Agent context
Amazon Vendor Central API models
4 SQL models that turn the raw Amazon Vendor Central 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
- 5Raw tables
- 5Staging
- 4Core
- 4Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Forecast vs actualsshipped, per ASIN per forecast window.grain: forecast window x vendor x marketplace x ASIN · 2 raw tables
- Inventory healthwith sales velocity attached so the numbers mean something.grain: day x vendor x marketplace x distributor view x selling program x ASIN · 2 raw tables
- Sales by ASINASIN per day. The vendor equivalent of a product performance report.grain: day x vendor x marketplace x distributor view x selling program x ASIN · 3 raw tables
- Sales over timethree revenue definitions separated and Amazon's markup made explicit.grain: day x vendor x marketplace x distributor view x selling program · 1 raw table
- 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 Vendor Central API's own reports first. Each model's notes say what the synced data can and can't support.
Connect Amazon Vendor Central API.
Your agents start with context.
Sync Amazon Vendor Central API to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.