Wordbook

The description states that Wordbook is a handwriting-first English vocabulary practice app for Japanese junior high students. The author, Masa Adachi, built it as a prototype during a hackathon using web technologies and AI models like Transformers.js and GPT-5.6. It includes OCR feedback, pronunciation, timers, and parent-auditable progress tracking. The app is described as requiring learners to write words by hand rather than recognize them, with three difficulty levels and a scoring system that penalizes timeouts or OCR failures.

The most important open question is whether this prototype has any traction or adoption beyond the single developer's personal use case — which is not evidenced in the description.

• The description states that Wordbook is a handwriting-first English vocabulary practice app.
• It is designed for Japanese junior high school students.
• Learners see an English word and its Japanese meaning, then write the word by hand.
• OCR feedback is provided using Transformers.js with the Xenova/trocr-small-handwritten model.
• Correct answers are spoken aloud using browser SpeechSynthesis API.
• Sessions contain up to 100 words and use a countdown timer.
• The app includes three difficulty levels:
  • Level 1: copy the visible word
  • Level 2: complete a partially hidden word
  • Level 3: write the word using only its meaning and character count
• Manual pass button is available if OCR fails, with prompt and handwriting image saved for parent review.
• Score history and audit records are stored in LocalStorage.

• The description states that the app was built to address a personal problem: the author's child could not retain vocabulary from paper word lists.
• It was designed as an alternative to multiple-choice apps, which the author believes encourage memorizing answer choices instead of recalling spelling or meaning.
• The product is positioned as a handwriting-first solution for English vocabulary practice.
• The author claims that the app does not merely test recognition but requires learners to produce spelling by hand.
• The prototype was built during Build Week and turned into a working demo.

• The description states that Wordbook targets Japanese junior high school students.
• It is implied that the primary user is a student learning English vocabulary.
• Parents are mentioned as auditors of progress, suggesting they may be part of the target audience or decision-makers in adoption.
• No evidence of other personas (e.g., teachers, schools) is provided.

• Not evidenced. The description does not mention any pricing model, monetization strategy, or business model.

• The app was built using HTML5, CSS3, JavaScript, and Canvas for handwriting capture.
• OCR is implemented using Transformers.js with the Xenova/trocr-small-handwritten model.
• Speech synthesis uses the browser's SpeechSynthesis API.
• Data persistence is handled via LocalStorage.
• Deployment is on GitHub Pages.
• The author used Codex and GPT-5.6 for development, debugging, and documentation.
• A native iPad app is planned using SwiftUI and PencilKit.

• Not evidenced. No data on users, usage metrics, retention, or adoption is provided.
• The prototype was built during a hackathon (Build Week).
• The author mentions that the live demo includes core functionality but does not indicate any real-world deployment or user base.

• Not evidenced. No mention of competitors or market landscape.
• The description implies that existing vocabulary apps are insufficient because they rely on recognition rather than production, but no specific competing products are named.

• The app is described as a prototype built during a hackathon with no evidence of traction or user validation.
• It uses browser-based OCR which the author notes is unreliable and requires manual pass buttons.
• The app is currently deployed as a web prototype, not a native app, despite plans to rebuild it for iPad.
• The author is the sole team member, raising questions about scalability and long-term development capacity.
• No evidence of revenue, customer acquisition, or market validation.

1. What is the actual user base beyond the developer's personal use case?
2. How many students are currently using this app in practice?
3. Has there been any formal feedback from parents or teachers?
4. What specific metrics indicate success or failure of the learning outcomes?
5. Is there a plan to monetize or scale beyond the prototype stage?
6. What are the technical limitations of browser-based OCR that affect usability?
7. How does the app handle data privacy and parental consent for children's information?