# AI Agent Node

The **AI Agent Node** allows you to incorporate intelligent, LLM-powered automation within your workflow. It enables your workflow to interact with AI models for tasks like generating text, analyzing inputs, or classifying documents—all directly inside Nected without external scripting or APIs.

With this node, you can:

* Generate AI responses dynamically
* Analyze text data
* Classify and extract document information automatically

Before using the AI Agent node, **you must connect Nected to an AI Provider** such as OpenAI, GoogleAI, Anthropic, or Vertex AI.

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-cover data-type="image">Cover image</th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Connect with AI Provider</strong></td><td>Before using the AI Agent node, connect Nected with an AI Provider such as OpenAI, GoogleAI, Anthropic, or Vertex AI.</td><td><a href="/files/uUr30qI2TBNmORsB2EwQ">/files/uUr30qI2TBNmORsB2EwQ</a></td><td><a href="/pages/Tep54cprXE2kr8T7pxri">/pages/Tep54cprXE2kr8T7pxri</a></td></tr></tbody></table>

### **How to Open the AI Agent Node?**

1. Navigate to the **Workflow Editor** in your Nected workspace.
2. Click on the **“+” (Add Node)** button to insert a new node.<br>

   <figure><img src="/files/viiaIBtw46IxnjDrid8I" alt=""><figcaption></figcaption></figure>
3. From the available node types, select **AI Agents**.
4. You’ll see three types of AI Agent nodes to choose from.

<figure><img src="/files/VkE8pVESqBP5uGNGZRsO" alt=""><figcaption></figcaption></figure>

### **Types of AI Agent Nodes**

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-cover data-type="image">Cover image</th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>AI Response</strong></td><td>Generate dynamic, text-based outputs from AI models using custom prompts or workflow data. Ideal for tasks like answering queries, drafting messages, or producing context-aware content.</td><td><a href="/files/uUr30qI2TBNmORsB2EwQ">/files/uUr30qI2TBNmORsB2EwQ</a></td><td><a href="/pages/bE8uVGVscgQxiIq8ZCiQ">/pages/bE8uVGVscgQxiIq8ZCiQ</a></td></tr><tr><td><strong>Text Analysis</strong></td><td>Analyze and interpret text automatically using AI. Perform sentiment detection, summarization, keyword extraction, and other NLP-driven insights directly within your workflow.</td><td><a href="/files/uUr30qI2TBNmORsB2EwQ">/files/uUr30qI2TBNmORsB2EwQ</a></td><td></td></tr><tr><td><strong>Document Classifier</strong></td><td>Automatically categorize and extract structured information from documents such as PDFs, DOCX, or TXT files. Perfect for parsing, tagging, and routing document data through your workflows.</td><td><a href="/files/uUr30qI2TBNmORsB2EwQ">/files/uUr30qI2TBNmORsB2EwQ</a></td><td></td></tr></tbody></table>


---

# 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.nected.ai/nected-docs/workflow/add-node/action-nodes/ai-agent-node.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.