Care Guard

CareGuard is a multi-agent AI system designed for workplace psychosocial case management. It helps HR teams efficiently handle sensitive employee wellbeing incidents by orchestrating six specialized AI agents that work together to: Triage and classify cases Assess psychosocial, legal, and retaliation risks Ensure compliance with duty of care, confidentiality, and EAP obligations Recommend appropriate care pathways and referrals Produce structured advisory memos and RACI action plans How it works CareGuard can operate in two modes: Band.ai SDK Mode (recommended): Creates a dedicated Band.ai chat room where the six Python agents (Triage Sentinel, Risk Analytics Engine, Policy Guard, Core Navigator, Compliance Review Director, and HR Advisory) deliberate in real time via @mentions. Local LLM Mode: Runs the full multi-agent workflow inline using models like Claude, Qwen, DeepSeek, Llama, or GPT-4o-mini. Built with React 19 + Tailwind (frontend), Express + TypeScript + MongoDB (backend), and deployed on Vercel, CareGuard streamlines complex HR case reviews while maintaining high standards of privacy, compliance, and ethical handling.