Agent context
Apple App Store models
5 SQL models that turn the raw Apple App Store 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
- 6Core
- 5Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Downloads and deletionsInstalls and deletions by type, the Installations and Deletions view of App Analytics: first-time downloads, redownloads, updates, restores and deletions.grain: one row per day x app x territory x source type x device · 1 raw table
- Product page conversionThe App Store funnel: impressions, product page views, taps on Get, and the downloads that followed, by where people found the app. App Analytics' Sources view, with conversion recomputed at any grain.grain: one row per day x app x territory x source type x device · 2 raw tables
- Ratings and reviewsWritten reviews per day and territory: how many, average stars, how many were negative, and how many you answered.grain: one row per review day (UTC) x app x territory (three-letter code) · 1 raw table
- Sales and proceedsUnits, customer sales and estimated developer proceeds per app and product, the Sales and Trends view of App Store Connect.grain: one row per day x app SKU x product (Apple ID) x country x product category x customer currency x proceeds currency · 1 raw table
- Usage and stabilitySessions, time in app and crashes per app version: App Analytics' Usage and Crashes views side by side, so a release that crashes more per session shows up the day it ships.grain: one row per day x app x app version x device · 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 App Store's own reports first. Each model's notes say what the synced data can and can't support.
Connect Apple App Store.
Your agents start with context.
Sync Apple App Store to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.