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
- 4Raw tables
- 1Staging
- 4Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Ad ReportGenerates an ad report by joining data from various tables in the Google Ads integration. It retrieves information such as date, account ID and name, campaign name and ID, ad group name and ID, ad ID and name, ad status and type, display URL, final URLs, spend, impressions, clicks, CPC, CTR, CPM, and conversions. Additional columns can be manually specified if needed.1 raw table
- URL ReportGenerates a report for URL performance in Google Ads. It retrieves data from various tables, including ad stats, accounts, campaigns, ad groups, and ads. The template calculates metrics such as spend, impressions, clicks, CPC, CTR, CPM, and conversions. Additional columns can be specified manually if needed.grain: day x ad · 3 raw tables
- Ad stats by country monthlyGenerates monthly ad statistics by country, including spend, clicks, CPC, cost per conversion, CTR, conversions, conversion value, impressions, and interactions, using data from Google Ads. It groups the data by month and country criterion ID.grain: month x country criterion ID · 1 raw table
- Marketing Insights DashboardThis SQL template consolidates advertising data from multiple platforms, including Facebook, Google, LinkedIn, TikTok, Snapchat, and Pinterest, into a unified dataset. It aggregates metrics such as clicks, impressions, spend, and conversions, and calculates performance indicators like CTR, CPC, CPM, and conversion rate. The result is grouped by date, platform, account, campaign, and ad identifiers for comprehensive marketing insights.grain: day x platform x account x campaign x ad · 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 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.