> For the complete documentation index, see [llms.txt](https://help.pickyassist.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.pickyassist.com/setting-up-guide/ai-agent/introduction.md).

# Introduction

AI Agent is an AI-powered conversational block in Picky Assist. It automates customer interactions using natural language.

An AI Agent can:

* Answer customer questions from your Knowledge Base.
* Collect and extract information from documents and images.
* Recommend products or services.
* Follow up with inactive customers.
* Transfer conversations to human agents or another AI Agent.<br>

### Where AI Agent fits in a flow

AI Agent is a block within [**Flow Builder**](/setting-up-guide/setting-up-flow-builder.md). Open or create a chatbot flow, add an AI Agent block, and connect it to the required steps.

Flow Builder → Open or create a chatbot flow → Add AI Agent → Connect it to the required flow steps

Use collected or extracted data in later steps with attribute tokens.

{% hint style="info" %}
AI Agent is a flow block, not a standalone chatbot. It can replace several question-and-condition steps with a natural conversation.
{% endhint %}


---

# 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://help.pickyassist.com/setting-up-guide/ai-agent/introduction.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.