Overview

Browser Use Cloud enables both AI-powered and direct browser automation through five core concepts:

Profile → Sessions → Tasks + Files

Plus standalone: Browser Sessions (direct CDP access)

Core Concepts

Profile: Preserves login state and browser settings across automations
Session: AI agent environment for natural language task execution
Browser: Direct Chrome DevTools Protocol access for custom automation
Task: Single automation instruction given to an AI agent
Files: Input data for tasks and output results from agents

Automation Approaches

AI-Powered (Simple)

1
const task = await client.tasks.createTask({
2
    task: "Search for top 10 Hacker News posts"
3
});

✅ Natural language ✅ Quick setup ❌ Limited control

AI-Powered (Advanced)

1
const session = await client.sessions.createSession({ 
2
    profileId: "profile_123" 
3
});
4
const task = await client.tasks.createTask({
5
    sessionId: session.id,
6
    task: "Log into dashboard and export data"
7
});

✅ State preservation ✅ Multi-step workflows ❌ Limited control

Direct Control

1
const browser = await client.browsers.createBrowserSession({ 
2
    profileId: "profile_123" 
3
});
4
const pwBrowser = await chromium.connectOverCDP(
5
    browser.cdpUrl
6
);

✅ Full control ✅ Custom scripts ❌ Requires programming

When to Use What

AI-Powered Simple: Quick tasks, no login, proof of concepts
AI-Powered Advanced: Multi-step workflows, login required
Direct Control: Custom automation, integration testing
Profiles: User-specific state, production apps