Agent context
Amazon Selling Partner API models
6 SQL models that turn the raw Amazon Selling Partner API tables into the reports people ask about. Deploy them in Weld and your agent queries the definitions behind every number.
How the set is built
- 10Raw tables
- 11Staging
- 8Core
- 6Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- ASIN profitabilityAmazon's fees, returns and your COGS.grain: day x seller x marketplace x ASIN x SKU · 7 raw tables
- Inventory healthand how much of it is dead.grain: seller x marketplace x SKU · 5 raw tables
- Product sales over timebased, so returns land on the day they happened.grain: day x seller x marketplace x ASIN x SKU x row type · 4 raw tables
- Sales over timeTraffic by date" page, and puts all three revenue definitions on one row.grain: day x seller x marketplace · 1 raw table
- Settlement ledgerGrain: settlement date x seller x marketplace x order x SKU. Currency: the settlement's own.grain: settlement date x seller x marketplace x order x SKU · 1 raw table
- Traffic and conversionconversion, at the grain each metric is actually measured on.grain: day x seller x marketplace x child ASIN · 2 raw tables
- Weld or dbt
- The same SQL in both dialects. Sync the folder with GitHub Sync, or copy the dbt models into your project.
- Check before you rely on it
- Reconcile a month against Amazon Selling Partner API's own reports first. Each model's notes say what the synced data can and can't support.
Connect Amazon Selling Partner API.
Your agents start with context.
Sync Amazon Selling Partner API to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.