Agent context
Pinterest Ads models
3 SQL models that turn the raw Pinterest Ads 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
- 4Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Ad performance dailyDaily delivery and results per ad (promoted Pin), the Ads Manager "Ads" tab by day.grain: date_day x account_id x ad_id · 5 raw tables
- Campaign country performance dailyDaily campaign performance by the viewer's country, the Ads Manager country breakdown.grain: date_day x account_id x campaign_id x country_code · 3 raw tables
- Campaign performance dailyDaily campaign performance with the rates Ads Manager shows: CTR, CPC, CPM, cost per conversion and checkout ROAS.grain: date_day x account_id x campaign_id · 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 Pinterest Ads's own reports first. Each model's notes say what the synced data can and can't support.
Connect Pinterest Ads.
Your agents start with context.
Sync Pinterest Ads to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.