> ## 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.

# Verifier Overview

> How verification works across Scale Gymnasium environments

Verifiers validate whether an agent successfully completed a task. Each environment type uses a different verification approach.

<Info>
  Explore live verifier examples at [gym.scale.com](https://gym.scale.com).
</Info>

## Comparison

| Environment | Verifier Access                   | Check Types                  |
| ----------- | --------------------------------- | ---------------------------- |
| **Website** | `/api/verifier` endpoint (Docker) | State, Log, Rubric           |
| **Desktop** | `/run_evaluator` endpoint         | File comparison, Rules-based |
| **MCP**     | Scale Gymnasium Web UI only       | LLM Judge, Rubric            |

## Choose Your Environment

<CardGroup cols={3}>
  <Card title="Website Verifiers" icon="globe" href="/deep-dives/verifiers/website">
    State checks, log checks, and rubric evaluation for web apps
  </Card>

  <Card title="Desktop Verifiers" icon="desktop" href="/deep-dives/verifiers/desktop">
    File comparison and rules-based evaluation for VMs
  </Card>

  <Card title="MCP Verifiers" icon="wrench" href="/deep-dives/verifiers/mcp">
    LLM Judge and rubric claims for tool-use tasks
  </Card>
</CardGroup>

## Common Concepts

### Score Interpretation

| Score       | Meaning                               |
| ----------- | ------------------------------------- |
| `1.0`       | Task completed successfully           |
| `0.0`       | Task not completed                    |
| `0.0 - 1.0` | Partial completion (where applicable) |

### Result Statuses

| Status        | Meaning                               |
| ------------- | ------------------------------------- |
| ✅ **Passed**  | All checks succeeded                  |
| ❌ **Failed**  | One or more checks failed             |
| ⏳ **Pending** | Rubric checks awaiting LLM evaluation |

## Next Steps

<CardGroup cols={2}>
  <Card title="Task Design" icon="clipboard" href="/deep-dives/task-design/overview">
    Create tasks with verifiers
  </Card>

  <Card title="Data Packs" icon="database" href="/deep-dives/data-packs">
    Configure initial environment state
  </Card>
</CardGroup>