Difficulty	Easy Peasy
Time	60 mins
Cost	£0
Key concepts	- WebUI

Google AI Studio API |

⚡️ 30 second Summary

Welcome to this project on Browser Automation with AI 🤖

Do you spend time on repetitive browser tasks like checking websites, filling applications, or copying data between sheets?…

Let's build your own AI agent that can go into your browser and complete tasks for you. Browser automation is a valuable skill for developers, testers, and anyone looking to streamline their online work

A peek into your browser agent in action. This is your agent figuring out how to enter a Google search!

🔰In this project, get ready to

🌐 Step #1: Set up your Development Environment!

In this project, we'll use Browser Use's WebUI. Browser Use is a developer tool that connects AI models with your browser, while WebUI adds a visual interface - so you can work with Browser Use with clicks instead of code

A sneak peek of WebUI, the visual interface for Browser Use

You're going to need a few development tools to get WebUI up and running:

Python is the programming language that powers WebUI and lets it run on your computer. You'll use it to run WebUI

Pip & UV are kind of like app stores - they help you download and install Python packages, which are like pre-built pieces of code. There are some packages you need in your computer for WebUI to work, so you'll use Pip and UV to install them

Git is a tool that will help you download the latest version of WebUI's source code from its online repository

🔰In this step, you’re going to

🔰1.1} Check if you already have the requisite tools

Before we start, let's check if you already have some of the required development tools in your computer

🍎 MacOS