A 6-week test of letting Claude run Amazon book ads
Claude directly managed an Amazon book ads account for about six weeks. This was not just using AI for ideas; it connected to the Ads API on a schedule, pulled reports, changed bids, added , and paused weak ads. There was no approval step before changes, only a log afterward.
The setup was for about 10 nonfiction books published under several pen names, where manual ad management was taking too much time for a catalog that barely earned enough. In June, royalties were $682 and was $757, so the account lost $75. The result still looked like progress because earlier losses were larger and required manual work.
One legal niche book produced about two thirds of the royalties, while the rest of the catalog did very little. Claude ran every three days against the Amazon Ads API, with a setting hard limits it was not allowed to change.
Key points
- Claude was connected directly to an Amazon ads account.
- It ran every three days and adjusted bids, , and paused ads.
- June ended with $682 in royalties and $757 in , a $75 loss.
- The experiment still saved manual work and reduced earlier losses.
- Most revenue came from one legal niche book, while the rest of the catalog performed poorly.