# Manual Crawler

Manual Crawler allows you to manually navigate through a website and create trajectories (sequences of actions) that can be tested and replayed. This is useful for creating specific test scenarios or exploring complex user flows. 

#### **Browser Session Selection (Optional)**

Select an existing browser session to use for authenticated manual crawling

**How to use:**

* Click the dropdown to see available browser sessions.
* Select a session if you want to crawl authenticated areas.
* Leave empty for unauthenticated crawling.

#### Using Manual Crawler

1. **Start the Crawler:**
   * Click **Start Manual Crawler.**
   * A browser window opens (this may take a few seconds) on the **SANDBOX** agent.
   * The browser navigates to your domain.
2. **Understanding the Toolbar:**

The browser window includes a toolbar with these controls:

* **Status Indicator (Green/Yellow Dot):**
  * **Green:** System is waiting for your action
  * **Yellow:** System is processing your last action
  * **Red:** Error occurred
* **Status Text:**
  * Shows current state: "Waiting for action", "Processing...", "Loading page..."
* **Set Starting Point:**
  * Sets the current URL as the starting point for a new trajectory
  * Useful when you want to create multiple trajectories from different starting pages
  * Each trajectory can have a different starting point
* **Stop & Reset:**
  * Stops the current trajectory recording.
  * Saves all the action recordings up to this point in a Trajectory.
  * Resets back to the starting point.
* **Quit:**
  * Closes the browser window
  * Ends the manual crawler session
  * Saves any trajectories you've created


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://copilot-docs.bugbase.ai/enterprise/how-to-trigger-an-external-scan/manual-crawler.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.