# Configuring capabilities

Capabilities are optional features that extend your AI Agent's functionality or modify its behavior. Enable only the capabilities your use case requires to maintain optimal performance and security.

<figure><img src="/files/XsIOIoqA0yB0jNrqQUpG" alt=""><figcaption></figcaption></figure>

## Available capabilities

### Query sources for insights

Enables your Agent to generate and execute SQL queries directly against your data connections, providing dynamic analysis beyond pre-configured widgets and layers.

#### What this capability unlocks

This capability grants access to powerful data manipulation tools:

<table><thead><tr><th width="249.82421875">Tool</th><th>Purpose</th></tr></thead><tbody><tr><td><code>execute_query</code></td><td>Run AI-generated SQL queries to analyze data and return insights conversationally.</td></tr><tr><td><code>add_source</code></td><td>Create temporary data sources from SQL queries that can be visualized as map layers.</td></tr><tr><td><code>remove_source</code></td><td>Clean up temporary AI-generated data sources.</td></tr></tbody></table>

{% hint style="warning" %}
**Important limitations for public maps**: Maps containing AI Agents with Query Sources for insights capability cannot be made public. This is a security restriction to prevent unauthorized data access. For public-facing applications:

* Build required logic into Workflows and exposed them as MCP Tools.
* Use pre-configured widgets and layers.
* Consider creating a separate, limited connection for public access.
  {% endhint %}

{% hint style="danger" %}
**Security considerations:** This capability allows direct database access through AI-generated SQL. Enable only when:

* Users are authorized to access the underlying data
* Your connection has appropriate read-only permissions
* You've configured proper data access policies in your organization
  {% endhint %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.carto.com/carto-user-manual/ai-agents/configuring-capabilities.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.