> For the complete documentation index, see [llms.txt](https://docs.gpmautomate.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.gpmautomate.com/automate-en/action-guide/navigation/go-to-url.md).

# Go to URL

This action instructs the browser to go directly to a website at the path (URL) you specified.

* Effect: This is the starting step for the tool to begin working. You just need to enter the website address, and the browser will automatically navigate to that page for you to perform the next steps.

🎥 Watch the tutorial video: [Here](https://youtu.be/a9qNt96X1SM).

#### Configuration parameters:

* URL: The exact address of the website you want to open.

  > ⚠️ Mandatory note: The path filled in this field must include the full network protocol as `https://` or `http://` at the beginning (For example: `https://24h.com.vn`). If you only enter the short form `24h.com.vn`, the system will not recognize the routing structure and will report an action error.
* Timeout (s): The timeout (in seconds) that the script will wait for the website to fully load all data. The system's default if you leave it blank is `60` seconds.

#### Practical example: Adjusting the wait time when using a slow Proxy

When you run a Marketing script or scrape data through Profiles with a Proxy attached, you may sometimes encounter Proxy packages with very slow connection speeds, long response times, or the target website's server being congested. If you keep the default time, the script may get disconnected midway due to timeout:

* Configuration method:
  * URL: `https://pinterest.com`
  * Timeout: Change from `60` to `120` (2 minutes).
* Result: The browser will patiently wait up to 120 seconds for the website to finish loading data. Conversely, if your network is very strong and you want to optimize speed so that the script does not hang when encountering a dead website, you can proactively reduce this number to `20` or `30` seconds for the system to quickly terminate the error flow and switch to another account.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

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

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.gpmautomate.com/automate-en/action-guide/navigation/go-to-url.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.