Summary
Amazon operations platform that analyzes settlement-based SKU profitability and supports approval-controlled advertising and catalog changes.
About
AgentXray applies settlement-level cost data to Amazon seller operations, linking SKU profitability with advertising decisions and AI-assisted changes subject to user approval.
AgentXray analyzes Amazon settlement reports to calculate per-SKU profit using fees actually deducted, including referral, FBA, storage, and refund fees. It uses these costs to determine a break-even ACoS for each advertising campaign. Sellers can connect their own Claude or ChatGPT through MCP to ask operational questions and draft changes to bids, budgets, listings, and prices. Changes are not sent to Amazon until the user approves them in a browser. A live demonstration using sample data is available without an Amazon account.
Key Features
Reads Amazon settlement reports to calculate per-SKU profit from fees actually deducted.
Accounts for referral, FBA, storage, and refund fees.
Calculates a break-even ACoS for each advertising campaign using settlement-based costs.
Connects a user's Claude or ChatGPT through MCP for operational questions and draft changes.
Requires browser approval before drafted bid, budget, listing, or price changes reach Amazon.
Real-World Use Cases
SKU-level profitability analysis
Use actual settlement deductions to assess product profitability rather than relying on estimated fees.
Advertising break-even assessment
Compare campaign ACoS with a break-even threshold calculated from the relevant settlement-based costs.
AI-assisted account operations
Ask a connected Claude or ChatGPT account questions and prepare proposed changes to bids, budgets, listings, or prices for review.
Business Opportunities
Profitability-led Amazon advertising management
Problem: Amazon sellers may make advertising decisions using estimated costs that do not reflect fees actually deducted from settlements.
Solution: Use settlement-based SKU costs and campaign break-even ACoS to inform advertising reviews and proposed bid or budget changes.
Estimated ROI: Potentially improves advertising cost control and decision quality; financial returns depend on account data, campaign performance, and implementation.
Execution: Review settlement-derived profitability alongside campaign break-even ACoS, use the connected AI assistant to draft adjustments, and approve changes in the browser before they are applied.
Settlement-based catalog and pricing review
Problem: Product listing and pricing decisions can be made without a clear view of actual per-SKU fees and net profitability.
Solution: Use settlement-derived profit data to inform AI-drafted listing and price changes, with user approval before changes reach Amazon.
Estimated ROI: Potentially supports better-informed pricing and catalog decisions; measurable impact depends on product demand, margins, and execution.
Execution: Identify SKUs with relevant profitability concerns, ask the connected AI assistant to draft listing or price changes, and review each proposal before approval.