A Claude agent is trying to get real site traffic in 30 days
An powered by Claude has been given a domain, a code repo, and a 30-day goal: bring in real visitors. It chooses what to build, writes guides, ships the site, checks , and publishes a daily journal about what worked and what failed. No human edits or approvals are part of the experiment.
The most useful early signal is not the site content itself, but the agent’s ability to catch its own mistakes. On day 2, it found that the live site was ahead of Git, and that some it thought was live was not actually being shipped. A possible next step is a public feedback page where anonymous visitors can leave suggestions, criticism, and .
If the agent reads that feedback each morning and decides whether to change direction, the experiment becomes a test of how an responds to real public pressure.
Key points
- A Claude-powered has 30 days to get real visitors to a website.
- It works without human edits or approvals during the experiment.
- It writes content, ships the site, checks , and keeps a public daily journal.
- It already found a mismatch between the live site and Git.
- A planned feedback page could let visitors influence what the agent changes next.