Agent context
Go HighLevel models
3 SQL models that turn the raw Go HighLevel 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.
- Opportunity outcomes monthlyWin rate and won value by the month deals were created, per pipeline and lead source: the cohort view behind HighLevel's opportunity and lead source reports.grain: one row per month created x location x pipeline x source · 2 raw tables
- Payments dailyMoney taken through HighLevel Payments per day: the Transactions view in Payments, summed. Amount, refunds, net, and how many customers paid.grain: one row per day (UTC, transaction created) x location x currency x source type x status · 1 raw table
- Pipeline snapshotThe HighLevel Opportunities board as numbers: how many deals and how much value sit in each stage of each pipeline right now, and how long they have been there.grain: one row per location x pipeline x stage x status, as of the last sync · 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 Go HighLevel's own reports first. Each model's notes say what the synced data can and can't support.
Connect Go HighLevel.
Your agents start with context.
Sync Go HighLevel to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.