Agent context
Cargoson models
3 SQL models that turn the raw Cargoson 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
- 2Raw tables
- 2Staging
- 4Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Carrier costs by monthShipments, freight spend, weight moved and delivery performance per carrier and service, per month.grain: month x cargoson_account x carrier_name x service_name x freight_currency · 2 raw tables
- Lane costsWhat it costs to move goods on each lane, by carrier: the table you take into a freight tender.grain: cargoson_account x collection_country x delivery_country x carrier_name x freight_type x freight_currency · 2 raw tables
- ShipmentsEvery booking as a shipment: lane, carrier, service, agreed freight price, goods weight, and how its transit went against the carrier's estimate.grain: one row per cargoson_account x booking_reference · 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 Cargoson's own reports first. Each model's notes say what the synced data can and can't support.
Connect Cargoson.
Your agents start with context.
Sync Cargoson to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.