Agent context
Netsuite models
4 SQL models that turn the raw Netsuite 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
- 4Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- AR AP agingOpen customer invoices and vendor bills, bucketed by days past due as of today. The document-level detail behind NetSuite's A/R Aging and A/P Aging reports.grain: transaction, one row per open invoice (CustInvc) or bill (VendBill) · 4 raw tables
- General ledgerEvery posting NetSuite made to the general ledger, one row per accounting line, with the account, its type and the line's subsidiary and dimensions.grain: transaction x transaction line x accounting book · 6 raw tables
- Profit and loss by monthNetSuite's Income Statement by month and account, built from the general ledger.grain: accounting book x subsidiary x month x account, income statement account types only, months with postings only · 6 raw tables
- Trial balanceMonth-end balance per account, per subsidiary and accounting book, built from the general ledger.grain: account x accounting book x subsidiary x month, from the first month the combination has a posting to the current month (or the last posted month, if later), so balances carry through months without activity · 6 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 Netsuite's own reports first. Each model's notes say what the synced data can and can't support.
Connect Netsuite.
Your agents start with context.
Sync Netsuite to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.