Agent context
LinkedIn Company Pages models
3 SQL models that turn the raw LinkedIn Company 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
- 10Raw tables
- 10Staging
- 3Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Follower demographicsWho follows each LinkedIn Page: the follower breakdowns from the Followers section of Page analytics (seniority, job function, industry, country, location, company size, employees), in one long table.grain: organization_id x facet x segment_id · 8 raw tables
- Follower growth dailyThe Followers section of LinkedIn Page analytics: new followers per day, split organic and paid, with an estimated follower total for each day.grain: date_day x organization_id · 2 raw tables
- Page performance dailyThe Updates (content) section of LinkedIn Page analytics: organic impressions, reach and engagement across all of a Page's posts, per day.grain: date_day x organization_id · 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 LinkedIn Company Pages's own reports first. Each model's notes say what the synced data can and can't support.
Connect LinkedIn Company Pages.
Your agents start with context.
Sync LinkedIn Company Pages to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.