> For the complete documentation index, see [llms.txt](https://docs.mydbsync.com/cloud-workflow/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mydbsync.com/cloud-workflow/ai/chat-agents.md).

# Chat Agents

The Chatbot widget is a conversational AI interface and processing engine that interacts with your users. To process and generate text, the widget integrates with a configurable large language model (LLM) provider of your choice. It formulates intelligent answers by drawing context from multiple configurable sources, including selected knowledge bases, web searches, MCP servers, and attachments that users upload during the chat. The Chatbot widget powers AI-driven knowledge assistants tailored for customer support, documentation navigation, and internal operations.

### Prerequisite 

Configure the Knowledge base as described [here](/cloud-workflow/ai/knowledge-base.md). 

### Procedure

To configure the chat agent, follow these steps:

{% stepper %}
{% step %}
Log in to DBSync with your credentials.
{% endstep %}

{% step %}
In the navigation pane, click <img src="/files/gkfB0UV6UUbxJMPmKlNl" alt="" data-size="line"> (Chat Agents).
{% endstep %}

{% step %}
Click **Create your first Chatbot**.

<div data-with-frame="true"><figure><img src="/files/rlxZh1EOsRj0PHeHcBSs" alt=""><figcaption></figcaption></figure></div>
{% endstep %}

{% step %}
In the **LLM Provider** list, select the provider for your large language model. The default provider is OpenAI.
{% endstep %}

{% step %}
In the **Model** list, select the specific model that you want the chatbot to use. \
The default model is GPT-5.5.
{% endstep %}

{% step %}
Optional: In the **Initial prompt** field, enter the first assistant message to display when the chat window opens, or leave the field empty to skip the greeting.<br>

<div align="left" data-with-frame="true"><figure><img src="/files/Azv5FHwhf6Q59sWZBQve" alt=""><figcaption></figcaption></figure></div>
{% endstep %}

{% step %}
In the **System Prompt** field, enter the instructions or persona details that guide the chatbot's behavior.

<div align="left" data-with-frame="true"><figure><img src="/files/bvKD8gEEroQpQk5DbEye" alt=""><figcaption></figcaption></figure></div>
{% endstep %}

{% step %}
To provide context, select one or more knowledge bases in the **Knowledge Base** list. To select multiple knowledge bases, press Control (or Command on macOS), and then click the items.
{% endstep %}

{% step %}
Optional: To add a new server configuration, click **Add MCP Server**.
{% endstep %}

{% step %}
Optional: To allow the chatbot to retrieve information from the internet, turn on the **Enable web search** toggle.

<div align="left" data-with-frame="true"><figure><img src="/files/QNbT9ddyU6yxPYdoBkfV" alt=""><figcaption></figcaption></figure></div>
{% endstep %}

{% step %}
Click **Save Config**.
{% endstep %}

{% step %}
In the **Type a message...** field, enter your question or prompt.
{% endstep %}

{% step %}
Optional: To add a file to your message, click <img src="/files/hteqSpCrb1skJ41UfK36" alt="" data-size="line">.
{% endstep %}

{% step %}
Click <img src="/files/yIeS95PNPfigx8Uvmzww" alt="" data-size="line"> or press enter to submit.

<div data-with-frame="true"><figure><img src="/files/UaLgzfeG45q17N5QglBV" alt=""><figcaption></figcaption></figure></div>
{% endstep %}

{% step %}
Optional: To start a new conversation, click **New Chat**.
{% endstep %}

{% step %}
Optional: To view your previous conversations, click **History**.\
![](/files/hRZ0aiCjyVcFZ8EOW8sW)
{% endstep %}

{% step %}
Optional: To categorize the conversation, click **Tags**.

* In the **Edit Tags** dialog, enter a tag name in the **Tags** field.
* Click **Add tag**.

<div align="left" data-with-frame="true"><figure><img src="/files/RNlui6diVZpDhFBlmW07" alt="" width="279"><figcaption></figcaption></figure></div>

* Enter the required **Customer**, **Project** and **Ticket**.&#x20;
* Click **Save Tags.**
* Go to **History** to view tags.

<div align="left" data-with-frame="true"><figure><img src="/files/zRZU5dhaYxUBxUVcoXY8" alt=""><figcaption></figcaption></figure></div>
{% endstep %}
{% endstepper %}


---

# 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:

```
GET https://docs.mydbsync.com/cloud-workflow/ai/chat-agents.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.