Agent context
Microsoft Ads models
4 SQL models that turn the raw Microsoft 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
- 7Raw tables
- 7Staging
- 5Core
- 4Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Account performance dailyDaily totals per account, the Microsoft Advertising "Accounts" view by day, with the account's time zone.grain: date_day x account_id · 3 raw tables
- Ad group performance dailyDaily ad group performance, the Microsoft Advertising "Ad groups" report by day.grain: date_day x account_id x ad_group_id · 4 raw tables
- Ad performance dailyDaily delivery and conversions per ad, the Microsoft Advertising "Ads" report by day.grain: date_day x account_id x ad_id · 5 raw tables
- Campaign performance dailyDaily campaign performance with the rates the Microsoft Advertising UI shows: CTR, CPC, CPM, cost per conversion and ROAS.grain: date_day x account_id x campaign_id · 3 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 Microsoft Ads's own reports first. Each model's notes say what the synced data can and can't support.
Connect Microsoft Ads.
Your agents start with context.
Sync Microsoft Ads to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.