Agent context
Gong models
4 SQL models that turn the raw Gong 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
- 9Raw tables
- 9Staging
- 5Core
- 4Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- CallsEvery Gong call with its rep, participants, talk time, Gong's interaction statistics and the CRM records it is linked to, on one row.grain: one row per gong_account x call · 6 raw tables
- Rep call activity by dayCalls per rep per day: how many, how long, external versus internal, inbound versus outbound. The activity half of Gong's Team Stats.grain: day x gong_account x rep (primary user) · 6 raw tables
- Rep interaction stats by weekGong's Interaction stats per rep per week: talk ratio, longest monologue, longest customer story, interactivity, patience and question rate.grain: ISO week (starting Monday) x gong_account x rep (primary user) · 6 raw tables
- Scorecard scores by repCoaching scorecards per rep per month: how many calls were reviewed, by how many reviewers, and the average scores the rep received.grain: review month x gong_account x reviewed rep x scorecard · 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 Gong's own reports first. Each model's notes say what the synced data can and can't support.
Connect Gong.
Your agents start with context.
Sync Gong to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.