Agent context
Klarna models
3 SQL models that turn the raw Klarna 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
- 3Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Daily settlement activitySales, returns, fees and the rest of the settlement ledger, per day.grain: day x klarna_account x merchant_id x currency_code · 1 raw table
- Fees by typeWhat Klarna charged, broken down by fee type, per month, with the effective rate against that month's sales.grain: month x klarna_account x merchant_id x currency_code x transaction_type x detailed_type · 1 raw table
- Payout reconciliationEvery Klarna payout, Klarna's own breakdown of it, and whether the synced transactions add up to that breakdown.grain: klarna_account x merchant_id x payout (payment_reference) · 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 Klarna's own reports first. Each model's notes say what the synced data can and can't support.
Connect Klarna.
Your agents start with context.
Sync Klarna to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.