# Seattle DGX Spark Hackathon Winners Spotlight

## Executive summary

This summary covers the NVIDIA DGX Spark Hackathon winners, spotlighting two advanced local AI applications: Kerberos, a shared spatial-awareness system for search-and-rescue (SAR) teams, and VELA, a voice-first, consent-controlled healthcare action system. Both projects demonstrate the power of running complex, multi-agent AI workflows entirely on local hardware (NVIDIA GB10), ensuring data privacy and real-time action capability.

## Key takeaways

- Local AI for Privacy and Reliability: Both winning systems (Kerberos and VELA) are designed to run entirely on the NVIDIA GB10, ensuring that sensitive data (e.g., medical records, live camera feeds) remains local and is not transmitted to the cloud, addressing critical security concerns in healthcare and SAR.
- Agentic Workflows for Complex Tasks: The projects utilize multi-agent architectures (e.g., VELA's system) where specialized agents (like Parakeet for speech recognition, Neatron for reasoning, and Magpie for speech output) collaborate to perform complex, multi-step tasks, moving beyond simple chatbots to actionable outcomes.
- Shared Situational Awareness in SAR: Kerberos creates a shared live map for SAR, integrating data from multiple sources (drones, robots, body cameras) to track responders, map searched areas, and pinpoint casualties or hazards, even indoors where GPS fails.

## Technical details

- Hardware & Architecture: The applications are built to run locally on the Acer Veriton GN100, powered by the NVIDIA GB10 Grace Blackwell Superchip, emphasizing edge computing and local processing.
- AI Models and Algorithms: The systems leverage advanced models including Neatron (used in both projects) for reasoning and multi-modal understanding, and incorporate algorithms like DPVO and SLAM for accurate odometry and mapping.
- Healthcare Workflow (VELA): VELA processes user care needs and insurance information to generate verified options across cost, coverage, and providers. It uses a multi-agent structure with Parakeet (speech recognition), Neatron (reasoning), and Magpie (spoken response).
- Security and Control: VELA implements 'explicit consent' before taking any consequential action. Furthermore, the system uses a sandbox environment and OpenShell to define boundaries, ensuring agents operate within controlled policies.

## Practical implications

- Search and Rescue: Providing first responders with real-time, shared situational awareness maps to optimize search patterns and locate casualties quickly.
- Healthcare Management: Streamlining the complex process of care planning by comparing insurance plans, finding providers, and scheduling appointments while requiring explicit user consent.
- Data Sovereignty: Enabling mission-critical applications to run entirely on local hardware, eliminating reliance on cloud services for data processing.

## Topics

Artificial Intelligence, Robotics, Edge Computing, Healthcare Technology, Search and Rescue, NVIDIA GB10 Grace Blackwell Superchip, Isaac Sim, Neatron, Parakeet & Magpie

Source: https://www.youtube.com/watch?v=p4yTWO0Y_t0