Agent context
Foreign Exchange Rates models
2 SQL models that turn the raw Foreign Exchange Rates 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
- 1Raw tables
- 1Staging
- 3Core
- 2Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Daily base ratesGap-filled daily rates against the base currency: every calendar day from a currency's first rate up to today, with the last known rate carried forward over any day that has none (a missed sync, a currency that stopped quoting, or today when the sync has not run yet).grain: date x base currency x quote currency · 1 raw table
- Daily ratesThe conversion table other models join to. Every day, every pair of currencies the connector quotes, gap-filled, including the identity pair (EUR to EUR = 1) so a join never has to special-case amounts already in the target currency.grain: date x from_currency x to_currency · 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 Foreign Exchange Rates's own reports first. Each model's notes say what the synced data can and can't support.
Connect Foreign Exchange Rates.
Your agents start with context.
Sync Foreign Exchange Rates to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.