Agent context
Toast Analytics models
4 SQL models that turn the raw Toast Analytics 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
- 5Raw tables
- 5Staging
- 4Core
- 4Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Daily salesToast's daily sales KPIs per restaurant: orders, guests, gross and net sales, discounts, refunds, voids, average order value and sales per labor hour.grain: business date x restaurant · 1 raw table
- Labor by jobLabor hours and cost per job per day, with each job's cost as a share of the restaurant's net sales that day (Toast's labor cost percentage, by job).grain: business date x restaurant x job · 2 raw tables
- Menu item performanceToast's Product Mix per menu item and day, with waste and each item's share of the restaurant's item sales.grain: business date x restaurant x menu item · 1 raw table
- PayoutsToast card payouts per settlement date: card payments, refunds, processing fees, withholdings and what landed in the bank, with the effective fee rate.grain: settled date x restaurant · 1 raw table
- 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 Toast Analytics's own reports first. Each model's notes say what the synced data can and can't support.
Connect Toast Analytics.
Your agents start with context.
Sync Toast Analytics to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.