Agent context
Mailchimp models
3 SQL models that turn the raw Mailchimp 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
- 9Raw tables
- 9Staging
- 3Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Audience growth dailyMailchimp's audience growth and activity, per audience per day: new subscribers, unsubscribes and other changes, plus the sending activity on that day.grain: one row per day x audience (list) · 2 raw tables
- Audience summaryOne row per audience: Mailchimp's own contact counts next to the same counts rebuilt from the synced members, plus member quality signals.grain: one row per audience (list), as of the last sync · 2 raw tables
- Campaign performanceMailchimp's campaign report, one row per sent campaign: who it went to, how much was delivered, opened and clicked, who unsubscribed, and attributed e-commerce revenue.grain: one row per campaign (sent campaigns only) · 6 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 Mailchimp's own reports first. Each model's notes say what the synced data can and can't support.
Connect Mailchimp.
Your agents start with context.
Sync Mailchimp to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.