Agent context
Qualtrics models
4 SQL models that turn the raw Qualtrics 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
- 6Staging
- 5Core
- 4Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Answer detailEvery answer to every question, in long format, with question and matrix-row text attached.grain: qualtrics_account x response x question x sub question x response_index · 5 raw tables
- Distribution performanceEmail distribution funnel: sent, bounced, opened, started, finished, and the rates between them, per distribution.grain: qualtrics_account x distribution · 2 raw tables
- NPS by monthNet Promoter Score per NPS question per month.grain: month x qualtrics_account x survey x question · 5 raw tables
- Response volumeRecorded responses per survey per day, finished and unfinished, with duration.grain: day x qualtrics_account x survey · 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 Qualtrics's own reports first. Each model's notes say what the synced data can and can't support.
Connect Qualtrics.
Your agents start with context.
Sync Qualtrics to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.