Inspiration

The idea was chosen by the author from nine candidates that another AI (OpenAI Codex) generated from the public hackathon brief.

In my words: Situations like these are close to my own experience, and they do not happen only to me; I often see them around me. At events and venues, I have found aisles narrow and hard to get through. I have seen people in wheelchairs, with strollers or canes, or with large luggage having trouble at seats and aisles, or had trouble while moving with them. I have set up desks and chairs and noticed only after arranging them that the aisles were narrow, and I had noticed spots in classrooms, shops and similar places where the desk layout made it hard for people to pass.

From nine candidates that another AI generated, I chose one that would help with a problem at familiar, everyday events, and one whose change can be seen at a glance in a video. I did not want to stop at one project; I wanted to try by submitting as many as I could.

What it does

SeatReach checks whether every seat in a small table layout can be reached from the entrance at the aisle width you set.

  • It opens on a "Community hall" preset: 6 tables, 36 seats, a 12 m x 8 m room, one entrance.
  • A width slider (60 to 120 cm, default 90 cm, for example a wheelchair) recomputes live.
  • Reachable floor is shaded teal. Blocked seats are orange with an icon.
  • One pinch marker names the tightest gap, such as "70 cm gap - needs 90 cm".
  • The summary reads "N of M seats reachable at W cm".
  • Drag, rotate, add or delete tables (10 cm snap). Pick a seat to see its route from the entrance.
  • Download the plan as a PNG or copy the layout as JSON.

In the preset, at 90 cm three seats are blocked by a 70 cm gap, and moving one table 30 cm left reconnects all 36. It is a planning aid on a simplified plan. It does not certify accessibility or fire-code compliance.

How we built it

The author is a Japanese speaker and not a software engineer. In Claude Code, the Devpost Learn Skill Pack's 1-start skill was run in the project folder, and scope.md, prd.md and spec.md were drafted from the Skill Pack's templates. The code was then written by OpenAI Codex, running on the author's own small home computer, from the spec. The app is a static page: HTML, CSS and plain JavaScript, with no build step, no external libraries and no network calls. core.js holds the calculator (a 10 cm grid, a distance transform for clearance, a flood fill from the entrance, and a widest-path search to name the pinch point). app.js draws on a canvas. tests.html runs 28 browser assertions on the calculator (all pass). It is hosted on GitHub Pages and licensed MIT.

Challenges we ran into

Because of the deadline, the author asked the assistant to answer the product questions provisionally; those answers are marked [AI-provisional] in the documents. After submitting, the author reviewed them on 2026-10-27 and kept them all as written.

In my words: The registration and submission fields were in English, and each time I had to choose, I needed a translation and a recommendation. When I was asked about my "confidence" before building anything, I had nothing to judge it by.

I submitted two projects starting about two hours before the deadline, so it was a race against time. I could not make time to answer the planning interview myself, so I had the AI answer provisionally. Right before submitting, saving stopped because of a field's character limit (255 characters), and the steps that needed my own hands, such as switching to the account I use for posting videos, all piled up at the end.

Accomplishments that we're proud of

The app runs fully in the browser with no libraries and was checked in a browser with the included tests.html before the demo was recorded.

In my words: Without writing code, I got both projects submitted before the deadline. Both have a page judges can try without an account, and tests that check how they work. I did not hide the parts I left to AI; I wrote them in the submission text and the planning documents.

What we learned

In my words: If I keep the decisions and the final buttons for myself and split the building work across several AIs, something takes shape even in a short time. I should have finished the steps that need my own hands, such as registration, accounts and publishing, first.

Answering the planning interview at length myself is what makes a project new. Next time I want to start earlier and answer the interview myself.

What's next

  • Several entrances and door widths.
  • Importing a JSON layout back into the page.
  • Suggesting the best single move automatically.
  • More table shapes.

About the "In my words" passages

These passages were added on 2026-11-05, after judging. AI drafted them in Japanese from the project records and common situations, and the author confirmed each line; the English above is a translation. The Japanese originals:

  • Inspiration: 次のような場面は自分の体験に近い。自分だけに発生でなく身の回りで見ることが多い。催しや会場で通路が狭くて通りにくかった。車いす・ベビーカー・杖・大きな荷物の人が席や通路で困っているのを見た(または一緒に移動して困った)。机や椅子を並べる設営をして並べた後で通路が狭いと気づいた。教室や店などの机の配置で人が通りにくい所があるのに気づいていた。別の AI が出した 9 案から身近な催しの困りごとに効く物を選んだ。動画で変化がひと目で分かる案を選んだ。1 本で終わらせず出せる数を増やして挑戦したかった。
  • Challenges we ran into: 登録や提出の欄が英語で、選ぶたびに訳と推奨が要った。作る前の時点で「自信」を聞かれても、判断の材料が無かった。締切の約 2 時間前から 2 本を出したので、時間との勝負だった。計画の聞き取りに自分で答える時間を取れず、AI に仮に答えさせた。提出の直前に、欄の字数の上限(255 字)で保存が止まった。動画の投稿用のアカウントを切り替えるなど、自分の手が要る所が最後に重なった。
  • Accomplishments that we're proud of: コードを書かずに、2 本を締切の前に出しきった。2 本とも、審査員がアカウントなしで触れる頁と、動きを確かめる試験が付いている。AI に任せた所を隠さず、提出の本文と計画の文書に書いた。
  • What we learned: 決めることと最後のボタンは自分、作る作業は複数の AI に分けると、短い時間でも形になる。登録・アカウント・公開など自分の手が要る段は、先に済ませておくべきだった。計画の聞き取りに自分で長く答えることが、作品の新しさになる。次はもっと早く始めて、聞き取りに自分で答えたい。

Built With

Share this project:

Updates

Submission history