Agent context
Google My Business models
3 SQL models that turn the raw Google My Business 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
- 3Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Location performance dailyThe Business Profile Performance view per location per day: how often the profile was shown, on which surface, and what people did with it.grain: date_day x location_id · 2 raw tables
- Reviews monthlyReview volume, rating and response per location per month, plus the running review count and average rating as of each month end.grain: month x location_id, every month from a location's first review to the current month (months without reviews are kept so the running figures are continuous) · 2 raw tables
- Search keywords monthlyThe search terms people used to find each location on Google Search and Maps, per month, ranked. The "Searches" panel of the Performance view.grain: month x location_id x search_keyword · 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 Google My Business's own reports first. Each model's notes say what the synced data can and can't support.
Connect Google My Business.
Your agents start with context.
Sync Google My Business to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.