Agent context
eSmiley models
2 SQL models that turn the raw eSmiley 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
- 3Raw tables
- 3Staging
- 4Core
- 2Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Food waste by area monthMonthly food waste per account and top-level area, with each area's share of the account's waste and the change from the previous month.grain: month x account x area x currency · 3 raw tables
- Food waste dailyFood waste per day, account and registration point: weight, value and CO2. The figures behind eSmiley's dashboard, as a table.grain: registration date x account x registration point · 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 eSmiley's own reports first. Each model's notes say what the synced data can and can't support.
Connect eSmiley.
Your agents start with context.
Sync eSmiley to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.