Agent context
Freshdesk models
5 SQL models that turn the raw Freshdesk 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
- 6Raw tables
- 5Staging
- 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: replies sent, tickets they gave the first response on and how fast, tickets currently assigned to them, and the CSAT they received.grain: month x freshdesk_account x agent · 6 raw tables
- CSAT by monthCustomer satisfaction per month, by the group and agent the response was given for: Freshdesk's "Satisfaction survey" report.grain: response month x freshdesk_account x group x agent · 5 raw tables
- First response by monthFirst response time (mean and median, calendar minutes) and first-response SLA attainment for the tickets created in each month: the "First response time" and "SLA" panels of Freshdesk's Helpdesk In-depth report.grain: created month x freshdesk_account x group x channel · 6 raw tables
- Ticket lifecycleOne row per ticket with its dimensions, a first response time derived from the conversation log, reply counts and the latest CSAT answer.grain: freshdesk_account x ticket · 6 raw tables
- Ticket volume by dayTickets created, tickets first responded to, and reply traffic per day.grain: day x freshdesk_account x group x channel · 6 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 Freshdesk's own reports first. Each model's notes say what the synced data can and can't support.
Connect Freshdesk.
Your agents start with context.
Sync Freshdesk to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.