Agent context
AppLovin models
2 SQL models that turn the raw AppLovin 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
- 2Core
- 2Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Ad performance dailyDaily delivery, installs and day-7 cohort revenue per creative set, the AppLovin advertiser report by campaign and creative set.grain: date_day x campaign_id x creative set (ad_id) · 1 raw table
- Campaign performance dailyDaily campaign performance with the rates AppLovin shows: CTR, CPC, CPM, cost per install (CPI), install rate and day-0 and day-7 ROAS.grain: date_day x campaign_id · 1 raw table
- 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 AppLovin's own reports first. Each model's notes say what the synced data can and can't support.
Connect AppLovin.
Your agents start with context.
Sync AppLovin to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.