Agent context
OpenWeather models
2 SQL models that turn the raw OpenWeather 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
- 2Core
- 2Analytics
Staging cleans each raw table once, core holds the logic, and analytics is the table dashboards and agents read.
- Daily forecastThe 3-hourly forecast rolled up to local days per location: the next five days of weather in the same shape as core.openweather.daily_weather, for staffing and ordering decisions.grain: local date x location (city, country) · 2 raw tables
- Daily weatherDaily weather per location, shaped for joining to sales, covers or footfall on date: temperatures, rain, wind, and a few plain-language flags.grain: date x location (city, country) · 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 OpenWeather's own reports first. Each model's notes say what the synced data can and can't support.
Connect OpenWeather.
Your agents start with context.
Sync OpenWeather to your warehouse, deploy these models, and query them from Claude, Cursor or ChatGPT over MCP. Free for 14 days, no credit card.