Agent context
Gorgias models
5 SQL models that turn the raw Gorgias 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
- 6Core
- 5Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Agent performance by monthPer agent per month: tickets closed and how fast, messages sent, first responses given, and satisfaction on their tickets.grain: month x gorgias_account x agent · 3 raw tables
- Response times by monthFirst response time, resolution time, messages per ticket, one-touch and zero-touch rates and satisfaction for the tickets created in each month: the "Support performance" overview.grain: created month x gorgias_account x team x channel · 3 raw tables
- Ticket lifecycleOne row per ticket with its dimensions, first response and resolution times derived from the message log and close timestamp, message counts and CSAT.grain: gorgias_account x ticket · 3 raw tables
- Ticket volume by dayTickets created, closed and left open per day: the "Overview" volume charts.grain: day x gorgias_account x team x channel · 3 raw tables
- Voice calls by dayPhone calls handled by Gorgias Voice per day: volume, answered, voicemail and talk time, the core of the "Voice" statistics.grain: day x gorgias_account x direction x status · 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 Gorgias's own reports first. Each model's notes say what the synced data can and can't support.
Connect Gorgias.
Your agents start with context.
Sync Gorgias to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.