar krävs rollen Marketing User eller Administrator på det kontot.

## Vart din data tar vägen

När du ställer en fråga skickas den data som behövs för svaret till den AI-leverantör du har kopplat. Det kan vara kontaktuppgifter och rapportsiffror. Ditt avtal med leverantören styr hur de hanterar datan.

eMarketeer sparar inget extra. Kalkylark som du exporterar raderas efter en dag.

## Personuppgifter

Du är fortfarande ansvarig för personuppgifterna i ditt eMarketeer-konto. Innan du delar kontaktdata med en AI-assistent bör du kontrollera att ditt avtal med leverantören omfattar behandling av personuppgifter.

## Koppla från

Du kan koppla från när som helst. Se [Koppla Claude till eMarketeer](https://support.emarketeer.com/docs/docs_se/integrationer/ai-assistants/connect-claude.md) eller [Koppla ChatGPT till eMarketeer](https://support.emarketeer.com/docs/docs_se/integrationer/ai-assistants/connect-chatgpt.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://support.emarketeer.com/docs/docs_se/integrationer/ai-assistants/data-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.
