A service that hands quotation work, long the preserve of veteran staff in woodworking shops, over to AI agents. The job is split into stages: read the PDF drawing, identify items and quantities, price the materials, produce the quote. At each stage a person checks, corrects and approves the AI's draft before it moves on.
Judges praised using AI to inherit the tacit knowledge behind manufacturing skills, singling out a quotation process broken down from on-site interviews with clear AI and human roles, and the ADK-and-Firestore setup aimed at continued development.
A Moonshot award tends to reward how far an idea could reach rather than how finished it is today, and this entry has that shape: it narrows to a single task, quotations, while aiming at something much larger, the transfer of what lives in a craftsman's head. The other likely factor is that human approval is built into the flow from the start. Where a wrong number is unacceptable, that is the precondition for using AI at all, and it makes real deployment easy to picture.
See all winners of 第2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).