Agent context
Monday.com models
3 SQL models that turn the raw Monday.com 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
- 3Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Board activityDaily activity per board, user and event type, from the monday activity log.grain: day (UTC) x board x user x event · 3 raw tables
- Item assignmentsWho is assigned to what: every person in every people column on every item.grain: item x people column x person · 4 raw tables
- Status changesEvery change to a status column, with the label before and after and how long the item sat in the previous label.grain: one row per status change event (item x status column x change time) · 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 Monday.com's own reports first. Each model's notes say what the synced data can and can't support.
Connect Monday.com.
Your agents start with context.
Sync Monday.com to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.