Agent context
Tiktok Shop (Seller) models
4 SQL models that turn the raw Tiktok Shop (Seller) 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
- 7Raw tables
- 8Staging
- 4Core
- 4Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Product sales over timeSales by product and SKU over time, event-based, and reconciling to core.tiktok_shop.sales_over_time on net_sales and units.grain: day x account x shop x currency x product x SKU x row type, where row type is SALE, CANCELLATION or RETURN · 4 raw tables
- Sales over timeSales over time for a TikTok shop: the sales equation per day, with shipping and tax, built from orders and returns.grain: day x account x shop x currency x row type (SALE, CANCELLATION, RETURN) · 4 raw tables
- Settlement ledgerWhat TikTok actually paid you: every settlement transaction, with its revenue, fees and shipping cost, on the statement it was paid in.grain: statement x account x shop x transaction · 3 raw tables
- Shop performanceTikTok's own shop analytics per day, on a continuous date spine, with the ratios Seller Center shows recomputed from their parts.grain: day x account x shop · 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 Tiktok Shop (Seller)'s own reports first. Each model's notes say what the synced data can and can't support.
Connect Tiktok Shop (Seller).
Your agents start with context.
Sync Tiktok Shop (Seller) to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.