> ## Documentation Index
> Fetch the complete documentation index at: https://docs.flowx.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Chat interface

> Add conversational AI to your applications with the FlowX.AI Chat component.

The Chat component provides a conversational interface for users to interact with AI agents. It supports real-time messaging, context-aware responses, and direct integration with your business processes.

## Overview

> [card] Real-time messaging
>
> Instant responses with streaming support

> [card] AI agent integration
>
> Connect to custom agents or FlowX accelerators

> [card] Session management
>
> Persistent conversations across sessions

> [card] Knowledge base access
>
> Context-aware responses from your data

## How it works

The Chat component follows a simple flow:

**1. User initiates chat**

User opens your application and the Chat component loads with a welcome message.

**2. Message exchange**

User sends a message. The component sends it to the configured AI agent workflow.

**3. Agent processing**

The agent processes the message, optionally querying knowledge bases or external systems.

**4. Response delivery**

The agent's response streams back to the user in real-time.

## Key concepts

### Agent workflows

The Chat component connects to an **agent workflow** that defines how messages are processed:

* **Input handling** - How user messages are received
* **AI processing** - Which models and prompts are used
* **Knowledge access** - What data sources the agent can query
* **Response generation** - How responses are formatted

### Session persistence

Conversations can be persisted to maintain context:

| Mode | Description | Use case |
| - | - | - |
| **Session-based** | Conversation lasts for browser session | Quick queries, support |
| **Persistent** | Conversation saved to database | Ongoing cases, history |

### Knowledge base integration

Agents can access knowledge bases for informed responses:

* **RAG (Retrieval-Augmented Generation)** - Agent can search relevant documents while it answers
* **Semantic matching** - Finds conceptually similar content, not just keyword matches
* **Source attribution** - Responses can cite their sources

> [!NOTE]
>
> Knowledge base integration requires configuration in the agent workflow. See [Knowledge Base Overview](https://docs.flowx.ai/6.x/docs/platform-deep-dive/integrations/knowledge-base-integration/knowledge-base-overview.md) for setup details.

## Display modes

The Chat component supports different display modes:

| Mode | Description |
| - | - |
| **Standalone** | Full-page chat experience |
| **Embedded** | Chat panel within a larger UI |
| **Floating** | Expandable chat button overlay |

## Best practices

> [accordion] Set clear expectations
>
> Use the welcome message to explain what the agent can help with. This reduces user frustration from mismatched expectations.

> [accordion] Provide context
>
> Pass relevant process data to the agent (user info, current step, etc.) so responses are contextually appropriate.

> [accordion] Handle limitations gracefully
>
> Configure fallback responses for when the agent can't help. Offer escalation to human support when needed.

> [accordion] Design for mobile
>
> Test the chat experience on mobile devices. Ensure the interface works well with on-screen keyboards.

## Implementation

For detailed configuration and styling options, see the UI Designer documentation:

> [card] [Chat component configuration](https://docs.flowx.ai/6.x/docs/building-blocks/ui-designer/ui-component-types/chat.md)
>
> Complete configuration reference for the Chat UI component

## Related resources

> [card] [BPMN integration](https://docs.flowx.ai/6.x/ai-platform/using-agents/bpmn-integration.md)
>
> Trigger agents from workflows

> [card] [Agent Builder](https://docs.flowx.ai/6.x/ai-platform/agent-builder/overview.md)
>
> Create custom agents

> [card] [Chat intents](https://docs.flowx.ai/6.x/ai-platform/patterns/intent-classification-routing.md)
>
> Configure intent-based routing

> [card] [Knowledge bases](https://docs.flowx.ai/6.x/docs/platform-deep-dive/integrations/knowledge-base-integration/knowledge-base-overview.md)
>
> Connect your data sources

> [card] [Chat-driven workflows](https://docs.flowx.ai/6.x/ai-platform/chat-driven-workflows.md)
>
> Build multi-turn chat experiences with session memory


## Related topics

- [Chat](https://docs.flowx.ai/6.x/docs/building-blocks/ui-designer/ui-component-types/chat.md)
- [Chat component](https://docs.flowx.ai/6.x/ai-platform/chat-component.md)
- [Chat-driven workflows](https://docs.flowx.ai/6.x/ai-platform/chat-driven-workflows.md)
- [FlowX.AI 5.4.0 Release Notes](https://docs.flowx.ai/release-notes/v5.x/v5.4.0-january-2026/v5.4.0-january-2026.md)
- [FlowX.AI 5.6.0 Release Notes](https://docs.flowx.ai/release-notes/v5.x/v5.6.0-march-2026/v5.6.0-march-2026.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.