Agent context
Younium models
3 SQL models that turn the raw Younium 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
- 4Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Account cmrrCurrent committed MRR, ACV and TCV per customer account, as Younium computes them, with each account's share of total CMRR.grain: one row per account, as of the last sync · 1 raw table
- MRR movementsThe CMRR bridge: opening committed MRR, new customers, expansion, contraction, churn, reactivation, closing CMRR. Recreates the movement breakdown of Younium's CMRR reporting from its bookings.grain: month · 3 raw tables
- Subscription MRR movementsYounium's CMRR movements per subscription per month: the drill-down behind the monthly CMRR bridge.grain: month x order number · 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 Younium's own reports first. Each model's notes say what the synced data can and can't support.
Connect Younium.
Your agents start with context.
Sync Younium to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.