A composition aid for school music classes. A student describes in their own words the song they want to make, and the AI proposes chord progressions and melodic techniques that could fit. It stops short of writing the piece itself: students try options and choose, bringing individual creativity into uniform-feeling lessons.
Judges praised an original idea made into a usable product: generative AI closing the knowledge gap between pros and beginners, a UX that sets direction by referencing real songs, and a Flutter interface that drops the piano roll.
The most telling decision may be that the AI's output is not the deliverable. Having the model compose the whole song would make a flashier demo, but it would not work as a class. Narrowing the tool to proposing options and letting the student choose is what makes it coherent as a teaching instrument. Music is also a hard domain to judge, and wrapping it so that a suggestion can be heard immediately through Lyria RealTime probably helped the idea land in the room.
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).