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

# Chat Overview

> Complete guide to Cloosphere Chat — conversations, file analysis, code execution, and web search

Cloosphere Chat goes beyond simple conversation: it's a **comprehensive AI workspace** supporting file analysis, code execution, web search, and voice conversations.

<Frame caption="Full chat interface">
  <img src="https://mintcdn.com/cloocus/jo_Hh1nBizxj0BOc/images/en/chat/overview-full.png?fit=max&auto=format&n=jo_Hh1nBizxj0BOc&q=85&s=07aa34897fc8a975323eb04ede7a0ffc" alt="Full chat interface" width="1911" height="905" data-path="images/en/chat/overview-full.png" />
</Frame>

## Chat Flow

When you send a message, it's processed through this flow.

```mermaid theme={null}
flowchart LR
    subgraph Input
        A[Text / File / Voice] --> B[Send message]
    end

    subgraph "AI Processing"
        B --> C{Web search?}
        C -->|Yes| D[Run web search]
        C -->|No| E{Knowledge base?}
        D --> E
        E -->|Yes| F[Document RAG retrieval]
        E -->|No| G[LLM response generation]
        F --> G
    end

    subgraph Output
        G --> H[Display response]
        H --> I[Citations]
        H --> J[Code execution]
        H --> K[TTS playback]
    end
```

## Chat Screen Layout

| Area              | Description                                                                         |
| ----------------- | ----------------------------------------------------------------------------------- |
| **Sidebar**       | Chat list, search, tag filter, folders, projects, Workspace access                  |
| **Chat Header**   | Model selection, multi-model add, chat menu (Share, Overview, Download, Copy, Tags) |
| **Message Area**  | Conversation display, response branch navigation, response toolbar                  |
| **Input Area**    | Text input, file attachment, voice input, extended features                         |
| **Chat Controls** | System prompt, model parameters, conversation flow visualization                    |

<Note>
  The chat header appears in the top-right corner after you send your first message. It stays hidden until you enter a message in a new chat.
</Note>

## Key Features

<Columns cols={2}>
  <Card title="Conversations" icon="messages" href="/en/chat/conversations">
    Manage chat history — create, search, organize into folders, archive, export
  </Card>

  <Card title="Model Selection" icon="robot" href="/en/chat/models">
    Choose models, compare multiple models, adjust parameters like Temperature
  </Card>

  <Card title="Advanced Features" icon="wand-magic-sparkles" href="/en/chat/capabilities">
    Enable and use web search, image generation, code execution
  </Card>

  <Card title="Files & RAG" icon="file-lines" href="/en/chat/files-and-rag">
    File attachment, knowledge base integration, citation review
  </Card>

  <Card title="Sharing & Organization" icon="share-nodes" href="/en/chat/sharing">
    Share links, tags, archives, folder management
  </Card>
</Columns>

## Command System

Use special-prefix commands in the input box to invoke features quickly.

| Command       | Function                            | Example                                            |
| ------------- | ----------------------------------- | -------------------------------------------------- |
| `@modelname`  | Ask a specific model directly       | `@gpt-4o review this code`                         |
| `/promptname` | Invoke a saved prompt template      | `/email-draft project delay notice`                |
| `#kbname`     | Reference a specific Knowledge Base | `#hr-policy What's the leave application process?` |

<Tip>
  Typing `@`, `/`, or `#` opens an autocomplete dropdown for selection.
</Tip>

## Keyboard Shortcuts

| Shortcut                | Action               |
| ----------------------- | -------------------- |
| `Enter`                 | Send message         |
| `Shift + Enter`         | Line break           |
| `Shift + Esc`           | Focus chat input     |
| `Ctrl + Shift + O`      | Open new chat        |
| `Ctrl + Shift + S`      | Toggle sidebar       |
| `Ctrl + Shift + C`      | Copy last response   |
| `Ctrl + Shift + ;`      | Copy last code block |
| `Ctrl + Shift + Enter`  | Generate prompt pair |
| `Ctrl + Shift + Delete` | Delete chat          |
| `Ctrl + .`              | Toggle settings      |
| `Ctrl + /`              | Show shortcuts       |

## AI Response Toolbar

A set of action buttons sits below each AI response.

<Frame caption="AI response toolbar">
  <img src="https://mintcdn.com/cloocus/jo_Hh1nBizxj0BOc/images/en/chat/overview-response-toolbar.png?fit=max&auto=format&n=jo_Hh1nBizxj0BOc&q=85&s=538f1ce3535b338b9bc35fc01de925a7" alt="AI response toolbar" width="2000" height="947" data-path="images/en/chat/overview-response-toolbar.png" />
</Frame>

| Button                | Action                                                     |
| --------------------- | ---------------------------------------------------------- |
| **Edit**              | Edit the AI response content directly                      |
| **Copy**              | Copy the full response to the clipboard                    |
| **Read Aloud**        | Read the response aloud with TTS                           |
| **Good Response**     | Response quality feedback — thumbs up                      |
| **Bad Response**      | Response quality feedback — thumbs down (optional comment) |
| **Continue Response** | Continue generating a truncated response                   |
| **Regenerate**        | Request a new response for the same prompt                 |
| **View Trace**        | View tokens used and processing time                       |

<Note>
  Editing a user message preserves the original and creates a new branch.
  Use the left/right arrows to navigate between branches.
</Note>

## Next Steps

* See [Conversations](/en/chat/conversations) for organizing chat history.
* Visit [Model Selection](/en/chat/models) to pick the right model and tune parameters.
* Use [Advanced Features](/en/chat/capabilities) for web search, image generation, and code execution.