Agent context
Adobe Commerce models
3 SQL models that turn the raw Adobe Commerce 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
- 5Staging
- 3Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Inventory coverStock on hand against recent sales: how many days the current stock lasts at the last 30 days' pace. The admin has a Low Stock report; this adds the rate of sale it lacks.grain: store x product x stock x website, as of the last sync · 4 raw tables
- Product sales over timeProduct-level sales with the same equation as sales_over_time, plus cost of goods where Magento recorded a cost. Covers what the admin's Products Ordered and Bestsellers reports show, with money attached.grain: day x store x order x item, top-level items only · 2 raw tables
- Sales over timeRecreates the Adobe Commerce admin "Orders" sales report (Reports > Sales > Orders: orders, sales items, sales total, invoiced, refunded, sales tax, sales shipping, sales discount, canceled) and adds a sales equation on top.grain: day x store x order · 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 Adobe Commerce's own reports first. Each model's notes say what the synced data can and can't support.
Connect Adobe Commerce.
Your agents start with context.
Sync Adobe Commerce to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.