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

# Agent Mode

> The agent writes code, generates media, builds websites, and executes multi-step tasks in a private sandbox.

Agent Mode is the default mode in Runable. The agent has a full toolkit: it writes code, runs commands, generates images and videos, builds websites, creates presentations, and handles complex multi-step projects. Everything runs in a private sandbox, isolated from your computer.

## How Agent Mode works

```mermaid actions={false} theme={null}
%%{init: {'theme': 'base', 'themeVariables': { 'primaryColor': '#e6fafb', 'primaryTextColor': '#1a1a2e', 'primaryBorderColor': '#01b7cb', 'lineColor': '#01b7cb', 'fontFamily': 'Inter, sans-serif', 'fontSize': '14px' }}}%%
flowchart LR
    A("You send a message"):::step --> B("Agent plans the approach"):::step --> C("Agent uses tools"):::step --> D("Result streams live"):::step
    classDef step fill:#e6fafb,stroke:#01b7cb,stroke-width:2px,rx:12,ry:12,color:#1a1a2e
```

<Steps>
  <Step title="You describe what you need">
    Type your goal in the input bar. Attach files if you have reference material.
  </Step>

  <Step title="The agent plans its approach">
    The agent reads your message, loads relevant skills, and decides which tools to use. For complex tasks, it writes a plan in a scratchpad before starting.
  </Step>

  <Step title="The agent executes with tools">
    The agent calls tools as needed: writing code, running bash commands, generating images, searching the web, creating files. You see every action in real time.
  </Step>

  <Step title="Results stream to the side panel">
    Generated artifacts (websites, slides, images, videos, documents) appear in the side panel as they are created. You can interact with them immediately.
  </Step>
</Steps>

## Model tiers

In Agent Mode, you select a tier rather than a specific model:

| Tier                                        | Best for                                              | Credit cost |
| ------------------------------------------- | ----------------------------------------------------- | ----------- |
| <Badge color="gray" size="sm">Lite</Badge>  | Quick edits, simple tasks, fast answers               | Lowest      |
| <Badge color="blue" size="sm">Pro</Badge>   | Most tasks, good balance of speed and quality         | Medium      |
| <Badge color="purple" size="sm">Max</Badge> | Complex reasoning, deep analysis, multi-step projects | Highest     |

Select your tier from the model selector in the input bar before sending a message.

## What the agent can do

<Columns>
  <div>
    ### Build

    * Write and execute code (any language)
    * Build and deploy websites
    * Create presentations and reports
    * Generate spreadsheets with formulas
    * Create carousels for social media
  </div>

  <div>
    ### Create media

    * Generate images from text
    * Create and edit videos
    * Produce audio, music, and podcasts
    * Remove and replace backgrounds
    * Upscale images up to 4x
  </div>
</Columns>

The agent also searches the web, reads and writes files, installs packages, and uses any tool in its sandbox environment.

## What you see in Agent Mode

Every tool call is visible in the chat:

| Tool type            | What you see                                |
| -------------------- | ------------------------------------------- |
| **Bash commands**    | Terminal output with the command and result |
| **File writes**      | Confirmation of what was written and where  |
| **File edits**       | A diff showing what changed                 |
| **Image generation** | A thumbnail preview inline in the chat      |
| **Video generation** | A video card with play button               |
| **Web search**       | Search results with sources                 |
| **Website preview**  | A live preview in the side panel            |

## What you cannot do in Agent Mode

* You cannot pick a specific model. You choose a tier (Lite, Pro, Max) and the agent uses the corresponding model.
* You cannot limit which tools the agent uses. It decides which tools are appropriate for the task.
* You cannot run multiple agent tasks simultaneously in the same chat.

## Next steps

<CardGroup cols={2}>
  <Card title="Chat Mode" icon="message" href="/chat-mode">
    Switch to conversation-only mode for research and analysis.
  </Card>

  <Card title="Plan Mode" icon="list-check" href="/plan-mode">
    Make the agent plan before building for complex projects.
  </Card>
</CardGroup>