​
What is agent()?

agent.execute("apply for a job at browserbase")
agent turns high level tasks into fully autonomous browser workflows. You can customize the agent by specifying the LLM provider and model, setting custom instructions for behavior, and configuring max steps. Agent

​
Why use agent()?

Multi-Step Workflows

Execute complex sequences automatically.

Visual Understanding

Sees and understands web interfaces like humans do using computer vision.

​
Using agent()

Here is how you can use agent() to create an agent. 
const agent = stagehand.agent({
  provider: "anthropic",
  model: "claude-sonnet-4-20250514",
  instructions: "You are a helpful assistant that can use a web browser.",
  options: {
    apiKey: process.env.ANTHROPIC_API_KEY,
  },
});
await agent.execute("apply for a job at Browserbase")
Stagehand uses a 1024x768 viewport by default (the optimal size for Computer Use Agents). Other viewport sizes may reduce performance. If you need to modify the viewport, you can edit in the Browser Configuration.

​
Available Models

Use specialized computer use models (e.g., computer-use-preview from OpenAI or claude-sonnet-4-20250514 from Anthropic)

Available Models

Check out the guide on how to use different models with Stagehand.

​
Agent Execution Configuration

Control the maximum number of steps the agent can take to complete the task using the maxSteps parameter. 
// Set maxSteps to control how many actions the agent can take
await agent.execute({
  instruction: "Sign me up for a library card",
  maxSteps: 15 // Agent will stop after 15 steps if task isn't complete
});
For complex tasks, increase the maxSteps limit and check task success. 
// Complex multi-step task requiring more actions
const result = await agent.execute({
  instruction: "Find and apply for software engineering jobs, filtering by remote work and saving 3 applications",
  maxSteps: 30, // Higher limit for complex workflows
});

// Check if the task completed successfully
if (result.success === true) {
  console.log("Task completed successfully!");
} else {
  console.log("Task failed or was incomplete");
}

​
Best Practices

Following these best practices will improve your agent’s success rate, reduce execution time, and minimize unexpected errors during task completion.

​
Start on the Right Page

Navigate to your target page before executing tasks: 
await page.goto('https://github.com/browserbase/stagehand');
await agent.execute('Get me the latest PR on the stagehand repo');

​
Be Specific

Provide detailed instructions for better results: 
await agent.execute("Find Italian restaurants in Brooklyn that are open after 10pm and have outdoor seating");

​
Troubleshooting

​
Next steps

Act

Execute actions efficiently using observe results

Extract

Extract structured data from observed elements