Agent context
E-conomic models
2 SQL models that turn the raw E-conomic 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
- 4Raw tables
- 2Core
- 2Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Invoice line itemsRetrieves invoice line items from the economic integration. It combines data from the "booked_invoices" table and the "products" and "customers" tables to provide information such as the customer name, invoice details, product details, and order by date in descending order.3 raw tables
- Order itemsRetrieves order items from the "economic" integration. It combines data from the "orders" table and the "customers" table, joining them based on the customer ID. The result is sorted in descending order by date.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 E-conomic's own reports first. Each model's notes say what the synced data can and can't support.
Connect E-conomic.
Your agents start with context.
Sync E-conomic to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.