> For the complete documentation index, see [llms.txt](https://docs.infotopics.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.infotopics.com/features/management-console/new-ai-platform.md).

# Data & AI Services

**Data & AI Services** is where you set up the two foundations that power AI features and data fetching across the extensions: the AI providers WriteBackExtreme talks to, and the semantic models it serves data from. You will find it in the management console sidebar.

The page has a card for each:

* **AI configuration** — connect to your AI provider and manage the agents that use it. Click **Manage AI configuration**.
* **Semantic models** — let WriteBackExtreme act as a data source for Supertables. Click **Explore semantic models**.

<figure><img src="https://3247237607-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F0gkOLIfzuEyMP2kvoT9o%2Fuploads%2Fgit-blob-a94ff4a088e3ac6c0a9fd2745a991b0a950837c0%2FConsole_AI_Overview.png?alt=media" alt=""><figcaption><p>Data &#x26; AI Services</p></figcaption></figure>

{% embed url="<https://www.youtube.com/watch?v=hoMMzPFaKDA>" %}

The two cards need different roles. Managing AI configurations and agents needs the **connection manager** role; semantic models need the **schema manager** role. An administrator reaches both.

## Getting AI working

To use the AI features in an extension, you need an AI configuration — the connection to your provider, with its credentials, model and parameters — and an agent linked to it.

{% content-ref url="/pages/iL0voP3IhxdJx8nF0BjM" %}
[Create an AI configuration](https://docs.infotopics.com/features/management-console/new-ai-platform/model-configuration.md)
{% endcontent-ref %}

WriteBackExtreme seeds five system agents, so for the built-in features you only have to point an existing agent at your configuration rather than build one.

{% content-ref url="/pages/G8LcX7b0WqQXawgGOm53" %}
[Configure AI agents](https://docs.infotopics.com/features/management-console/new-ai-platform/agent-configuration.md)
{% endcontent-ref %}

## Semantic models

A semantic model lets Supertables query data through the WriteBackExtreme data engine instead of its own, which pays off on large datasets.

{% content-ref url="/pages/2gnaBENVOBLEk1SCT3n5" %}
[Semantic modeling](https://docs.infotopics.com/features/management-console/semantic-modeling.md)
{% endcontent-ref %}

## Using AI in extensions

Once a configuration is in place and your agents point at it, the AI features can be switched on in the extensions that support them:

* [SuperTables](https://docs.infotopics.com/supertables)
* [InputTables](https://docs.infotopics.com/inputtables)


---

# 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://docs.infotopics.com/features/management-console/new-ai-platform.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.
