Sobia Noor@Sobia

Inspiration In 2016, a landmark research paper proved that human crowds design significantly better robots when they can observe and iterate on each other's work ("Social" condition) compared to working in isolation ("Independent" condition). The social group unlocked a hidden "design quality" factor—largely driven by symmetry—that helped their robots walk farther. With the rise of agentic workflows, we asked a fundamental question: Does the "wisdom of the crowd" still hold true when the crowd is entirely made of AI agents? What It Does CrowdSeed AI is a simulation engine and interactive Streamlit platform that reruns this exact behavioral experiment using LLMs instead of humans. Agents are placed in a 5x5 grid environment and tasked with drawing connected lines to form a rigid robot body. The robots are then evaluated in a physics simulator to see how far they can walk. We split our AI agents into two distinct experimental tracks: - Independent Group (Control): Agents can only see and iterate on their own past design attempts. - Social Group (Experimental): Agents can view, adapt, and build upon the successful designs of their peer agents. How We Built It - Agent Infrastructure: Multi-agent LLM framework orchestrated to handle memory, and sequential design generations. - Physics & Evaluation Engine: A customized 2D physics evaluation layer that scores the distance traveled by each generated 5x5 grid robot. - Frontend & Analytics Dashboard: A Streamlit web application featuring results. What We Discovered (Our Real Results) Design Quality & Latent Factors: The Social AI agents scored significantly higher on the computed "design quality" factor than the independent agents (p = 0.0002, indicating a statistically significant result). Value & AI Infra Impact CrowdSeed AI provides the infrastructure to benchmark and study "artificial culture" and social synergy, proving that social connectivity makes AI agent swarms fundamentally more creative and capable.

Enterprise investment due diligence is slow, opaque, and inconsistent. Analysts spend hours collecting information across disconnected tools with no systematic review process and no audit trail. Aegis Agent solves this with a genuine multi-agent workflow. Four specialized AI agents — Forensic Planner, Data Analyst, Risk Auditor, and Executive Finalizer — collaborate through Band chat rooms to analyze investment opportunities. Every agent handoff happens via Band. Every decision is logged. When a user submits a company and deal context, Aegis creates a dedicated Band room and the agents execute a structured workflow: 1. Planner (AI/ML API): Decomposes the task, selects optimal inference models 2. Analyst (Featherless AI): Synthesizes findings, cites sources with URLs 3. Reviewer (Featherless AI): Validates analysis, scores risk 0–100, loops back if gaps found 4. Finalizer (AI/ML API): Produces polished dossier with verdict, alternatives, and reasoning chain Users can pause the room and intervene at any point — the agents adapt and continue with user direction baked into their context. The frontend renders this entire operation as a live war room dashboard. Acts are cinematic. Handoffs are visible. Partner tool usage is unmissable. The result: auditable, explainable, enterprise-grade AI investment analysis.

Travelry is your ultimate AI-powered travel concierge, designed to transform the often-stressful process of trip planning into a seamless, enjoyable conversation. Users interact naturally with our intelligent assistant, expressing their travel desires, budget, and preferences. Leveraging the speed of Groq for real-time responses and the contextual understanding of fine-tuned Llama models, Travelry provides personalized recommendations for hotels, and local activities. From dynamic itinerary generation to real-time price comparisons and secure in-app booking, our platform consolidates all aspects of travel organization. It eliminates information overload and fragmented experiences, offering a single, intuitive solution for discovering, planning, and booking your perfect journey, enhancing efficiency and personalization for every traveler.

🌎 Hybrid Hackathon | 💻 Online Build: September 10–16, 2026 | 📍 On-site: September 15–17, 2026 The official hackathon of AI Infra Summit — co-organized by Kisaco Research and lablab.ai. Build production-grade AI applications on the modern AI infrastructure stack, alongside 8,000+ attendees, researchers, founders, and infra leaders. 📍 On-site Venue (September 15–17): Santa Clara Convention Center 5001 Great America Pkwy, Santa Clara, CA 📍 On-site participation is by invitation only. Travel and accommodation expenses 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.

📅 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.