Agent context
Google Ads models
4 SQL models that turn the raw Google 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
- 8Raw tables
- 8Staging
- 5Core
- 4Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Ad performance dailyDaily delivery and conversions per ad, the Google Ads "Ads" view by day.grain: date_day x account_id x ad_id (ad_group_id is carried in the key as well, because Google identifies an ad by ad group and ad ID together) · 5 raw tables
- Campaign performance dailyDaily campaign performance with the rates the Google Ads UI shows: CTR, CPC, CPM, cost per conversion and ROAS.grain: date_day x account_id x campaign_id · 3 raw tables
- Country performance dailyDaily campaign performance by country, Google's "Locations > user locations" report with names attached.grain: date_day x account_id x campaign_id x country_criterion_id x location_type · 4 raw tables
- Landing page performance dailyDaily spend, clicks and conversions per landing page, so ad traffic can be set against sessions and orders in web analytics.grain: date_day x account_id x campaign_id x landing_page · 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 Google Ads's own reports first. Each model's notes say what the synced data can and can't support.
Connect Google Ads.
Your agents start with context.
Sync Google Ads to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.