@byrrajus43949

Minima is a compact token efficient routing agent for Track 1 of the AMD Developer Hackathon. It reads hidden natural-language tasks from /input/tasks.json, classifies each prompt into one of the required categories, and routes the task to the appropriate model from the provided ALLOWED_MODELS list. The goal is to maintain answer quality and keep Fireworks token usage low. The agent is built around conservative routing, category specific prompts, output validation, and a fallback path for malformed responses. It never hardcodes model IDs, never stores secrets, and sends all Fireworks requests through the provided FIREWORKS_BASE_URL. Results are written only as the required JSON schema: task_id and answer.

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.