Agent context
Zoho CRM models
4 SQL models that turn the raw Zoho CRM 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
- 8Raw tables
- 8Staging
- 5Core
- 4Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Zoho CRM Deal PipelineEvery Zoho deal classified as open, won or lost, with its account and owner joined on. Zoho ships no is_won flag, so the outcome is derived from the stage string - and the model shows you which stages fell through.grain: one row per deal · 3 raw tables
- Zoho CRM Deal Flow by MonthDeals created, won and lost per month per rep, with win rate by count and by value. Built on a month spine so a quiet month returns zeros instead of vanishing from the chart.grain: month x owner · 3 raw tables
- Zoho CRM Rep ActivityCalls, meetings and tasks logged per rep per day. Activity is per rep and never per deal - Zoho's What_Id and Who_Id are not synced, so the link to a deal does not exist in this connector.grain: day x owner · 4 raw tables
- Zoho CRM Account 360One row per account: its people, its open and won pipeline, and when anyone last wrote anything down. Flags accounts sitting on open pipeline with no note in 90 days.grain: account · 5 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 Zoho CRM's own reports first. Each model's notes say what the synced data can and can't support.
Connect Zoho CRM.
Your agents start with context.
Sync Zoho CRM to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.