Agent context
Chargebee models
3 SQL models that turn the raw Chargebee 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
- 7Raw tables
- 7Staging
- 5Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Billing by monthWhat was invoiced, credited, paid and written off, by month. The cash-side companion to the MRR models, and the closest match to Chargebee's invoice and credit note exports totalled by month.grain: month x currency · 3 raw tables
- MRR by customer monthMRR per customer per month, and the movement that took it there: new, expansion, contraction, churn or reactivation.grain: month x customer x currency · 7 raw tables
- MRR movementsThe MRR bridge by month: opening MRR, new, expansion, contraction, churn, reactivation, closing MRR, plus customer counts. Chargebee's "MRR movements" view, rebuilt from invoices.grain: month x currency · 7 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 Chargebee's own reports first. Each model's notes say what the synced data can and can't support.
Connect Chargebee.
Your agents start with context.
Sync Chargebee to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.