Kshitij Vashisht@kshitijvashisht

Pattern-AI is a conversational cognitive intelligence platform designed to understand how a person's thinking, communication, and behavioral patterns evolve across multiple conversations rather than analyzing isolated messages. Instead of treating each interaction independently, Pattern-AI aggregates conversational history and performs post-conversation cognitive analysis to generate explainable cognitive profiles that evolve over time. The platform provides three adaptive interaction modes. Pattern Mode enables users to engage in natural conversations and receive longitudinal cognitive insights. Expert Mode integrates retrieval-augmented knowledge retrieval from psychology, psychiatry, neurology, and scientific literature to support evidence-aware professional conversations. Patient Mode allows experts to securely invite patients into isolated sessions, where conversations are transformed into structured expert-facing cognitive reports after the session concludes. To maintain a responsive user experience, Pattern-AI separates real-time conversation from computationally intensive cognitive analysis. Chat interactions remain lightweight while profile generation, behavioral extraction, and report synthesis are performed after the conversation ends. The system combines a Next.js frontend with a FastAPI backend, secure authentication, encrypted data storage, vector retrieval, and explainable AI workflows to create a scalable platform for cognitive research, professional decision support, and longitudinal behavioral understanding. Pattern-AI is intended as a research and decision-support platform and is not a medical diagnostic system.

To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. ADP members can access AI tutorials, experts, and community support. In addition, new members can claim a free month of DeepLearning.ai pro, $100 in AMD GPU cloud credits, and $50 in Fireworks AI API credits. All hackathon participants will receive on hackathon launch additional compute and API credits for their projects. Ready to build what's next on AMD? Sign up with AMD below to secure your spot.

📅 June 12–19, 2026 • June 12: Kick-off Stream • June 12–19: Online Build Phase • June 19: Project Submissions Ends 🌍 Fully online hackathon. Join and build from anywhere in the world. 🤝 Build practical enterprise workflows where AI agents communicate, coordinate, exchange context, and complete work together. 🧠 Powered by Band and Codeband, built for collaborative AI systems and agent orchestration. 🏆 Prize Pool: $10,000+ 🧑‍💻 Apply now to build the next generation of enterprise multi-agent systems.