SponsoredSynergy45Stronger looking, Thicker looking Hair SerumVisit Synergy45

Your business here

This income claim has not been independently verified. This article shows what the person shared so readers can see the workflow.

An Amazon Arbitrage Seller Screens Products and Suppliers With Two Claude Prompts

An Amazon arbitrage seller uses one Claude prompt to judge products against fixed buy rules and another to research suppliers. His screenshots show monthly sales growing from $235,902 in March to $372,802 in August: sales, not profit.

Who this is about: Amazon online arbitrage seller (@fbajayden)

Get the prompt
Income claim
Unverified claimMonthly Amazon sales growing from $235,902 in March to $372,802 in August, by his screenshots. Sales, not profit.
Money comes from
Reselling discounted retail products on Amazon (online arbitrage).

What it takes

Cost
Free planClaude: Free plan. Pro is $20 a month billed monthly ($17 a month billed yearly), and Max starts at $100 a month. Team seats are $25 a month billed monthly.Price checked Oct 24, 2026 on claude.com. Prices change; check before you buy.
Setup time
An afternoonOur estimate from the source, for one business.
Skill needed
No codeApps and settings only.

Explain it simply

Arbitrage means buying products cheaply in one place and reselling them on Amazon for more. This seller wrote two reusable instructions for Claude, an AI chatbot: one checks whether a product passes his buying rules, like enough monthly sales and enough other sellers, and the other looks for a store that sells it cheaply enough. That way every product gets judged by the same rules, and fast.

New to AI? See how AI works

How it works

  1. Pull each product's data from SellerAmp SAS.
  2. Run prompt 1, the product analyzer, which checks the product against fixed buy rules: 350+ sales a month, a big brand and 2+ sellers.
  3. Run prompt 2, supplier research, on Tactical Arbitrage results to find where to buy the product profitably.
  4. Check the listing and the supplier yourself before you buy any stock.

How it went

Sales went from $235,902 in March to $372,802 by August, by his screenshots. A July screenshot shows $402,105.76 in sales, with orders, refunds, payout and gross profit.

  • These are sales figures: cost of goods and Amazon fees aren't taken out, and sourcing, cash and account health matter as much as the prompts.
  • He doesn't say how much time the prompts save.

Prompt

PromptWritten by our editors from the source
Prompt 1 - Product analyzer
"Here is SellerAmp data for [product]: [paste price, BSR, est. monthly
sales, seller count, Buy Box share, restrictions]. Pass only if: 350+
sales/month, recognised brand, 2+ sellers, no restriction for my account,
ROI at least [X]% after fees. Answer PASS or FAIL with the reason for each
rule."

Prompt 2 - Supplier research
"For this product [ASIN, name, max buy cost $X], review these Tactical
Arbitrage results [paste]. List sources where landed cost leaves at least
[X]% ROI, and flag pack size, bundle or model mismatches."

Always check the listing and the supplier yourself before you buy.

Our versions; his prompts are described, not published.

Business fit

Who this suits, and how:

  • Amazon arbitrage and wholesale sellers: write your buy rules into one prompt so every product is judged the same way.

    Shopify & ecommerce
  • Side hustlers starting retail arbitrage: use the rules as a checklist before buying stock.

    Solo founders
  • eBay and Walmart resellers: use the same screening prompt with your own market's data.

    Shopify & ecommerce
  • Small retailers: screen new products to carry against sales and competition data.

    Local & service

Related

Similar tools

Other tools for this job, and how they differ. Chosen by our editors, never paid for.

  • ChatGPT

    The same two-prompt approach works with a custom GPT if you already pay for ChatGPT.

  • Keepa

    Price and sales-rank history for Amazon products, often used alongside SellerAmp to check a deal.

  • Jungle Scout

    Product research aimed more at private label than arbitrage.

“Light evidence” (grade D) means: A brief, early or in-progress claim. Treat it as an idea to test, not proof. How we grade. Spotted a mistake? Suggest a correction.