> ## Documentation Index
> Fetch the complete documentation index at: https://browseruse-0aece648-larsen-v1-unified-docs.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Watch a run

> Poll a run's status until it finishes. browser-use exposes steps; browsercode exposes events.

The SDK `run()` waits for you. If you call the API directly (or want live progress), poll the run.

## Poll status

`status` is one of `queued`, `running`, `completed`, `stopped`, `failed`.

<CodeGroup>
  ```python Python theme={null}
  from browser_use import BrowserUse
  import time

  client = BrowserUse()
  run = client.agents.browser_use.runs.create(task="...")   # returns immediately
  while True:
      status = client.agents.browser_use.runs.status(run.id)
      if status.status in ("completed", "stopped", "failed"):
          break
      time.sleep(2)
  print(status.result)   # the answer string. `output` is only set for structured output.
  ```

  ```bash curl theme={null}
  curl "https://api.browser-use.com/api/v1/agents/browser-use/runs/run_abc123/status" \
    -H "X-Browser-Use-API-Key: $BROWSER_USE_API_KEY"
  ```
</CodeGroup>

`/status` is the cheap poll target — status, `result`, `output`, cost. Use `GET /runs/{id}` for the full object.

**`result` vs `output`:** `result` is the plain-language answer string, present on every completed run — read it on the golden path. `output` is reserved for structured output and is `null` today (no request parameter enables it yet — put the JSON shape you want in the `task` text and parse `result`). `browsercode`'s larger output comes back as [files](/cloud/files), not in either field.

## See what the agent is doing

Each agent has its own native progress surface — they are genuinely different, so they aren't forced into one shape:

* **`browser-use` → `/steps`** — the browser step list (each navigation/click/extraction).
* **`browsercode` → `/events`** — an incremental event stream (code, terminal output, browser actions).

<CodeGroup>
  ```bash browser-use theme={null}
  curl "https://api.browser-use.com/api/v1/agents/browser-use/runs/run_abc123/steps" \
    -H "X-Browser-Use-API-Key: $BROWSER_USE_API_KEY"
  ```

  ```bash browsercode theme={null}
  # incremental — pass the last cursor you saw to get only newer events
  curl "https://api.browser-use.com/api/v1/agents/browsercode/runs/run_abc123/events?after=CURSOR" \
    -H "X-Browser-Use-API-Key: $BROWSER_USE_API_KEY"
  ```
</CodeGroup>

The [registry](/cloud/choose-an-agent) tells you which watch verb an agent uses. Live streaming (SSE) is coming; today watching is poll-based.

## Find the browser a run used

`browserId` appears on the run once its browser is provisioned (null while queued). Use it to fetch the [recording or downloads](/cloud/manage-browser).

```bash curl theme={null}
curl "https://api.browser-use.com/api/v1/agents/browser-use/runs/run_abc123" \
  -H "X-Browser-Use-API-Key: $BROWSER_USE_API_KEY"
# → { "id": "run_abc123", "browserId": "br_...", "status": "completed", ... }
```