Agent context
Daisycon models
4 SQL models that turn the raw Daisycon 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
- 5Raw tables
- 5Staging
- 4Core
- 4Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Invoice costs monthlyInvoiced affiliate costs per month and invoice line type: what you actually pay Daisycon, split into commission, fees and whatever else the lines say.grain: invoice_month x advertiser_id x currency x line_code · 3 raw tables
- InvoicesWhat Daisycon has invoiced the advertiser, one row per invoice, with the line totals next to the header totals and how long each invoice took to pay.grain: advertiser_id x invoice_number · 3 raw tables
- Media performanceAffiliate results per media, Daisycon's statistics grouped by media: clicks, transactions by status, commission, revenue, and the rates affiliate managers steer on (conversion rate, approval rate, cost of sale, commission per click).grain: advertiser_id x media_id, totalled over the sync window · 2 raw tables
- Publisher performanceAffiliate results per publisher, Daisycon's statistics grouped by publisher: clicks, transactions by status, commission, revenue, and the rates affiliate managers steer on (conversion rate, approval rate, cost of sale, commission per click).grain: advertiser_id x publisher_id, totalled over the sync window · 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 Daisycon's own reports first. Each model's notes say what the synced data can and can't support.
Connect Daisycon.
Your agents start with context.
Sync Daisycon to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.