A platform linking museums and visitors. From a painting's image, AI writes commentary at three difficulty levels in several languages, delivered as an audio guide. Preferences left on each work are matched against embeddings to suggest what to see next and where it hangs, while museums see a per-work view of how pieces land.
Judges saw novelty in a concept that turns to the under-examined museum experience and recommends art and venues matched to a visitor's taste. They also credited the vision of drawing visitors to smaller museums and its potential as a real service.
As we read it, the core is that it does not stop at an audio guide: the reactions it collects flow back to the museum. A one-sided app invites comparison with existing guide apps; feedback that returns to exhibition planning gives a museum a reason to adopt it. Commentary at three difficulty levels in several languages also fits venues whose audiences vary widely. The award tier reads as recognition of the concept plus awareness of the distance left to a working service.
See all winners of 第4回 Agentic AI 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).