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

# Quickstart with the CLI

> Start a coding agent in a sandbox from your terminal and read what it did

**1. Create an API key**

Sign in to [Tracks](https://tracks.alpic.ai). Open your profile menu at the bottom of the sidebar, then **API keys**, and click **New API key**. Copy the key: it starts with `trk_` and is shown only once.

Runs start only while your balance is above $0. Your first sign-in comes with $10 of free credit; add more in **Billing**. See [billing](https://docs.tracks.alpic.ai/concepts/billing.md).

**2. Install the CLI**

```bash theme={null}
npm install --global @alpic-ai/tracks
export TRACKS_API_KEY=trk_...
tracks health
```

`tracks health` prints `ok` when the API is reachable. It doesn't check your key or your balance: the next step does.

**3. Start a run**

```bash theme={null}
tracks runs create "Explain what this project does and how to run it locally" \
  --harness claude-code --model claude-sonnet-5-5 \
  --repository https://github.com/alpic-ai/apps-sdk-template \
  --budget 2
```

The command returns right away with the run as JSON. Note its `id`: the sandbox is still preparing.

Without `--budget` or `--time-limit`, a run uses the [default budget and time limit](https://docs.tracks.alpic.ai/concepts/runs.md#budget-and-time-limit).

**4. Follow it**

```bash theme={null}
tracks runs follow <id> --events
```

This prints what the agent does as it happens, one JSON line per event, until the run ends.

**5. Read the result**

```bash theme={null}
tracks runs get <id>
tracks runs usage <id>
```

The first shows how the run ended, the second what it consumed and cost.

**6. See it in the web app**

Open **Runs** in the [web app](https://tracks.alpic.ai) and click your run. You see the agent's conversation, the tools it called and the run's settings, with its cost.

> [!NOTE]
>
> The sandbox is destroyed when the run ends. Anything the agent should keep, it must push or send somewhere, for
> example by asking it in the prompt to open a pull request.

## Compare two agents

One run tells you what one agent did. To know which agent does your task best, give the same task to several agents in an experiment: see [compare two agents](https://docs.tracks.alpic.ai/guides/compare-two-agents.md).

## Next steps

* [Runs](https://docs.tracks.alpic.ai/concepts/runs.md): follow-up prompts, setup scripts, files and limits.
* [Private repositories](https://docs.tracks.alpic.ai/guides/private-repositories.md): give the agent code that isn't public.
* [CLI reference](https://docs.tracks.alpic.ai/cli/overview.md) and [API reference](https://docs.tracks.alpic.ai/api/overview.md).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.