Agent context
Amazon Attribution models
3 SQL models that turn the raw Amazon Attribution 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
- 5Raw tables
- 5Staging
- 3Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Campaign performance dailyDaily campaign results as the Amazon Attribution console shows them: click-throughs, detail page views, add to carts, purchases and sales, promoted and total, with the funnel rates and the Brand Referral Bonus.grain: date_day x profile_id x advertiser x campaign_id · 3 raw tables
- Creative performance dailyDaily click-throughs and Amazon conversions per Attribution creative: what your off-Amazon traffic (search, social, email, influencers) did once it reached Amazon.grain: date_day x profile_id x advertiser x campaign_id x ad_group_id x ad_id · 3 raw tables
- Product performance dailyDaily Amazon Attribution results per product: which ASINs your off-Amazon traffic sold, how much of it was brand halo, and how many buyers were new to the brand.grain: date_day x profile_id x advertiser x campaign_id x ad_group_id x asin x product_conversion_type · 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 Amazon Attribution's own reports first. Each model's notes say what the synced data can and can't support.
Connect Amazon Attribution.
Your agents start with context.
Sync Amazon Attribution to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.