Build Week Demo
Compare how different weekly worksheet plans may change a learner's progress toward advanced learning goals in Japan.
Based on a real family workflow across Japanese, Math, and English.
Anonymized real-world sample
This sample is derived from a real learner's progress. Names, identifying details, and exact dates have been removed or altered.
Study plan
Change the weekly worksheet total for each subject and compare three possible future paths.
Goal benchmarks
The sample uses published 2026 Japanese reference benchmarks to explain what the learner is trying to reach.
Future paths
Each path uses the same target date and current worksheet levels, but a different weekly worksheet plan.
Progress history
The chart shows the sample learner's worksheet history and the current worksheet point used for planning.
Background
Future Paths began as a private planning tool for a family using Kumon in Japan. It compares worksheet progress and weekly study plans as several possible future paths.
Independent project. Not affiliated with or endorsed by Kumon.
The benchmark names are shown to explain the real Japanese use case. Future Paths does not calculate official award eligibility.
Build method
The creator did not directly edit a single character of HTML, CSS, or JavaScript.
GPT-5.6 was used to turn lived experience, product decisions, privacy requirements, and review feedback into implementation prompts. Codex generated and revised all application code and project files.
Codex output was repeatedly brought back to ChatGPT for evaluation. Claude or Gemini were sometimes used for additional perspectives. The feedback was then synthesized with GPT-5.6 into the next prompt and returned to Codex.
The creator's role was to test the application, make product decisions, and direct every revision in natural language.
The application is evidence that a personal planning problem can be turned into working software without direct code editing, then shared so others can continue it through natural language.
AI remixable source
Future Paths is not only a hosted demo. The complete source files are available under the MIT License.
You can download the files, load them into an AI assistant that can read project files, describe your own subjects, curriculum, goals, or workflow, and use a coding agent such as Codex to implement a customized version.
Open by design
Future Paths was not created primarily for exclusive ownership or monetization.
The source files are released under the MIT License so that anyone can use, copy, modify, redistribute, and build upon them while preserving the copyright notice and license text.
The value of this project is not limited to one finished application. A tool born from one person's lived experience can be inherited by others, adapted for new purposes, improved, and passed on again.
For this project, "open" does not only mean that the code is visible. It means that the continuation of the software is open to everyone.
The application is open source. More importantly, the ability to continue creating it is open.
MIT License allows use, modification, redistribution, and commercial use. Modified versions do not have to be published, but the original copyright notice and license text must be preserved.
The creator wants the original attribution to remain so that people can identify who started the project. This attribution is not intended to prevent anyone from using, modifying, redistributing, or building upon the software under the MIT License.
The MIT License applies to the original Future Paths source code and documentation. It does not grant rights to third-party trademarks, logos, curriculum materials, benchmark publications, or copyrighted content.
This public Build Week demo is a reproducible snapshot anchored to July 21, 2026. Customized versions may replace the fixed planning anchor with their own date logic.
Future Paths is not only a hosted demo. The complete source files are available under the MIT License.
You can download the files, load them into an AI assistant that can read project files, describe your own subjects, curriculum, goals, or workflow, and use a coding agent such as Codex to implement a customized version.
Software can now be read, rewritten, and passed on through natural language, much like written knowledge. Subject to the license, a tool created from one person's experience can become an adaptable shared resource.
AI-generated changes may contain errors. Always test the customized version before relying on it.
Do not upload personal learner data to third-party AI services unless you understand and accept their privacy terms.
Please read all files in this project and explain:
1. How the application is structured
2. Which files control the interface, calculations, data, and translations
3. What personal or private data I should avoid adding
4. How I could adapt it to my own subjects, curriculum, goals, and workflow
Do not modify any files yet.
After explaining the current project, ask me questions about the version I want to build. Then create a complete implementation prompt that I can give to Codex or another coding agent.このプロジェクトの全ファイルを読み、次の内容を説明してください。
1. アプリがどのような構造になっているか
2. 画面、計算、データ、翻訳を担当するファイルはどれか
3. 追加しない方がよい個人情報や非公開情報は何か
4. 自分の教科、教材体系、目標、運用方法へ変更するには何が必要か
まだファイルは変更しないでください。
現在の構造を説明したあと、私が作りたいバージョンについて質問してください。その回答をもとに、Codexなどの実装AIへ渡せる完全な修正プロンプトを作成してください。Accepted headers: date,japanese,mathematics,english or 日付,国語,算数,英語.
| Date | Japanese | Math | English |
|---|