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

# Web UI Guide

> Complete guide to using the Scale Gymnasium Web interface

The Scale Gymnasium Web UI at [gym.scale.com](https://gym.scale.com) provides a visual interface for exploring environments, running agent loops, and verifying task completion.

<Info>
  **Prerequisites:** Access to the Scale Gymnasium Web UI at [gym.scale.com](https://gym.scale.com). Contact Scale if you don't have access.
</Info>

<Tabs>
  <Tab title="MCP Environment">
    ## MCP Environment

    The MCP environment provides access to 45+ MCP servers and 300+ tools for tool-based agent interactions.

    ### Navigation

    Select an MCP server from the left sidebar under **TOOL USE** (e.g., Quickbooks, Hubspot CRM, Calendar, Email, Slack).

    ### Tools Panel

    The **Tools for \[Server]** panel on the left shows:

    * **Search tools**: Filter tools by name
    * **Refresh**: Reload the tool list
    * List of available tools with descriptions (e.g., `quickbooks_create_customer`, `calendar_get_events`)

    Click a tool to view its parameters and execute it.

    ### Server Data Panel

    The **Server Data** panel on the right shows the database state:

    * **Tabs**: Switch between data tables (e.g., customers, invoices, bills, items, vendors)
    * **Refresh**: Reload the data
    * **Hide**: Collapse the panel
    * **Pagination**: Navigate through records with Previous/Next

    Use this to inspect the current state and verify changes after tool calls.

    ### Tips

    <Accordion title="Efficient Tool Discovery">
      Find tools quickly in the MCP interface:

      * Use the search box to filter by tool name
      * Select different servers from the sidebar to see their tools
      * Read tool descriptions for parameter guidance
    </Accordion>
  </Tab>

  <Tab title="Website Environments">
    ## Website Environments

    Website environments include Calendar, Cloudfile, Shopora, and Pandora's Inbox.

    ### Interface Views

    Each website environment has two tabs:

    | View               | Purpose                                    |
    | ------------------ | ------------------------------------------ |
    | **GUI View**       | The live, interactive website              |
    | **Sample RL Data** | Pre-built tasks with prompts and verifiers |

    You can also view the **Application State** to see real-time database changes.

    ### GUI View

    The live, interactive web application:

    * Interact with the website as a user would
    * All interactions are logged automatically
    * Session-scoped isolation prevents cross-contamination

    ### Application State

    Real-time database view:

    * See all tables (events, users, files, etc.)
    * Watch state update as you interact
    * Copy data for verification design

    ### Sample RL Data

    Pre-built tasks for testing:

    * **Browse tasks**: See available prompts
    * **Open in Agent Executor**: Load the task into the agent executor

    ### Running Agent Loops

    1. Select a task from **Sample RL Data**
    2. Click **Open in Agent Executor**
    3. Watch the trajectory unfold

    **Output includes:**

    * Step-by-step trajectory
    * Screenshots at each action
    * Model chain of thought
    * Next goal predictions

    <Note>
      After the agent loop completes, click the **Execute** button next to the verifier to run verification.
    </Note>

    ### Tips

    <Accordion title="Debugging with Application State">
      Use the Application State view to understand exactly what changed:

      1. Note the state before your action
      2. Perform the action
      3. Compare the new state
      4. Use this to design accurate verifiers
    </Accordion>

    <Accordion title="Using Sample RL Data as Templates">
      Sample tasks demonstrate proper task structure:

      * Study the prompt format
      * Examine verifier check configuration
      * Use as templates for custom tasks
    </Accordion>
  </Tab>

  <Tab title="Desktop Environments">
    ## Desktop Environments

    Desktop environments provide access to Ubuntu, Windows, and Mac virtual machines.

    ### Interface Tabs

    | Tab                     | Purpose                                    |
    | ----------------------- | ------------------------------------------ |
    | **Environment & Tools** | Live VM sandbox view with controls         |
    | **Sample RL Data**      | Pre-built tasks with prompts and verifiers |

    ### Environment & Tools

    The sandbox view shows the live VM:

    * **Reset**: Reset the VM to initial state
    * **Fullscreen**: Expand the VM view

    Below the sandbox, the **Task Configuration** section allows you to:

    * Select a preset task from the dropdown
    * View the task prompt

    ### Sample RL Data

    Browse pre-built tasks:

    * Each task shows the prompt, task initializer config, and verifier
    * Click **Load Task** to load it into the environment

    ### Running a Task

    1. Select an OS from the left sidebar (Ubuntu, Windows, or Mac)
    2. Go to **Sample RL Data** and click **Load Task** on a task
    3. The task configuration loads with:
       * **Task Prompt**: The instruction for the agent
       * **Task Initializer**: Setup config (click **Execute Initializer** to run)
       * **Verifier**: Evaluation config (click **Execute Verifier** after completion)

    ### Workflow

    1. Click **Execute Initializer** to set up the VM with required files and applications
    2. Complete the task manually in the VM, or use the Agent Executor
    3. Click **Execute Verifier** to check if the task was completed successfully
  </Tab>
</Tabs>

## Working with Verifiers

The Web UI provides integrated verification for Website and Desktop environments.

<Note>
  MCP environments do not have verifier support in the Gymnasium UI.
</Note>

### Running Verification

1. Complete a task (manually or via agent)
2. Click **Execute** next to the verifier
3. View check results

### Check Types

| Type             | Description               | Result            |
| ---------------- | ------------------------- | ----------------- |
| **State Check**  | Verifies database changes | Pass/Fail         |
| **Log Check**    | Verifies interaction logs | Pass/Fail         |
| **Rubric Check** | LLM-evaluated criteria    | Pass/Fail/Pending |

### Interpreting Results

* **✅ Passed**: All checks succeeded
* **❌ Failed**: One or more checks failed (see details)
* **⏳ Pending**: Rubric checks awaiting LLM evaluation

## Next Steps

<CardGroup cols={2}>
  <Card title="Key Concepts" icon="book" href="/getting-started/key-concepts">
    Understand the core terminology
  </Card>

  <Card title="Docker Deployment" icon="docker" href="/getting-started/quickstart-docker">
    Run environments on your own infrastructure
  </Card>
</CardGroup>