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

# Quickstart

> From install to your first scored mission in five minutes.

This walks you from a fresh install to a fully run, scored mission with
fine-tuning data on disk. It assumes you've [installed](/cli-setup/installation)
`cadenza` and have the `gym` extra (or are happy to stop before `env run`).

<Steps>
  <Step title="Sign in">
    Your administrator issues you a token <Tooltip tip="Don't have a token? Reach out to acparekh@stanford.edu to request one and unlock this feature."><Icon icon="circle-question" iconType="regular" /></Tooltip>. Sign in once:

    ```bash theme={null}
    cadenza login <your-name> <your-token>
    ```

    Verify:

    ```bash theme={null}
    cadenza whoami
    # signed in as <your-name> (<account-id>)
    ```

    See [Authentication](/cli-setup/authentication) for details. Sign-in is
    required for `env action` commands and for any **governed** command that
    returns a verdict (`env lora eval`, `env residual train/eval/bench`,
    `env distill eval`, `env vla grd/eval`). Scaffolding, running, stats, and
    data export all work signed-out.
  </Step>

  <Step title="Scaffold a project">
    ```bash theme={null}
    cadenza mkdir rescue-dog
    ```

    Creates `./rescue-dog/` with an `env.json` mission spec, a `main.py` driver,
    `requirements.txt`, and a `README`. Inspect the mission:

    ```bash theme={null}
    cadenza env show rescue-dog
    ```

    This renders the scene zones, objects, and the ordered mission phases.
  </Step>

  <Step title="Run the mission">
    ```bash theme={null}
    cadenza env run rescue-dog --headless
    ```

    Executes the mission phase-by-phase with the built-in scripted driver, logs
    every tick, and automatically runs the LLM judge at the end for a verdict.
    Drop `--headless` to watch it in the MuJoCo viewer.
  </Step>

  <Step title="Inspect results & make training data">
    Each run writes to `rescue-dog/.cadenza-env/`:

    * `<run-id>.log.jsonl`: one record per action (phase, reward, observation).
    * `<run-id>.finetune.jsonl`: `(prompt, action, reward)` records for VLA training.

    Analyze and export:

    ```bash theme={null}
    cadenza env stats rescue-dog                         # motion + reward analytics
    cadenza env finetune rescue-dog .cadenza-env/<run-id>.log.jsonl -o train.jsonl
    ```
  </Step>
</Steps>

## What next

<CardGroup cols={2}>
  <Card title="Author a mission" icon="diagram-project" href="/cli/environment-schema">
    The full `env.json` schema: phases, predicates, reward shaping.
  </Card>

  <Card title="Build actions" icon="hand" href="/cli/actions">
    Create and sync reusable robot actions to your account.
  </Card>

  <Card title="Fine-tune" icon="brain" href="/cli/training-and-lora">
    `env train` and `env lora` to improve a policy.
  </Card>

  <Card title="Drive it from Python" icon="code" href="/sdk/custom-environments">
    Run the same mission with your own VLA via the SDK.
  </Card>
</CardGroup>