EchoWeave

Our team was inspired by Anthropic CEO Dario Amodei’s essay, "Machines of Loving Grace," which envisioning a future where AI helps eliminate disease and helps people find meaning. We realized that as AI begins to handle routine work, the question of human purpose becomes urgent. We chose to participate in the Creative Flourishing track to build a bridge between generations, ensuring that the "universal talent" of storytelling and cultural expression isn't lost to time or social isolation. +4

EchoWeave is a full-stack application designed to facilitate "intergenerational knowledge exchange". The backend, built with FastAPI and the Claude API, features a "Reflective Interviewer" that uses evidence-based oral history techniques to guide users through their memories rather than making decisions for them. The React frontend captures voice-to-text transcripts, allowing seniors to interact naturally without the barriers of complex technical requirements. To turn these memories into immersive digital books, we integrated Nano Banana 2 for style-accurate historical illustrations and Lyria 3 for era-specific background music. +3

During development, we faced significant technical and ethical hurdles. We had to resolve port conflicts on our local machines to meet the 19:15 technical deadline. A more profound challenge was wrestling with the hard ethical question of how to keep the human as the creator while using AI as a tool. We engineered a "Style Lock" to prevent the model from "homogenizing" unique cultural dialects or personal slang into a standard, generic prose. We also prioritized privacy and human dignity by requiring explicit human-in-the-loop approvals before any AI-generated narrative enhancement was saved to the final record. +4

Through this hackathon, we learned that AI is most powerful when it amplifies human creativity rather than short-cutting the process in ways that diminish it. By centering human dignity and agency, we discovered that technology can enhance human connection rather than replacing it. We also realized the importance of building solutions for specific people facing real problems—in our case, the elderly seeking to preserve their legacy—rather than creating hypothetical tools for "everyone"