Agent context
SevenRooms models
3 SQL models that turn the raw SevenRooms 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
- 3Raw tables
- 3Staging
- 3Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Booking lead timeHow far ahead guests book, by who took the booking and the reservation type.grain: reservation date x venue x booked by x reservation type x lead time band · 1 raw table
- Covers by dayReservations, covers, cancellations, no-shows and spend per day, venue and shift. The daily covers report a SevenRooms venue runs on.grain: reservation date x venue x shift category · 2 raw tables
- Guest feedbackGuest feedback scores per venue and visit date: overall, food, drinks, service and ambience.grain: reservation date x venue x feedback type · 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 SevenRooms's own reports first. Each model's notes say what the synced data can and can't support.
Connect SevenRooms.
Your agents start with context.
Sync SevenRooms to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.