PPC Reporting with Claude for Amazon Sellers

What they did

Applied for Amazon Ads API access, had Claude write the auth script, then pulled Ads API campaign stats and every search term plus SP-API sales, traffic, FBA inventory and returns into one daily JSON bundle with plain Python. Reconciled one day against the old tool, then built a dashboard that splits sales drops into seasonal vs ad-driven, forecasts days of supply from last year's next 30 days, and flags size-return problems.

How it went

The author reports search-term coverage went from 39% (old tool) to 100% (API), the numbers reconciled to the cent against the old tool ($358.99 spend / 1,187 clicks / 50 orders / $1,104.46 sales on the test day), and cancelling the £73/mo tool saves £876 a year.

We only report what the source says. Results are self-reported unless noted.

Worth knowing

Ads API approval took about 10 days. The author keeps a rule that Claude never changes anything in Seller Central or Ads without explicit approval (stated in a follow-up post).

Copy-paste prompt

You are my Amazon data engineer. Write a plain-Python script (standard library only) that:
1. Uses my Amazon Ads API refresh token to pull daily Sponsored Products campaign stats and the full search-term report for the last 30 days, plus the same 30-day window last year.
2. Uses SP-API to pull Sales & Traffic by ASIN, FBA inventory, and customer returns for the same windows.
3. Saves everything as one JSON bundle per day.
Then write a reconciliation check: for a date I choose, print total spend, clicks, orders and sales so I can compare them against my current PPC tool. Do not make any write calls to Amazon.

The source didn't publish its exact prompt. We wrote this starter so you can try the same workflow. Replace anything in [brackets].