Agent context
ShipHero models
4 SQL models that turn the raw ShipHero 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
- 11Raw tables
- 11Staging
- 5Core
- 4Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Fulfillment by dayFulfilment throughput, shipping cost and on-time rate per warehouse per day.grain: day x shiphero_account x warehouse · 6 raw tables
- Order fulfillmentEvery order with when it shipped, whether it met its required ship date, what the labels cost and what the customer was charged for shipping.grain: one row per shiphero_account x order · 5 raw tables
- Product returns by monthUnits shipped and units returned per SKU per month, for return rates by product.grain: month x shiphero_account x account_id x sku · 5 raw tables
- Warehouse productivityPicks and packs per warehouse user per day, ShipHero's "picks per day" and "packs per day" reports side by side.grain: day x shiphero_account x warehouse x user · 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 ShipHero's own reports first. Each model's notes say what the synced data can and can't support.
Connect ShipHero.
Your agents start with context.
Sync ShipHero to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.