Agent context
Medallia models
4 SQL models that turn the raw Medallia 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 on every feedback record, in long format, with the question name, option label and numeric score resolved.grain: medallia_account x feedback record x question x position · 5 raw tables
- Feedback volumeFeedback records created and responses received per unit per day, with response rate.grain: day x medallia_account x unit · 2 raw tables
- NPS by unit monthNet Promoter Score per unit per month for your likelihood-to-recommend questions.grain: month x medallia_account x unit x question · 5 raw tables
- Topic volumeHow often each text analytics topic comes up in comments, per unit per month.grain: month x medallia_account x unit x topic · 3 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 Medallia's own reports first. Each model's notes say what the synced data can and can't support.
Connect Medallia.
Your agents start with context.
Sync Medallia to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.