> 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.md).

# AI

DBSync Cloud Workflow includes AI features for workflow automation and conversational experiences. You can connect supported LLM providers, ground responses with your content, and configure agents for specific use cases.

### What this section covers

This section helps you:

* Connect supported LLM providers with API keys.
* Configure AI Agent actions inside workflows.
* Create knowledge bases from files and web pages.
* Build chat agents that answer with business context.

### Core AI components

#### API key guides

Before you use any AI feature, connect a supported model provider. Provider setup varies by console, billing model, and credential format.

Use these guides to generate and manage keys for:

* OpenAI ChatGPT
* Anthropic Claude
* Google Gemini
* Amazon Bedrock
* Azure OpenAI

Start here: [AI Agent: API Key Guides](/cloud-workflow/ai/ai-agent-api-key-guides.md)

#### AI Agent

Use **AI Agent** inside a workflow when you want an LLM to process incoming data. You can define prompts, insert workflow variables, preview results, and refine the output before runtime.

AI Agent also supports options such as:

* Model selection
* MCP server connections
* Vector database context
* Optional web search

Learn more: [AI Agent](/cloud-workflow/ai/ai-agent.md)

#### Knowledge Base

The **Knowledge Base** stores the content that powers grounded AI responses. You can upload files or scan web pages, then manage document status, metadata, and processed chunks from one place.

This is the foundation for accurate, context-aware answers in chat experiences.

Learn more: [Knowledge Base](/cloud-workflow/ai/knowledge-base.md)

#### Chat Agents

Use **Chat Agents** to create a conversational assistant for users, teams, or customers. A chat agent combines an LLM provider with system instructions and one or more knowledge bases.

You can also extend responses with:

* MCP servers
* Optional web search
* User file attachments
* Conversation history and tags

Learn more: [Chat Agent](/cloud-workflow/ai/chat-agents.md)

### Recommended setup flow

Follow this order for the fastest setup:

{% stepper %}
{% step %}
Create an API key for your LLM provider.
{% endstep %}

{% step %}
Create a knowledge base with your source content.
{% endstep %}

{% step %}
Configure an AI Agent for workflow tasks, or a Chat Agent for conversations.
{% endstep %}
{% endstepper %}

### Choose the right feature

Use **AI Agent** when you need AI inside a workflow step.

Use **Chat Agent** when you need an interactive assistant that answers questions in real time.

Use **Knowledge Base** when you want both features to respond with your business content instead of generic model output.


---

# 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.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.