Agent context
Calendly models
3 SQL models that turn the raw Calendly 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
- 4Staging
- 4Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Bookings by sourceWhere bookings come from and what became of them: new bookings by UTM source, medium and campaign, followed through any reschedules to their final outcome.grain: booking month x calendly_account x utm_source x utm_medium x utm_campaign x event type · 2 raw tables
- Meetings by dayCalendly's "Scheduled events" analytics per host and event type, as a daily time series: what was booked, what took place, what was canceled or no-showed.grain: day x calendly_account x host x event type · 3 raw tables
- Scheduled eventsEvery scheduled meeting, classified, with its hosts, invitee outcomes and booking lead time on one row.grain: one row per calendly_account x scheduled event · 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 Calendly's own reports first. Each model's notes say what the synced data can and can't support.
Connect Calendly.
Your agents start with context.
Sync Calendly to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.