> For the complete documentation index, see [llms.txt](https://www.center.daxium-air.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.center.daxium-air.com/user-documentation/daxium-ai/getting-started.md).
# Getting Started
Activate Daxium AI on your workspace, check the prerequisites and understand how your data and AI credits are handled.
Daxium AI brings AI-powered features to Daxium-Air, such as rewriting the content of a text [field](/user-documentation/components-concepts-terminology.md#field) in a [submission](/user-documentation/components-concepts-terminology.md#submission).
{% hint style="info" %}
Daxium AI is currently in **beta**. To activate it on your [workspace](/user-documentation/components-concepts-terminology.md#workspace), contact your project manager or your account manager.
{% endhint %}
{% hint style="warning" %}
AI can make mistakes. Always review and double-check what an AI feature returns before you save or use it.
{% endhint %}
Once Daxium AI is activated, the administrators of the workspace get access to a new **AI Consumption** menu in the general settings of the [back office](/user-documentation/components-concepts-terminology.md#back-office). From this menu, they choose which AI features are available and follow how they are used: see [Features Activation & Consumption Tracking](/user-documentation/daxium-ai/features-activation-and-consumption.md).
## Prerequisites
{% hint style="warning" %}
AI features only work when the user is **online**. Without a network connection, they are unavailable.
{% endhint %}
### Licencing
Daxium-Air comes in three [licence tiers](/user-documentation/components-concepts-terminology.md#licence-tier): **Starter**, **Pro** and **Premium**.
AI features are only available with the **Pro** and **Premium** licence tiers. The Starter tier does not include them; if you want to try AI features for a limited time, contact your account manager.
{% hint style="info" %}
If your company has a specific contract with Daxium, or if you do not know your licence tier, contact your account manager.
{% endhint %}
Each [user](/user-documentation/components-concepts-terminology.md#user) is given a number of AI credits every month. This number varies according to the licence tier. Each completed request to an AI feature uses one credit.
Once a user has used all their credits, they can no longer use AI features until the next reset.
{% hint style="info" %}
AI credits are reset on the **1st of each month at midnight (UTC)**.
{% endhint %}
### Version prerequisites
To use AI features on mobile, users need at least:
* **Android:** version 3.1.2
* **iOS:** version 2.6.4
## How your data is handled
Daxium AI is a separate component from Daxium-Air. It has **no direct access** to the data stored in Daxium-Air.
When a user calls an AI feature:
1. Daxium-Air sends to Daxium AI **only the data the feature needs**.
2. Daxium AI prepares the request and sends it to the AI provider, then returns the answer to Daxium-Air.
For example, with the [text rewriting](/user-documentation/daxium-ai/text-rewriting.md) feature, only the text to rewrite and the language of the user are sent.
Requests and answers always go through the Daxium servers: neither the web browser nor the mobile app communicates directly with the AI provider.
---
# 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://www.center.daxium-air.com/user-documentation/daxium-ai/getting-started.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.
