Inspiration
Yuki was caught in the 2011 Tokyo Earthquake, and since he couldn't receive immediate assistance, his thumb was forced to be amputated. We designed this app to prioritize individuals in danger during natural disasters and crises.
What it does
CrisisWeave connects people in need with available volunteers using AI to assess urgency, match help, and optimize response.
How we built it
We built a FastAPI backend with CrewAI agents for assessment, matching, and logistics, and a Flutter frontend for real-time coordination.
Challenges we ran into
Integrating multiple AI agents, handling async backend operations, and designing a unified data flow without a finished frontend.
Accomplishments that we're proud of
A fully functional AI-driven backend, seamless agent coordination, and a working API ready for live crisis simulations.
What we learned
How to orchestrate multi-agent systems, structure APIs for scalability, and design resilient coordination workflows under time pressure.
What's next for CrisisWeave
Add persistent databases, real-time updates, full Flutter integration, and partnerships with NGOs for real-world disaster deployment.
Log in or sign up for Devpost to join the conversation.