Agent context
QRFY models
3 SQL models that turn the raw QRFY 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
- 2Raw tables
- 2Staging
- 3Core
- 3Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Qr codesEvery QR code in the account with QRFY's lifetime scan counter: the My QR Codes list.grain: one row per QR code, as of the last sync · 1 raw table
- Scans by location and deviceWhere and on what devices codes are scanned: QRFY's country, city and operating-system breakdowns, per code per month.grain: one row per month (UTC) x QR code (scan_url) x country x city x operating system · 1 raw table
- Scans dailyScans per QR code per day: QRFY's Statistics chart, total and unique scans, by code.grain: one row per day (UTC) x QR code (scan_url) · 1 raw table
- 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 QRFY's own reports first. Each model's notes say what the synced data can and can't support.
Connect QRFY.
Your agents start with context.
Sync QRFY to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.