Product Research · X post · source Oct 26, 2026
Sales Database and Buy-Price App Built with Claude and Amazon's Seller Connector
Turn your own sales history into buy prices for sourcing
“first dashboard in about 15 minutes of his own time”
Per source Self-reported by the source, not independently verified.
Copy-paste prompt
Using the Amazon seller connector, pull my orders, FBA orders and settlements for the last 24 months into a local database with one row per sale. For each item, show units sold, average and lowest sale price, and the max buy price that leaves 50% profit after Amazon fees and shipping. Read-only: don't change any listing or price.
The source didn't publish its exact prompt. We wrote this starter so you can try the same workflow. Replace anything in [brackets].
What they did
A collectible Hot Wheels seller who has sold on Amazon since 1997 used Claude with Amazon's seller connector to pull all his available account data into a relational database, then had Claude build a seller app on top of it: today's orders, items to ship, FBA orders, money, and a 12-month sales history per item.
How it went
He had the first dashboard in about 15 minutes of his own time and built the app in 2 days, mostly while playing video games. Within 3 days it used his real sales data to set buy target prices for a 50% profit and ran an eBay scraper looking for matches, and he cut its token usage by about 95% versus day 1. He also reported the connector failing for a while after he upgraded his Claude plan.
We only report what the source says. Results are self-reported unless noted.
Worth knowing
Short posts with screenshots, no sales figures. Pricing buys from your own sell-through history rather than from an estimate is the useful idea.