Developed a real-time AI-powered platform to detect and prevent toxic and abusive language in digital communication. • Detects harmful and abusive text in real-time using AI models • Handles obfuscated text patterns (e.g., h@te, !d!ot) for better accuracy • Built moderation system with admin dashboard for monitoring content • Designed backend APIs for real-time processing and response Focused on improving online safety by enabling intelligent and scalable content moderation systems. Tech: FastAPI, React, OpenRouter AI, Tailwind CSS