Agent context
Traede models
4 SQL models that turn the raw Traede 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
- 9Raw tables
- 9Staging
- 4Core
- 4Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Invoiced sales over timeInvoiced wholesale revenue per day, from booked Traede invoices.grain: day x traede_account x currency · 1 raw table
- Order bookEvery sales order line with what has been shipped and invoiced against it, and what is still open.grain: one row per traede_account x order x variant (an order line) · 5 raw tables
- Product salesInvoiced units, revenue, cost and gross margin per variant per day.grain: day x traede_account x currency x variant · 4 raw tables
- Production order statusEvery production order line with what has been received, what is still outstanding, and how far the supplier's dates have slipped.grain: one row per traede_account x production order line · 4 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 Traede's own reports first. Each model's notes say what the synced data can and can't support.
Connect Traede.
Your agents start with context.
Sync Traede to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.