H
Gallery/第3回 AI Agent Hackathon with Google Cloud/添削AI『言の葉』
添
Award of Excellence — 第3回 AI Agent Hackathon with Google Cloud 2025

添削AI『言の葉』

A web app for marking handwritten exams. Questions and grading criteria are registered in advance; given a PDF of answers, three AI roles, sorting, transcription and commenting, draft the feedback. Teachers edit and place the comments on screen, then export a PDF, lifting a returned test from a bare score to real feedback.

Event
第3回 AI Agent Hackathon with Google Cloud
Organizer
Zenn (Classmethod) / Google Cloud Japan
Year
2025
Region
Japan
Prize
Award of Excellence
Tech
Google CloudGemini APIGemini 2.5 ProCloud Storage (GCS)Cloud Run

From the organizer's citation (summary)

Judges valued that the project tackles teacher workload, a problem with wide impact, while keeping room for human intervention instead of handing everything to the AI. They called it grounded work whose day-to-day operation is easy to picture.
A summary of the commentary the organizer published. See the source for the original wording. Zenn (Classmethod) official results

Why It Won — our reading

Splitting the work across three AI roles looks like the load-bearing choice. A handwritten script demands a sequence of very different judgements: sort the pages, read the writing, assess the answer. Packed into one prompt, failure becomes impossible to trace; split into roles, a human can see where it went wrong. With the teacher in control of the final comments, the result is something that can plausibly sit in a classroom, a setting with little tolerance for silent error.

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

2025フ
Grand Prize

フクシア

第3回 AI Agent Hackathon with Google Cloud
An agent aimed at the paperwork load on social workers. It fills a client's assessment items from an interview transcript, then searches a custom RAG index of support programmes in Yamagata Prefecture and lists fitting ones as tasks. A plain UI works where paper and digital coexist, returning time to face-to-face support.
2025F
Award of Excellence

FutureRun

第3回 AI Agent Hackathon with Google Cloud
An app for experiencing race day before it arrives. It cross-references the course GPX, the weather and the runner's goals and training history, then works out which points to watch, how to pace and where to drink. The advice comes back as a generated video with captions, helping runners picture the course and judge well.
2025P
Award of Excellence

PawMate

第3回 AI Agent Hackathon with Google Cloud
A web service linking the owner of a lost pet with whoever spots it. One agent reads images, another predicts behaviour, and together they estimate from weather, time of day and terrain where the animal is likely to be, drawing it as a heat map. Finders' photos are auto-matched by similarity, and both sides can chat directly.
2025R
Award of Excellence

RouteKeeperAI

第3回 AI Agent Hackathon with Google Cloud
A system that surfaces road hazards before you drive them. It pulls Street View imagery every 50 metres along a chosen route and has AI analyse each point from several angles — blind corners, road surface, visibility — scoring risk on a ten-point scale. The result is a colour-coded map you can question spot by spot in chat.

See all winners of 第3回 AI Agent 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).