Glossary
What is browser automation?
Browser automation is controlling a web browser with code to perform actions automatically: open pages, click, type, upload files and read results. Tools include Playwright, Puppeteer and Selenium. Traditional scripts follow fixed selectors; AI agents add flexibility by reading each page and deciding what to do.
Tools
| Tool | Notes |
|---|---|
| Playwright | Microsoft; Chromium, Firefox, WebKit; many languages |
| Puppeteer | Google; Chrome-focused; JavaScript |
| Selenium | Long-standing; WebDriver standard; many languages |
Scripts vs agents
A script says "click the element with id submit". When the site changes, it breaks. An AI agent reads the page and finds the submit button by meaning. For many different sites, like hundreds of directory forms, scripts need constant maintenance; agents with form understanding handle variety better, and recorded paths per site make them faster and more reliable.
Limits
Automation should respect site terms, rate limits and bot checks. Bypassing CAPTCHAs or protections is against most sites' rules.
Example
A team maintains Playwright scripts for 50 directories and spends hours each month fixing broken selectors. Switching to an agent that reads each form, guided by notes on each directory's flow, cuts maintenance to rechecking the notes.
FAQ
Which browser automation tool is best?
Playwright is popular for new projects; Selenium for existing ecosystems.
Is browser automation legal?
Generally, if you follow site terms and laws; bypassing protections is not acceptable.
Can browser automation fill any form?
Most, except steps built to require a human, like CAPTCHAs.
Does browser automation work on sites with bot protection?
Often not reliably from servers; in a user's own browser it works far better.