Trapwise

Trapwise is a self-reported SAT-style learning app designed to analyze why students miss questions by identifying recurring reasoning patterns behind wrong answers. The author states that it uses a "Mistake Twin" system to build personalized profiles of student traps and offers targeted practice through an adaptive loop: Practice → Detect → Train → Weaken.

The product is described as a full-stack web application built with Next.js, React, TypeScript, Tailwind CSS, Supabase, OpenAI GPT-5.6, Playwright, Vercel, GitHub, HTML, CSS, and JavaScript. It includes local fallbacks for core features to reduce dependency on external services like Supabase or OpenAI.

Key claims include:

• The app treats wrong answers as diagnostic evidence.
• It builds a "Mistake Twin" profile based on patterns in distractor choices.
• A feature called "Trap Forge" allows students to study how wrong answers are created.
• The Judge Demo enables users to experience the core loop without an account.

There is no evidence of revenue, customers, or traction beyond the author's own description. The project was submitted as a hackathon entry and has not been independently verified.

The description states that Trapwise is an adaptive SAT-style learning app. It claims to:

• Analyze patterns behind incorrect answers
• Identify recurring reasoning traps through wrong answer choices
• Build a "Mistake Twin" profile of student-specific patterns
• Provide targeted follow-up practice based on those patterns
• Use a learning loop: Practice → Detect → Train → Weaken

The app is described as having:

• A main educational experience that works without external services (local fallbacks)
• Core features like diagnostics, distractor-to-mistake mappings, Mistake Twin generation, and follow-up selection
• Optional AI enhancements via OpenAI GPT-5.6 for richer feedback
• A "Judge Demo" that allows users to experience the core loop without account creation

The author describes it as a full-stack web application built with Next.js, React, TypeScript, Tailwind CSS, Supabase, OpenAI GPT-5.6, Playwright, Vercel, GitHub, HTML, CSS, and JavaScript.

Inference The app appears to be a prototype or proof-of-concept rather than a production-ready product, given its hackathon context and emphasis on local fallbacks.

The author states that most test-prep apps only tell students which questions they got wrong, but rarely explain why the wrong answer felt convincing. Trapwise aims to be different by:

• Treating wrong answers as diagnostic evidence
• Identifying recurring reasoning patterns (e.g., solving for wrong value, misreading graph)
• Creating a "Mistake Twin" that shows dominant and secondary mistake patterns
• Teaching students to think like question designers through "Trap Forge"

The positioning evolves from:

1. Basic test prep → Diagnostic learning
2. Correct/incorrect feedback → Pattern-based reasoning analysis
3. Student as test-taker → Student as pattern analyst

The author emphasizes that the app does not claim certainty about a student's private thought process, instead using phrases like "Your answer pattern suggests..." and "Your current Mistake Twin tends to..."

Inference The positioning reflects an attempt to differentiate from traditional SAT prep tools by focusing on understanding reasoning errors rather than just correct answers.

The description states that Trapwise is designed for students preparing for the SAT, specifically those who want to understand why they miss questions and how to avoid recurring traps.

It targets users who:

• Are taking or preparing for standardized tests (SAT)
• Want to move beyond simple correctness feedback
• May be struggling with recurring reasoning patterns in test-taking
• Would benefit from personalized practice based on their mistake history

The app is described as having a "Judge Demo" that allows anyone to experience the core loop without creating an account, suggesting it's designed for broad accessibility.

Inference The target customer appears to be high school students or test-takers preparing for standardized exams, particularly those who struggle with pattern recognition in problem-solving rather than knowledge gaps.

The description does not provide any information about:

• Revenue model
• Pricing structure
• Monetization strategy
• Customer acquisition costs
• Unit economics

It mentions optional cloud features supported by Supabase, including:

• User authentication
• Cloud progress storage
• Profiles
• Cross-device persistence
• Leaderboard information
• Account-based learning history

However, the app also supports guest access and a demo mode that works without accounts or payments.

Inference The business model is unclear from this description. It appears to have optional paid features (cloud sync, leaderboards) but also offers free access through guest mode and demo functionality.

The author states that Trapwise was built as a full-stack web application using:

• Next.js
• React
• TypeScript
• Tailwind CSS
• Supabase
• OpenAI GPT-5.6
• Codex
• Playwright
• Vercel
• GitHub
• HTML, CSS, JavaScript

Key technical signals include:

• Local learning engine: Core features work without external services (Supabase/OpenAI)
• Deterministic systems: Main experience remains functional even when AI is unavailable
• Fallback behavior: Local fallbacks for all major functions
• Responsive design: Mobile navigation, keyboard accessibility
• Security considerations: Session identifiers to prevent duplicate rewards
• Error handling: Bounded loading states, retry actions, safer error messages

The app includes:

• Structured question metadata (subject, skill, difficulty, correct answer, distractors with mistake categories)
• Adaptive practice selection based on performance and patterns
• Game-like elements (XP, levels, streaks, achievements)

Inference The technical implementation shows a focus on reliability and accessibility, with an emphasis on local functionality to reduce dependency on external services.

The description contains no evidence of:

• Revenue
• Customers
• User base
• Adoption metrics
• Product-market fit validation
• Market traction
• Growth indicators

It mentions that the project was submitted to the OpenAI 2026 hackathon, indicating it's a prototype or proof-of-concept rather than a mature product.

The author notes:

• The app includes a "Judge Demo" for hackathon judges
• It supports guest access without accounts
• It has a fictional demo leaderboard
• It was built in a short timeframe (hackathon context)

Inference There is no evidence of traction or maturity beyond the initial development phase. The project appears to be at an early stage, likely a prototype or MVP.

The description does not provide any information about:

• Competitors
• Market positioning relative to existing test prep tools
• Differentiation from similar products
• Market size or growth trends
• Competitive advantages or disadvantages

It only states that most test-prep apps tell students which questions they answered incorrectly, but rarely explain why the wrong answer felt convincing.

Inference The competitive landscape is unknown. The author positions Trapwise as different from traditional SAT prep tools by focusing on reasoning patterns rather than correctness alone, but no specific competitors are mentioned.

Key risks and red flags based on the description:

1. Unvalidated educational claims: The app's core premise that wrong answers contain valuable diagnostic information is unproven in practice.

1. Lack of evidence for effectiveness: No data showing whether the Mistake Twin system actually improves learning outcomes.

1. Unclear business model: No indication of how the product will generate revenue or scale beyond a hackathon prototype.

1. Dependency on author's expertise: The entire project was built by one person (Trung Vo), raising questions about scalability and team capacity.

1. AI integration risks: While AI is optional, the app still relies on OpenAI GPT-5.6 for enhanced features, which could be unreliable or costly.

1. Limited validation: The Judge Demo is fictional and designed for short-term use, not real-world testing.

1. Unproven market demand: No evidence of customer interest or market validation beyond the author's own claims.

1. Technical implementation risks: The complexity of pattern detection and AI integration may be underestimated.

Inference The project appears to be a conceptually interesting but untested prototype with significant uncertainty around both educational effectiveness and commercial viability.

1. What evidence supports the claim that identifying reasoning patterns improves learning outcomes?
2. How was the "Mistake Twin" system validated with real students?
3. What is the actual implementation plan for scaling beyond a single developer?
4. How does the app handle edge cases in pattern detection?
5. What are the specific revenue models being considered?
6. How will user data be collected and used ethically?
7. What metrics are being tracked to measure educational effectiveness?
8. How does the app differentiate from existing SAT prep tools in practice?
9. What is the timeline for moving beyond prototype status?
10. How will the AI components be maintained and updated?