---
title: 'Interact with a website'
description: 'You can use Stagehand to intelligently interact with a website using AI'
icon: 'arrow-pointer'
---

## Executing actions

Stagehand has an `act()` function that can be used to execute actions on a page using natural language. Here's an example of Stagehand to find jobs on LinkedIn:

![Take actions with Stagehand](/media/linkedin.gif)

This workflow is as simple as the following lines of code:
```js
const page = stagehand.page
// Navigate to the URL
await page.goto("https://linkedin.com");

await page.act("click 'jobs'");
await page.act("click the first job posting");
```

The `page` object extends the Playwright page object, so you can use any of the [Playwright page methods](https://playwright.dev/docs/api/class-page) with it.

## Read structured data from the page

You can use the `extract()` method to extract structured data from the page. Here's an example of how to extract the job title from the job posting:

```js
const { jobTitle } = await page.extract({
	instruction: "Extract the job title from the job posting",
	schema: z.object({
		jobTitle: z.string(),
	}),
});
```

Stagehand uses [Zod](https://zod.dev/) to help you define the schema of the data to be extracted.

## Preview/Cache an action

Sometimes you want to preview an action before it's executed. You can do this by calling `page.observe()` before `act()`.

```js
const [action] = await page.observe("click 'jobs'");

console.log("Going to execute action:", action)
// You can add extra logic here to validate/cache the action

await page.act(action)
```

`action` will be a JSON object that describes the action to be taken.

```javascript
/** action is a JSON-ified version of a Playwright action:
{
	description: "The jobs link",
	action: "click",
	selector: "/html/body/div[1]/div[1]/a",
	arguments: [],
}
**/
```

For more on caching, see the [caching docs](/examples/caching).

## What actions can I take?

Stagehand maps natural language to [Playwright](https://playwright.dev) actions. 

We generally support the following actions:

| Action | Description |
|--------|-------------|
| `scrollIntoView` | Scrolls an element into the visible area of the browser window |
| `scrollTo` | Scrolls to a specific percentage of the page height |
| `fill` | Fills in form fields with specified text |
| `type` | Types text into input fields (alias for `fill`) |
| `press` | Simulates pressing keyboard keys |
| `click` | Clicks on elements matching the specified selector |
| `nextChunk` | Scrolls the height of the viewport by 100% |
| `prevChunk` | Scrolls the height of the viewport by -100% |

Each of these actions can be triggered using natural language commands. For example:
```js
await page.act("scroll to the bottom of the page")
await page.act("fill in the username field with 'john_doe'")
await page.act("scroll the modal to the next chunk")
```