Agent context
Notion models
3 SQL models that turn the raw Notion 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
- 4Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Database pagesEvery page that is a row in a Notion database, with its title, its status, who created it and how long since anyone touched it.grain: page · 4 raw tables
- Pages createdNew database rows per day, data source and creator: how fast each tracker, CRM or request log in Notion is filling up.grain: creation date (UTC) x data source x creator · 4 raw tables
- Status breakdownHow many pages sit in each status of each database, and how stale they are. The board view of a Notion database, as a table. A snapshot as of the last sync.grain: data source x status property x status value · 4 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 Notion's own reports first. Each model's notes say what the synced data can and can't support.
Connect Notion.
Your agents start with context.
Sync Notion to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.