Agent context
Unleashed models
3 SQL models that turn the raw Unleashed 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
- 4Staging
- 3Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Open sales ordersSales orders placed but not yet completed: the order book, with how late each order is against its required date. A snapshot as of the last sync.grain: sales order · 1 raw table
- Sales marginRevenue, cost of goods and gross margin from completed sales orders, the numbers behind Unleashed's sales enquiry and gross margin reports.grain: completed date x warehouse x customer x product x line type · 3 raw tables
- Stock positionStock on hand, availability, value and slow movers per product, as of the last sync. Unleashed's Stock on Hand report with reorder flags.grain: product, all warehouses combined · 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 Unleashed's own reports first. Each model's notes say what the synced data can and can't support.
Connect Unleashed.
Your agents start with context.
Sync Unleashed to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.