Agent context
Workday Financial Management models
4 SQL models that turn the raw Workday Financial Management 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
- 6Raw tables
- 6Staging
- 5Core
- 4Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- AR agingOpen customer invoices, bucketed by age as of today.grain: one row per customer invoice with an amount due · 2 raw tables
- General ledgerEvery line of every posted journal entry, with its ledger account and the account's classification.grain: journal entry x line index · 5 raw tables
- Profit and loss by monthIncome statement by month and ledger account, from posted journal lines.grain: company x ledger x book code x account set x ledger account x month, Revenue and Expense accounts only, months with postings only · 5 raw tables
- Trial balanceMonth-end balance per ledger account, per company, ledger and book code, built from posted journal lines.grain: company x ledger x book code x account set x ledger account x month, from the first month with a posting to the current month (or the last posted month, if later), so balances carry through months without activity · 5 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 Workday Financial Management's own reports first. Each model's notes say what the synced data can and can't support.
Connect Workday Financial Management.
Your agents start with context.
Sync Workday Financial Management to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.