Mohamed Taha KAANANE@Choku

NovaAI is a general-purpose AI assistant developed for the AMD AI Hackathon to demonstrate how a single intelligent agent can solve a broad range of natural language tasks through an elegant, user-friendly interface. The application combines a modern desktop experience with a backend powered by Fireworks AI models, creating a seamless workflow for interacting with advanced language models. The interface is intentionally designed to be clean, minimal, and distraction-free. Users interact with the assistant through a conversational chat environment featuring conversation history, streaming responses, markdown rendering, syntax-highlighted code blocks, and persistent chat sessions. The goal is to make powerful AI capabilities accessible through an intuitive user experience. Under the hood, the application follows a modular architecture that separates the user interface from the inference engine. When a user submits a prompt, the UI formats the request into a standardized JSON task file, which is processed by the existing backend pipeline. The backend invokes Fireworks AI models to generate responses and writes the results back to an output JSON file. The interface then automatically reads the generated results and displays them as natural conversational replies. This file based communication makes the system highly modular, allowing the frontend and AI backend to evolve independently. The project emphasizes responsiveness, scalability, and maintainability. By separating presentation from inference and relying on standardized task and result formats, the architecture is easy to extend with additional models, workflows, or capabilities in the future. NovaAI demonstrates how modern AI systems can combine powerful language models with thoughtful software engineering to deliver an intuitive and practical assistant for everyday problem solving.

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.