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

# AI

The **AI** section in Settings allows administrators to manage **AI providers**, define **data-sharing policies**, and control how contextual information is shared with AI models during analysis, conversations, and agent executions.

<figure><img src="/files/y7kcNuV0Lb51V015cpIy" alt=""><figcaption></figcaption></figure>

## Data Sharing Permissions

At the top of the page, you can configure **what type of data is allowed to be shared** with AI providers. These settings apply globally and define the privacy and governance boundaries of AI usage inside Gaio DataOS.

#### 1. Metadata

Basic structural information about tables is shared.

**Included**

* Column name
* Column title
* Data type

**Excluded**

* Sensitive data values

**Purpose**\
Helps the AI understand schema structure without accessing actual data.

#### 2. Table Sample Data

A limited subset of table data is shared.

**Included**

* First 10 rows
* Sensitive data (if enabled)

**Purpose**\
Improves contextual understanding for more accurate responses in conversations involving data interpretation.

#### 3. Analytics

Derived analytical information from tables.

**Included**

* Frequency distributions
* Metrics
* Analytical summaries
* Sensitive data (if enabled)

**Purpose**\
Allows the AI to reason over patterns, trends, and aggregates rather than raw data only.

#### 4. Results Sample

A subset of query execution results is shared.

**Included**

* First 10 query results
* Sensitive data (if enabled)

**Purpose**\
Provides execution context for follow-up questions and complex analytical reasoning.

***

## Creating or Editing an AI Configuration

1. Navigate to **Settings → AI**
2. Click **New** or **Edit** on an existing configuration
3. Fill in the following fields:

#### Fields Description

* **Name**\
  Internal identifier for the AI configuration.
* **Supplier**\
  Select the AI provider (e.g., OpenAI, Anthropic, DeepSeek).
* **Model**\
  Choose the specific model available for the selected supplier (e.g., GPT-4, Claude Opus, DeepSeek Chat).
* **API Key**\
  Paste the provider-issued API key. This key is stored securely and used at runtime.

4. Click **Save**

***

### Preferential Model

You can mark one AI configuration as **Preferential**.

* The preferential model is used by default across:
  * Dashboards
  * Agents
  * AI-powered features
* Other models remain available for manual selection or advanced use cases.

### Governance and Security Notes

* Sensitive data sharing is **explicitly controlled** per data scope.
* API keys are never exposed to end users.
* AI suppliers only receive the data scopes you explicitly enable.
* You can mix providers (e.g., OpenAI + Anthropic) in the same environment.

### Best Practices

* Start with **Metadata only**, then progressively enable sample data if needed.
* Use **Table Sample Data** for exploratory analysis and schema discovery.
* Enable **Analytics** only when deeper statistical reasoning is required.
* Define one **Preferential model** to keep behavior consistent.
* Use different providers to compare quality, cost, and performance.

{% hint style="info" %}
This configuration layer ensures Gaio’s AI capabilities remain **powerful, transparent, and compliant**, while giving teams full control over how intelligence is applied to their data.
{% endhint %}