Agent context
Auth0 models
4 SQL models that turn the raw Auth0 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
- 4Raw tables
- 4Staging
- 4Core
- 4Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Logins by applicationLogin and signup activity per application and connection, from the tenant log. Answers "which app is failing logins" and "which connection do people sign up with", which Auth0's Dashboard only shows tenant-wide.grain: one row per UTC day x client (application) x connection · 1 raw table
- Monthly active usersMonthly active users and how many of them were new that month.grain: one row per calendar month (UTC) · 2 raw tables
- Tenant activity dailyThe Auth0 Dashboard, by day: logins, signups and leaked-password detections as Auth0 counts them, next to the same activity rebuilt from the tenant log, with failures broken down by reason and daily active users.grain: one row per UTC day · 2 raw tables
- User signupsNew users per day by how they signed up, and how many went on to verify their email and come back. The signup side of Auth0's Users page, as a time series.grain: one row per UTC signup day x connection x provider · 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 Auth0's own reports first. Each model's notes say what the synced data can and can't support.
Connect Auth0.
Your agents start with context.
Sync Auth0 to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.