Weather-based staffing automation
BUSINESS PROBLEM
Operations managers rebuild the same weather-versus-staffing judgement call every morning.
WHAT I BUILT
A workflow that pulls the daily forecast and branches into one of two analysis prompts depending on whether conditions are severe or standard, delivering a tailored staffing and operations recommendation each morning.
RESULT
Demonstrates conditional branching into distinct prompts based on external data. Built and tested against live forecast data.
MY ROLE
- Workflow design
- Prompt engineering
- Evaluation & testing
HOW IT WORKS
- 01A scheduled step pulls the day's forecast for a configured location.
- 02A condition check routes to a severe-weather prompt or a standard-conditions prompt.
- 03The resulting recommendation is emailed to a configured inbox each morning.
TECHNICAL IMPLEMENTATION
Zapier workflow with an OpenWeather fetch, a path split on weather condition, and two separately written Gemini prompts.
LIMITATIONS
- Recommendations are advisory text with no connection to a scheduling system.
- The severe-versus-standard split is a binary rule, which is coarser than real operational judgement.