Point it at a website. Get the spreadsheet.
Copying listings by hand takes an afternoon. Writing a scraper takes longer. Fulminare opens the pages in a real browser, follows pagination, pulls the fields you name, and saves them to a spreadsheet.
Go to news.ycombinator.com and collect the top 60 stories across the first two pages: title, link, points, number of comments, and age. Save it as an .xlsx sorted by points.
How it does it
- 01Opens the site in a real browser on its sandbox.
- 02Works out the page structure and the fields you asked for.
- 03Follows next-page links until it has everything.
- 04Saves a clean CSV or .xlsx and shows you a preview.
Handles pages that need clicking
Because it uses a real browser, it can click Load more, open detail pages, and wait for content that loads with JavaScript.
Respect the site
Use it on public pages you are allowed to collect from, and check the site's terms for anything commercial.
Questions
Do I need to write code?
No. Describe the data in plain English. Fulminare writes and runs whatever it needs on its own machine.
Can it run every day?
Start it as an overnight run for big jobs. For repeating it, run the same prompt again from your session history.
Is Fulminare free?
Yes. The free plan includes 3 live sandboxes, 200 runs / day, 100k tokens / mo, 5 overnight runs / mo — no card required.
How is this different from ChatGPT?
A chatbot tells you how to do the task. Fulminare does it: every session runs on its own cloud machine with a real shell, browser, and file system, and you get the finished files back.
Related
Stop reading answers.
Start getting work done.
Busy people save hours every week when the agent stops advising and starts doing. Point Fulminare at the job. Come back to it finished.