Agent context
Walmart Seller Center models
3 SQL models that turn the raw Walmart Seller Center 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
- 6Raw tables
- 7Staging
- 3Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Product sales over timeSales by SKU per order day, from the Orders API, reconciling to core.walmart.sales_over_time on net sales and units.grain: order day x seller x currency x ship node type x SKU · 5 raw tables
- Sales over timeSales over time for a Walmart Marketplace seller, from the Orders API: the sales equation per order day, with shipping and tax.grain: order day x seller x currency x ship node type · 5 raw tables
- Settlement ledgerWhat Walmart actually paid you: the settlement reconciliation file turned into a ledger, one row per order line and transaction type per payout.grain: settlement date x seller x posted date x purchase order x purchase order line x SKU x transaction type · 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 Walmart Seller Center's own reports first. Each model's notes say what the synced data can and can't support.
Connect Walmart Seller Center.
Your agents start with context.
Sync Walmart Seller Center to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.