Sibtain Ahmed@sibtain_ahmed

PermitOS is an AI-powered permitting intelligence platform for real estate developers. Before submitting plans to city authorities, developers upload a project brief and receive a governed, multi-agent pre-screen tied to real regulations — starting with Austin, TX. The problem: permitting is slow, fragmented, and expensive. Zoning, building, environmental, and filing requirements live in different silos. A single setback or egress issue discovered late can cost weeks and thousands in rework. How it works: PermitOS uses five specialist agents orchestrated on Band of Agents. A Conductor opens a per-case Band chatroom and dispatches Jurisdiction & Zoning, Building & Safety, Site & Environmental, and Permit Packager agents in sequence. Each agent calls Austin-specific tools, returns structured JSON with pass/fail checks and legal citations, and never oversteps its scope. The Conductor merges reports, detects conflicts, assigns readiness (Ready / Needs Changes / Blocked), and escalates to a human approver. The Packager assembles permits required, documents, fee estimates, and filing sequence. Every step is logged with an audit hash for regulated workflows. Our demo — Riverside Residences, a 50-unit multifamily project — surfaces a real Austin Land Development Code setback violation (8 ft vs 10 ft required) while passing FAR, height, parking, and life-safety checks. The UI shows live agent progress, compliance reports, suggested fixes, and a filing-ready package (~$47K fees, 45-day estimate). Built for Band of Agents Hackathon Track 3: Regulated & High-Stakes Workflows — multiple models, tool use, structured outputs, human-in-the-loop, and full traceability. PermitOS does not replace licensed professionals or city reviewers; it front-loads compliance review so developers fix issues before they pay application fees.

RunwAI transforms air traffic control from reactive problem-solving to predictive, real-time prevention. The FAA manages over 45,000 flights daily across increasingly congested airspace, while delays and cancellations have grown at nearly double the rate of flight volume - costing the aviation industry over $30B annually. RunwAI addresses this by combining multimodal AI with AMD GPU acceleration. The system fuses three live data sources: OpenSky Network for real-time flight positions and transponder data, METAR weather feeds for atmospheric conditions, and live video streams for visual runway and airspace monitoring. These inputs are processed through an AI pipeline running on AMD Instinct MI300X GPUs, leveraging ROCm 5.x with HIP-optimized kernels for efficient tensor operations across inference workloads. Core capabilities include: (1) Predictive congestion detection - identifies emerging conflicts before they escalate; (2) Weather-aware intelligence - continuously analyzes weather severity and its impact on routes; (3) Intelligent rerouting - generates optimized flight paths balancing safety, fuel efficiency, and airspace capacity; (4) Explainable decision support - delivers evidence-based recommendations with confidence metrics. Performance benchmarks: sub-4ms detection latency, under 2-second response latency, 35% improvement in conflict detection, and over 99% rules check accuracy - processing 10,000+ flight updates per second. The live dashboard provides an airspace map view, conflict alerts panel, and AI-powered rerouting suggestions for controllers in real time.

📅 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.

Grab your ideas, spin up compute, and start building what’s next! Start with $100 in AMD Developer Cloud credits and begin building right away. Get access to hands-on tutorials, workshops, and curated learning resources to help you build faster and go further. To unlock credits and join the hackathon, sign up for the AMD AI Developer Program. 🤝 Go solo or team up — ship something real. 💰 $21,500+ total prize pool & 1 × AMD Radeon™ AI PRO R9700 GPU up for grabs. 📍 On-site Venue (May 9-10): MindsDB SF AI Collective 3154 17th St, San Francisco, California, USA 📍On-site participation is by invitation only. Travel and accommodation expenses will not be covered. 🧑‍💻 Developers, builders, and innovators - bring your boldest ideas and let’s turn them into real AI systems on AMD.

Create noteworthy apps with advanced reasoning across audio, vision, and text in real time with GPT-4o. 🕒 72 hours to complete the challenge 💡 Create revolutionary apps which use GPT-4o advanced features 🤝 Take part alone or form a team with other participants 🚀 Engage in a 3-day virtual development marathon and network with tech and business leaders 🏆 Win opportunity to participate in LabLab NEXT acceleration program