Claude in Chrome · Anthropic
Track competing newsletters' rankings every week
A Substack newsletter writer scheduled Claude in Chrome to scrape the top Substack charts every Tuesday, then had Claude Cowork analyze the movers. He says a job that took ages by hand now takes a couple of minutes.
What they did
He asked Claude in Chrome to build a table of the first 250 entries on a third-party Substack chart site with rank, name, date and free or paid status, offered as a CSV, then converted that chat into a task scheduled every Tuesday. A Claude Cowork task scheduled shortly after reads the folder and lists the top gainers, new entrants and biggest losers, separately for paid and free lists, to spot growth patterns and collaboration partners.
How it went
The poster says the scrape now takes a couple of minutes instead of a long manual session, and each week a spreadsheet with the full analysis lands in his folder.
Worth knowing
Scheduled tasks only run while the computer is awake, and Cowork needs the desktop app open; each run also uses plan allowance. He advises not automating everything, and the article does not address data or account security.
Try it with Claude in Chrome
Go to <ranking page URL> and build a table of the first <number> entries with rank, name, category and any free or paid label, then save it as a CSV in <folder>. Repeat this every <weekday>. After each run, compare it with last week's file and list the biggest risers, new entries and biggest fallers in my niche, <your niche>.
We wrote this prompt from the case. Replace the parts in angle brackets with your own details.
What this label means: User reports
Someone using it at work posted about it. Any numbers are theirs, so we write "the poster says".
Real cases of AI agents at work, from every major agent, each linked to where it was first reported. Rewritten in our own words, most with a prompt you can try. These are not Wize customers.