An agent aimed at the paperwork load on social workers. It fills a client's assessment items from an interview transcript, then searches a custom RAG index of support programmes in Yamagata Prefecture and lists fitting ones as tasks. A plain UI works where paper and digital coexist, returning time to face-to-face support.
Judges valued a problem rooted in interviews with people in the field, and execution that carried the idea through to testing. That grounding was called its greatest strength, with hope voiced that it clears adoption hurdles and gets used.
The judges pointed to field grounding, which also shows in the design. Limiting the RAG index to programmes in one prefecture keeps answers easier to trust than a nationwide sweep would, and it is a realistic call for a team aiming to reach testing inside a hackathon. The interview transcript as entry point also targets a step every social worker goes through. The unadorned UI looks less like a shortcut than a condition for entering an office where paper still circulates.
See all winners of 第3回 AI Agent Hackathon with Google Cloud →
Summaries are written by this site. Project pages include demo videos, screenshots and the team's own write-up (videos may autoplay).