Arsal Mujeeb@ARdebug

As AI assistants evolve from simple chat interfaces to autonomous workers, developers need robust frameworks to handle complex, multi-domain workflows (such as querying academic knowledge bases, managing GitHub repos, and handling calendar/email productivity). Traditional monolithic prompts fail when scaling across diverse toolsets. We set out to build a clean, production-ready architecture that bridges autonomous multi-agent orchestration with a responsive, full-stack dashboard—giving users a unified command center powered by specialized AI agents. Orchestration & Logic: LangGraph, LangChain Core, Claude 3.5 Sonnet (ChatAnthropic) Vector Database & RAG: Qdrant Vector Cloud, FastEmbed Tool Protocols: Custom MCP (Model Context Protocol) servers using FastMCP Backend: FastAPI, Uvicorn, Python Frontend: React, Vite, modern CSS dark-theme dashboard with real-time state route indicators and animated agent badges

Every gamer wants to get better, but using AI coaching software usually comes with a huge downside: it slows down your PC. In competitive games, dropping frames for even a second can cost you the match. Plus, gamers are always worried about anti-cheat systems banning them for running background apps. That is why our team, The Agentic State, built AgenticAim. AgenticAim is a smart, automated esports coach that helps you improve your aim and fine-tune your mouse sensitivity—all without slowing down your computer. Instead of forcing your PC to run heavy AI programs while you play, we built a system that offloads all the hard work to the cloud. Here is how it works: We used a multi-agent AI system built with LangGraph. As you play, our app looks at your mouse movements and screen data to figure out your habits. But the real magic happens through the AMD Token Factory. Whenever the AI needs to do heavy video processing or complex decision-making, it sends that task straight to AMD’s cloud servers. Because AMD handles the heavy lifting, your PC stays 100% focused on running your game at maximum frames per second (FPS). For the backend, we kept things fast and secure using FastAPI and SQLite to log your gaming sessions. We also designed it to be totally safe to use—it never alters game memory, so you do not have to worry about anti-cheat penalties. AgenticAim gives regular players the same amazing insights that pros get, using AMD's powerful cloud tech to keep gameplay buttery smooth and competitive.

Six Matches. One leaderboard. Build on AMD, earn points and compete for prizes.

🌎 Hybrid Hackathon | 💻 Online Build: 12-17 October 2026 | On-site phase: 17-18 October 2026 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. The AMD Developer Hackathon: ACT III is a hands-on event for developers, founders, engineers and builders who want to push what’s possible with AI on real infrastructure. 📍 If approved for the on-site experience, you'll also have the opportunity to showcase your project live. Travel and accommodation will not be covered.

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.