A dashboard app that transcribes a meeting in the browser as it happens, then has a lead AI dispatch work to specialist agents that assemble tasks, owners, decisions, agenda items and a summary diagram. The facilitator is freed from note-taking, and when the meeting ends an organised board is already on everyone's screen.
Judges praised the team for building an inventive AI app on Firebase in a short window, noting that Authentication made the sign-in layer quick to build and that Realtime Database's low latency suited this use case — the result of careful design.
Rather than cramming everything into one prompt, the build splits the work: a lead agent hands tasks to specialists. That structure is easy to explain in front of judges, and because the output is broken into units — tasks, owners, decisions — it is also easier to see where something went wrong. The payoff is demo-friendly as well: the instant a meeting ends, the board is already sitting on the shared screen.
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).