Browser automation script generator
Describe a task in a browser and get a browser-use agent script or a Playwright test, with stable locators and no embedded secrets.
Your key stays in your browser.It goes straight to the provider, never to our servers, and we neither log nor keep it. Use a dedicated key with a spending cap, and delete it in the provider's dashboard when you are done.
Input
Result
The result will appear here.There are two ways to make a browser do something: give an AI agent a precise task and let browser-use figure out the clicks, or write the steps as a Playwright script when you already know them. Both start with a description, and both are easy to get wrong — a vague task string sends the agent wandering, a Playwright test full of CSS selectors breaks on the next deploy. Describe what should happen and this generator writes either: a browser-use script whose task is spelled out step by step with the exact output format, or a Playwright test in TypeScript or Python with role-based locators, real assertions and no fixed sleeps.
How it works
- For browser-use, the task string is the program, so it is written to be followed literally: URLs, field labels, the order of steps, what to do when something is missing, the output format.
- For Playwright, locators use roles, labels and text rather than CSS or XPath; guesses are marked with a TODO comment so you know what to verify.
- Credentials are never written into the script — they are read from named environment variables, and tasks that would need CAPTCHA bypass or scraping behind someone else's login are left out and noted.
Where your data goes
With your own key, what you type and the key go from your browser straight to the provider you choose; neither passes through Hysen Labs. In hosted mode, your text goes through our server to our provider (DeepSeek) and is billed in credits; we keep the token counts and cost of each run for billing, never the text itself or the answer. How the provider handles the text is governed by its own privacy policy.
This tool handles keys and credentials, so nothing about a run is saved, not even to your own history.
About your API key
We do not collect, store or leak your key: it lives only in this page's memory (unless you tick “remember in this tab”) and is gone when you close it. Still, treat any key you have pasted into a web page with care — create a dedicated key with a spending cap for use here, and delete or rotate it in your provider's dashboard when you are done.
What it costs
This tool is free, with no sign-in and no points.
Common questions
- When should I use an agent instead of Playwright?
- Use browser-use when the site changes often, the path is not fully known, or the task needs judgement — reading a table and deciding what to click. Use Playwright when the steps are fixed and you want them to run fast, cheaply and identically every time, which is what tests and scheduled jobs need.
- Which model does the browser-use script need?
- Any supported vision-capable model; the script is generated with a placeholder you set. Browser-use's own benchmarks favour the larger frontier models for reliability, while a cheaper model is fine for simple extraction. The required API key variable is named in a comment.
- Will the Playwright test pass on the first run?
- Often, if the page uses accessible labels; otherwise the TODO-marked locators need adjusting after one run with the Playwright inspector. The structure — one test per scenario, explicit expectations, auto-waiting — is the part that is hard to get right and is already done.
The open-source behind it
This tool is a self-contained implementation. browser-use/browser-use (MIT) does the same job as a library — if you need this behaviour inside your own program, start there rather than calling a web page.
browser-use/browser-useAlso known as
- browser-use script generator
- playwright test generator ai
- browser automation from description
- web scraping agent python
- generate playwright test from text
- browser agent task prompt