> For the complete documentation index, see [llms.txt](https://docs.sprinthub.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.sprinthub.com/en/topics/convert/chatbot/chatbot-common-questions/chatbot-using-ai-agents.md).

# Chatbot - Using AI Agents

The **AI Agent** allows the chatbot to automatically respond to users using artificial intelligence, interpreting questions and generating responses based on a configured context. This makes support more natural, flexible, and capable of handling open-ended questions.

Unlike rigid flows with buttons or fixed paths, the AI Agent understands the intent of the user's message and responds dynamically.

{% embed url="<https://youtu.be/8r8Iwjmkav8>" %}

***

### How the AI Agent works

When the **AI Agent** is active in the chatbot:

1. The user sends a message.
2. The AI analyzes the content of the question.
3. The system consults the **configured context** (information, rules, or knowledge base).
4. The AI generates an appropriate response and sends it to the user.

This makes it possible to answer questions such as:

* Service hours
* Information about products or services
* Frequently asked questions
* General guidance

All without the need to create a specific flow for each question.

To create your AI Agent, see the article below:

{% content-ref url="/pages/861bb44c720660c049e303ea9addac19dfc003cc" %}
[AI Agents - Initial Settings](/en/topics/artificial-intelligence/ai-agents/ai-agents-initial-settings.md)
{% endcontent-ref %}

{% content-ref url="/pages/51adcffad614e83955c54e913438e004abf88441" %}
[Configuring the MCP AI Agent - Creating an Agent to Rewarm Leads](/en/topics/artificial-intelligence/ai-agents-mcp/configuring-the-mcp-ai-agent-creating-an-agent-to-rewarm-leads.md)
{% endcontent-ref %}

***

### Where the AI Agent can be used

The AI Agent can be used at different points in the chatbot, for example:

* **Initial support** to answer general questions
* **Automatic support** before routing to an attendant
* **Flow supplement**, when the user asks questions outside the bot's script
* **Knowledge base**, answering questions about products, services, or processes

***

### Best practices when using AI in the chatbot

To get better responses, it's important to configure the AI context well.

It is recommended to:

* Insert **clear company information**
* Define **service rules**
* Include **frequently asked questions and answers**
* Inform **products, services, and hours**

The more complete the context is, the more accurate the AI's responses will be.

***

### Integration with human support

Even while using AI, the chatbot can route the user to an attendant when necessary.

Some examples:

* When the AI doesn't know how to answer
* When the user requests to speak with an attendant
* When human support is needed

Thus, the AI Agent helps to **automate a large part of conversations**, while still keeping the possibility of human support when needed.

***

✅ **Tip:** The AI Agent can be combined with traditional chatbot flows, using menus, buttons, and automations to create a more complete support experience.

***


---

# 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 dynamically by asking a question.

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

```
GET https://docs.sprinthub.com/en/topics/convert/chatbot/chatbot-common-questions/chatbot-using-ai-agents.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.