Agent context
Paypal models
3 SQL models that turn the raw Paypal 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
- 2Raw tables
- 2Staging
- 4Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Balance reconciliationTies the transaction history to the balance PayPal reports today.grain: PayPal account x currency · 2 raw tables
- Daily balance activityDaily settlement summary: what moved the PayPal balance each day, by currency. Recreates the totals of PayPal's balance and activity reports.grain: day (UTC) x currency · 1 raw table
- TransactionsEvery PayPal transaction record, classified: the itemised activity behind PayPal's activity download and balance report.grain: transaction id x event code · 1 raw table
- 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 Paypal's own reports first. Each model's notes say what the synced data can and can't support.
Connect Paypal.
Your agents start with context.
Sync Paypal to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.