LLM-Augmented Decision Support Tool
AI Safety Evaluation System, Regional Champion, Data4Good
Built a deployable LLM-powered safety evaluation system for AI-generated educational content. Originally developed for the Data4Good competition as Regional...
Competition Context: This demo extends a DataCamp analytics project and applies the full LLM-as-a-Judge architecture developed during the Data4Good competition, where our team The White Hatters were Regional Champions and advanced to the National Championship at UW Foster.
To enable LLM features, users must input their own API key using OpenAI or Gemini.