Hammad Khan@hammadkhan

Council AI is a multi-agent decision-intelligence system built for the AMD Developer Hackathon: ACT II (Team Error 200). Instead of asking a single chatbot for an opinion, Council AI lets you brief a custom panel of AI specialists on any high-stakes question moving to a new city, choosing a tech stack, deciding whether to attend an event and get back a structured, evidence-backed recommendation. Here's how it works: an orchestrator agent reads the query and dynamically invents 3-4 specialist roles suited to that specific decision, rather than picking from a fixed set of categories. In Enhanced mode, a prompt-engineer agent further refines each specialist's brief. Each specialist then runs live web research via the Tavily API and produces an independent report. A debate agent cross-examines all the reports, surfacing where the specialists agree and where they conflict. Finally, a synthesis agent weighs the evidence and the debate to produce a final verdict, an executive summary, and a bottom-line recommendation. The backend is a FastAPI service that streams the whole pipeline to the browser over Server-Sent Events, so users watch the council assemble, research, and argue in real time instead of staring at a loading spinner. The frontend is built with TanStack Start, React 19, and Tailwind CSS 4, with Framer Motion powering the transitions. All reasoning is powered by GPT OSS 20 Instruct served through the Fireworks AI API. Council AI turns a single-shot LLM answer into something closer to how real high-stakes decisions get made: multiple experts, real research, honest disagreement, and a considered final call.

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.