Agent context
Facebook Pages models
2 SQL models that turn the raw Facebook Pages 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
- 4Staging
- 2Core
- 2Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Page performance dailyThe Facebook Page Insights overview per Page per day: followers, new likes, views and viewers of the Page's content, engagement, Page visits and video views.grain: date_day x page_id · 2 raw tables
- Post performanceThe Posts list of Page Insights / Meta Business Suite: every post with its lifetime views, viewers, reactions, comments, shares, clicks and engagement rate.grain: one row per post · 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 Facebook Pages's own reports first. Each model's notes say what the synced data can and can't support.
Connect Facebook Pages.
Your agents start with context.
Sync Facebook Pages to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.