H
Gallery/第4回 Agentic AI Hackathon with Google Cloud/KOTOWARI Link
K
Excellence Award — 第4回 Agentic AI Hackathon with Google Cloud 2026

KOTOWARI Link

An app that lays the laws behind everyday scenes over the scenes themselves in AR. Pick a difficulty and a field, point a phone at a fountain or a bridge, and an AI reads the image and draws trajectories and force vectors on top of what the camera sees. If curiosity goes further, a link leads to a fuller written explanation.

Event
第4回 Agentic AI Hackathon with Google Cloud
Organizer
Zenn (Classmethod) / Google Cloud Japan
Year
2026
Region
Japan
Prize
Excellence Award
Tech
Google CloudVertex AIGemini 3.0 ProAgentic VisionCloud RunCloud StorageFirebase HostingUnityARCoreAR FoundationARCore Geospatial APIReactFastAPI

From the organizer's citation (summary)

Judges called the concept appealing: AR and generative AI combined to make scientific mechanisms intuitively visible. They saw promise as children's learning material, since curiosity can roam across phenomena, and noted the potential of AR glasses.
A summary of the commentary the organizer published. See the source for the original wording. Zenn (Classmethod) official results

Why It Won — our reading

Two hard things had to work at once: reading a phenomenon out of a camera image, and anchoring the drawing to real-world coordinates. Getting both running in a hackathon window is a hurdle cleared. Letting the user pick a difficulty and a field up front probably mattered too — if the same fountain is explained one way to a ten-year-old and another to a high schooler, the range widens sharply. Returning output as a diagram rather than prose looks like the crux.

This is our own analysis based on the official announcement and the project's own materials. It is not the organizer's stated reasoning.
AD — Advertisement

More winners from this event

2026A
Grand Prize

Anatom-AI

第4回 Agentic AI Hackathon with Google Cloud
A 3D anatomy atlas driven by plain language. Ask about cerebral infarction and the AI picks the relevant organs and vessels, renders them in 3D and adds an explanation. Interpretation, identification and drawing are separate stages, holding down wrong displays, and ambiguous input comes back as candidates to confirm.
2026B
Award of Excellence

Bananacraft

第4回 Agentic AI Hackathon with Google Cloud
An agent that builds a Minecraft town from a vague description. It draws a concept image, works out zoning and building plans, then converts the image in two steps, putting the structure into language before turning it into coordinates, which keeps the result coherent. The frame goes up in bulk; a bot adds decoration on site.
2026B
Award of Excellence

BrickQuest

第4回 Agentic AI Hackathon with Google Cloud
An app that suggests what you can build with the bricks you own. It recognises parts from photos to build an inventory, and once you pick a theme and difficulty the AI generates a 3D build sequence. A physics engine checks it for overlaps and floating pieces, reports the faults and makes the AI redo it, up to three times.
2026A
Encouragement Award

ARTESTERISM

第4回 Agentic AI Hackathon with Google Cloud
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.

See all winners of 第4回 Agentic AI Hackathon with Google Cloud →

Winners using the same tech

Check the original

The links below lead to external sites.

Summaries are written by this site. Project pages include demo videos, screenshots and the team's own write-up (videos may autoplay).