Act

What is `act()`?

await stagehand.act("click on add to cart")

act enables Stagehand to perform individual actions on a web page. Use it to build self-healing and deterministic automations that adapt to website changes.

Why use `act()`?

Natural Language Instructions

Write automation in plain English. No selectors or complex syntax.

Precise Control

Build automations step by step. Define exactly what happens at every moment.

Self-Healing

Actions automatically adapt when websites change.

Caching

Cache actions to avoid LLM calls and ensure consistent execution across runs.

Using `act()`

Use act to perform single actions in your automation. Here’s how to click a button:

await page.goto("https://example-store.com");
await stagehand.act("click the add to cart button");

iFrame and Shadow DOM Support Stagehand automatically handles iFrame traversal and shadow DOM elements without requiring additional configuration.

With act, breaking complex actions into small, single-step actions works best. If you need to orchestrate multi-step flows, use multiple act commands or agent.

Suggested actions

Action	Example instruction
Click	`click the button`
Fill	`fill the field with <value>`
Type	`type <text> into the search box`
Press	`press <key> in the search field`
Scroll	`scroll to <position>`
Select from dropdown	`select <value> from the dropdown`

Return value of `act()`?

When you use act(), Stagehand will return a Promise<ActResult> with the following structure:

{
  success: true,
  message: 'Action [click] performed successfully on selector: xpath=/html[1]/body[1]/div[1]/span[1] → Action [click] performed successfully on selector: xpath=/html[1]/body[1]/div[2]/div[1]/section[1]/div[1]/div[1]/div[25]',
  actionDescription: 'Favorite Colour',
  actions: [
    {
      selector: 'xpath=/html[1]/body[1]/div[1]/span[1]',
      description: 'Favorite Colour',
      method: 'click',
      arguments: []
    },
    {
      selector: 'xpath=/html[1]/body[1]/div[2]/div[1]/section[1]/div[1]/div[1]/div[25]',
      description: 'Peach',
      method: 'click',
      arguments: []
    }
  ]
}

Do this
Don't do this

Break your task into single-step actions.

// Break it into single-step actions
await stagehand.act("open the filters panel");
await stagehand.act("choose 4-star rating");
await stagehand.act("click the apply button");

For multi-step tasks, use agent() instead.

// Too complex - trying to do multiple things at once
await stagehand.act("open the filters panel, choose 4-star rating, and click apply");

Advanced Configuration

You can pass additional options to configure the model, timeout, variables, and target page:

// Custom model configuration
await stagehand.act("choose 'Peach' from the favorite color dropdown", {
  model: "google/gemini-2.5-flash",
  timeout: 10000
});

Server-side Caching

serverCache only works when running with env: "BROWSERBASE". It has no effect in local environments.

When running on Browserbase, Stagehand automatically caches act() results server-side. Repeated calls with the same inputs return instantly without consuming LLM tokens. Caching is enabled by default and can be controlled globally on the constructor or overridden per call:

// Disable server-side caching for the entire instance
const stagehand = new Stagehand({
  env: "BROWSERBASE",
  serverCache: false,
});

// Or disable it for a single call
await stagehand.act("click the login button", { serverCache: false });

// Check whether a result was served from cache
const result = await stagehand.act("click the login button");
console.log(result.cacheStatus); // "HIT", "MISS", or undefined

For how the cache works, tuning the validation threshold, and best practices, see the Server Caching guide.

Using with Custom Pages

You can use act() with pages from other browser automation libraries like Puppeteer, Playwright, or Patchright by passing the page option:

import { Stagehand } from "@browserbasehq/stagehand";
import puppeteer from "puppeteer-core";

const stagehand = new Stagehand({
  env: "BROWSERBASE",
});
await stagehand.init();

// Connect with Puppeteer
const browser = await puppeteer.connect({
  browserWSEndpoint: stagehand.connectURL(),
  defaultViewport: null,
});

const pages = await browser.pages();
const customPage = pages[0];

await customPage.goto("https://www.example.com/blog");

// Use act with the custom Puppeteer page
await stagehand.act("click the next page button", {
  page: customPage
});

This works with:

Puppeteer: Pass Puppeteer Page objects
Playwright: Pass Playwright Page objects
Patchright: Pass Patchright Page objects
Stagehand Page: Use stagehand.context.pages()[0] or context.activePage() (default)

Complete API Reference

See the full act() reference for detailed parameter documentation, return values, and advanced examples.

Best practices

Ensure reliable actions

Use observe() to discover candidate actions on the current page and plan reliably. It returns a list of suggested actions (with selector, description, method, and arguments). You can pass an observed action directly to act to execute it.

const [action] = await stagehand.observe("click the login button");

if (action) {
  await stagehand.act(action);
}

Analyze pages with observe()

Plan actions with observe() before executing with act.

Reduce model costs

Enable automatic action caching by specifying a cacheDir when initializing Stagehand. The first time an action runs, it’s cached. Subsequent runs reuse the cached action without LLM calls.

import { Stagehand } from "@browserbasehq/stagehand";

// Enable caching by specifying a cache directory
const stagehand = new Stagehand({
  env: "BROWSERBASE",
  cacheDir: "act-cache" // Actions are automatically cached here
});

await stagehand.init();
const page = stagehand.context.pages()[0];

// First run - makes LLM call and caches the action
await stagehand.act("click the login button");

Caching persists across script executions. The first time you run your script, actions are cached to your local filesystem. On subsequent runs, cached actions are reused automatically, significantly reducing costs and improving performance.

Complete caching guide

Learn advanced caching techniques and patterns for optimal performance.

Secure your automations

Variables are not shared with LLM providers. Use them for passwords, API keys, and other sensitive data.

Load sensitive data from environment variables using .env files. Never hardcode API keys, passwords, or other secrets directly in your code.

// Variables use %variableName% syntax in the instruction
await stagehand.act("type %username% into the email field", {
  variables: { username: "user@example.com" }
});

await stagehand.act("type %password% into the password field", {
  variables: { password: process.env.USER_PASSWORD }
});

await stagehand.act("click the login button");

When handling sensitive data, set verbose: 0 in your Stagehand configuration to prevent secrets from appearing in logs. See the configuration guide for more details.

User Data Best Practices

Complete guide to securing your browser automations with best practices and configurations.

Troubleshooting

Method not supported

Problem: act fails with “method not supported” errorSolutions:

Use clear and detailed instructions for what you want to accomplish
Review our evals to find the best models for your use case
Use observe() and verify the resulting action is within a list of expected actions

Solution 1: Validate with observe

const prompt = "click the submit button";
const expectedMethod = "click";

try {
  await stagehand.act(prompt);
} catch (error) {
  if (error.message.includes("method not supported")) {
    // Observe the same prompt to get the planned action
    const [action] = await stagehand.observe(prompt);

    if (action && action.method === expectedMethod) {
      await stagehand.act(action);
    } else {
      throw new Error(`Unsupported method: expected "${expectedMethod}", got "${action?.method}"`);
    }
  } else {
    throw error;
  }
}

Solution 2: Retry with exponential backoff

// Retry with exponential backoff for intermittent issues
const prompt = "click the submit button";
const maxRetries = 3;

for (let attempt = 0; attempt <= maxRetries; attempt++) {
  try {
    await stagehand.act(prompt, { timeout: 10000 + (attempt * 5000) });
    break; // Success, exit retry loop
  } catch (error) {
    if (error.message.includes("method not supported") && attempt < maxRetries) {
      // Exponential backoff: wait 2^attempt seconds
      const delay = Math.pow(2, attempt) * 1000;
      console.log(`Retry ${attempt + 1}/${maxRetries} after ${delay}ms`);
      await new Promise(resolve => setTimeout(resolve, delay));
    } else {
      throw error;
    }
  }
}

Action failed or timed out

Problem: act times out or fails to complete action (often due to element not found)Solutions:

Ensure page has fully loaded
Check if content is in iframes: Learn more about working with iframes
Increase action timeout
Use observe() first to verify element exists

// Handle timeout and element not found issues
try {
  await stagehand.act("click the submit button", { timeout: 30000 });
} catch (error) {
  // Check if page is fully loaded
  await page.waitForLoadState('domcontentloaded');

  // Use observe to check element state
  const [element] = await stagehand.observe("find the submit button");

  if (element) {
    console.log("Element found, trying more specific instruction");
    await stagehand.act("click the submit button at the bottom of the form");
  } else {
    console.log("Element not found, trying alternative selector");
    await stagehand.act("click the button with text 'Submit'");
  }
}

Incorrect element selected

Problem: act performs action on wrong elementSolutions:

Be more specific in instructions: include visual cues, position, or context
Use observe() to preview which element will be selected
Add contextual information: “the search button in the header”
Use unique identifiers when available

// More precise element targeting
// Instead of:
await stagehand.act("click the button");

// Use specific context:
await stagehand.act("click the red 'Delete' button next to the user John Smith");

// Or preview with observe first:
const [action] = await stagehand.observe("click the submit button in the checkout form");
if (action.description.includes("checkout")) {
  await stagehand.act(action);
}

Next steps

Orchestrate complex workflows with Agent

Use Agent to autonomously execute multi-step tasks and complex workflows.

Caching actions

Speed up repeated automations by caching actions.

Extract data with extract()

Use extract with a data schema to pull clean, typed data from any page.

Preview actions with observe()

Preview actions with observe() before executing them.

First Steps

The Basics

Configuration

Best Practices

Integrations

Reference

Migration Guides

What is `act()`?

Why use `act()`?

Natural Language Instructions

Precise Control

Self-Healing

Caching

Using `act()`

Return value of `act()`?

Advanced Configuration

Server-side Caching

Using with Custom Pages

Complete API Reference

Best practices

Ensure reliable actions

Analyze pages with observe()

Reduce model costs

Complete caching guide

Secure your automations

User Data Best Practices

Troubleshooting

Next steps

Orchestrate complex workflows with Agent

Caching actions

Extract data with extract()

Preview actions with observe()

​What is act()?

​Why use act()?

Natural Language Instructions

Precise Control

Self-Healing

Caching

​Using act()

​Return value of act()?

​Advanced Configuration

​Server-side Caching

​Using with Custom Pages

Complete API Reference

​Best practices

​Ensure reliable actions

Analyze pages with observe()

​Reduce model costs

Complete caching guide

​Secure your automations

User Data Best Practices

​Troubleshooting

​Next steps

Orchestrate complex workflows with Agent

Caching actions

Extract data with extract()

Preview actions with observe()

What is `act()`?

Why use `act()`?

Using `act()`

Return value of `act()`?

Advanced Configuration

Server-side Caching

Using with Custom Pages

Best practices

Ensure reliable actions

Reduce model costs

Secure your automations

Troubleshooting

Next steps