Agent context
Apple Ads models
2 SQL models that turn the raw Apple 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
- 2Raw tables
- 2Staging
- 3Core
- 2Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- App performance dailyDaily spend and results per promoted app, across all its campaigns: what an app's Apple Ads budget bought each day.grain: date_day x account_id x app_id · 2 raw tables
- Campaign performance dailyDaily campaign performance, the Apple Ads Campaigns view by day, with the rates Apple shows: TTR, average CPT, average CPM, cost per install and install rate.grain: date_day x account_id x campaign_id · 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 Apple Ads's own reports first. Each model's notes say what the synced data can and can't support.
Connect Apple Ads.
Your agents start with context.
Sync Apple Ads to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.