5e9c1f4f68
Co-authored-by: Ritik Sahni <ritiksahni0203@gmail.com> Co-authored-by: Suchintan <suchintan@users.noreply.github.com>
93 lines
3.2 KiB
Plaintext
93 lines
3.2 KiB
Plaintext
---
|
|
title: Watching Live Execution
|
|
subtitle: Monitor, interact with, and control running tasks
|
|
slug: cloud/monitor-a-run
|
|
---
|
|
|
|
When you run a task from the [Discover page](/cloud/run-a-task), you're taken to the live execution screen where you can watch the browser in real time.
|
|
|
|
<img src="/images/cloud/live-execution-overview.png" alt="Live execution screen" />
|
|
|
|
---
|
|
|
|
## The execution screen
|
|
|
|
The execution view has three panels:
|
|
|
|
| Panel | What it shows |
|
|
|-------|---------------|
|
|
| **Left: Task configuration** | The block being executed, its URL, and prompt. A status badge shows the current state. |
|
|
| **Center: Live browser** | Real-time view of the browser. You see pages load, forms fill, and buttons click. |
|
|
| **Right: Agent logs** | Real-time LLM reasoning and action decisions. Shows why the AI made each choice. |
|
|
|
|
---
|
|
|
|
## When the live view is available
|
|
|
|
The live browser stream is active while the task is still in progress:
|
|
|
|
| Status | Live view |
|
|
|--------|-----------|
|
|
| `created` | Waiting to start |
|
|
| `queued` | Waiting for a browser |
|
|
| `running` | **Active**: the browser is navigating |
|
|
| `paused` | Waiting for human interaction |
|
|
| `completed` | Stream closed. View the recording instead. |
|
|
| `failed` | Stream closed. View the recording instead. |
|
|
| `terminated` | Stream closed |
|
|
| `timed_out` | Stream closed |
|
|
| `canceled` | Stream closed |
|
|
|
|
Once a task reaches a final state, the live stream closes. Open the run from **Runs** in the sidebar to access the full recording, screenshots, and action history.
|
|
|
|
---
|
|
|
|
## Taking control of the browser
|
|
|
|
The **Take Control** button lets you interact directly with the browser. This is useful when:
|
|
- A CAPTCHA appears that the AI can't solve
|
|
- The site has an unusual login flow
|
|
- You need to navigate past an unexpected popup
|
|
|
|
Click **Take Control** to start interacting. Your mouse and keyboard input goes directly to the browser. Click **Stop Controlling** to hand control back to the AI.
|
|
|
|
<Warning>
|
|
Taking control pauses the AI agent. Remember to release control so the agent can resume.
|
|
</Warning>
|
|
|
|
---
|
|
|
|
## Stopping a running task
|
|
|
|
You can cancel a task at any time while it's running or queued. Click the **Cancel** button in the task header. A confirmation dialog appears before the task is stopped. The task transitions to `canceled` and any configured webhook fires with the canceled status.
|
|
|
|
---
|
|
|
|
## Reviewing results
|
|
|
|
Once a task finishes, open it from **Runs** to see the full results.
|
|
|
|
### Actions tab
|
|
|
|
Step-by-step breakdown of every action the AI took. Each entry shows:
|
|
|
|
- **Action type**: Click, Type, Scroll, Select, etc.
|
|
- **Success or failure** indicator
|
|
- **AI reasoning**: Why the agent chose this action
|
|
- **Input details**: For type actions, the text that was entered
|
|
|
|
### Recording tab
|
|
|
|
Full video replay of the browser session. Every task is recorded automatically.
|
|
|
|
### Parameters tab
|
|
|
|
The configuration you submitted: URL, prompt, engine, proxy location, webhook URL, data schema, and other settings.
|
|
|
|
### Diagnostics tab
|
|
|
|
Debug information for troubleshooting:
|
|
- **LLM prompts**: The exact prompts sent to the AI model
|
|
- **Element trees**: The DOM structure the AI analyzed
|
|
- **Annotated screenshots**: Screenshots with element labels the AI used for decisions
|