Agent context
Zendesk models
4 SQL models that turn the raw Zendesk 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
- 5Core
- 4Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Agent performance by monthSolved tickets, reply and resolution times and CSAT per agent per month: the "Agent activity" style leaderboard.grain: month x zendesk_account x assignee · 4 raw tables
- Response times by monthFirst reply time, full resolution time, requester wait time and CSAT for the tickets solved in each month: the "Efficiency" and "Satisfaction" views of Zendesk's Support dashboard.grain: month x zendesk_account x group x channel · 4 raw tables
- Ticket lifecycleOne row per ticket with its dimensions, Zendesk's own time metrics and CSAT.grain: zendesk_account x ticket · 4 raw tables
- Ticket volume by dayTickets created, solved and left unsolved per day: Zendesk's "Tickets" tab.grain: day x zendesk_account x group x channel · 4 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 Zendesk's own reports first. Each model's notes say what the synced data can and can't support.
Connect Zendesk.
Your agents start with context.
Sync Zendesk to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.