# AI Agent Call

### Definition

The "**AI Agent Call**" module allows you to integrate the intelligence of an AI Agent directly into your integration flow. With it, you can process data, make logical decisions, or generate content automatically between the stages of your integration.

{% hint style="info" %}
Before configuring this module, you must have an [AI Agent](/english/skyone-studio/artificial-intelligence/agents.md) already created and configured on the platform.
{% endhint %}

### Add "AI Agent Call" Module

The "**AI Agent Call**" module appears under the Tools option in the flow editor. After clicking to add it, the initial configuration modal will be displayed.

<figure><img src="/files/07tw7HW0Yrt362sMdmwT" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
[Learn more about the Module Header.](/english/skyone-studio/integrations/flows/module-header.md)
{% endhint %}

1. Fill in or choose the following items to use the module:

   * **Agent ID:** Select from the list the AI Agent you wish to use for this specific task.
   * **Context key (optional):** Define a context variable or SMOP.
   * **Prompt:** Describe in detail what the Agent should do with the data received at this stage.
   * A**ttachments (optional):** Insert the file content (PDF or image) encoded in Base64 format, previously registered as a variable. Read also: [Variables](/english/skyone-studio/integrations/flows/flow-management/flow-canva-configuring-and-editing-the-flow/flow-settings.md#variables).

2. Click "**Next**". You will be redirected to the test screen.

3. Click "**Test**" to verify the module.

4. To finish, simply click "**Save**".


---

# 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.skyone.cloud/english/skyone-studio/integrations/flows/tool-modules/ai-agent-call.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.