Agent context
Grin models
3 SQL models that turn the raw Grin 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
- 11Raw tables
- 11Staging
- 4Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Campaign performanceOne row per campaign: the creator funnel, the content it produced, the sales it drove and what it cost. Grin's campaign report, with the costs on the same row.grain: one row per grin_account x campaign · 11 raw tables
- Conversions by dayAffiliate and discount-code sales over time, per campaign: orders, revenue and commission on the day Grin recorded the conversion.grain: day x grin_account x campaign x conversion type x currency · 2 raw tables
- Creator campaign performanceWhat each creator did on each campaign, and what it cost and returned: proposal status, content posted and its reach, attributed sales, commissions, what is owed to them and what their seeded products cost.grain: one row per grin_account x campaign x creator (contact) · 11 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 Grin's own reports first. Each model's notes say what the synced data can and can't support.
Connect Grin.
Your agents start with context.
Sync Grin to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.