My Class Twin

The description states that My Class Twin is an AI-powered app that attends classroom lessons with students — particularly those with ADHD — by capturing audio, transcribing it, generating structured notes and quizzes, and supporting spaced repetition review. It builds a study loop from raw classroom recordings.

It uses:

• Flutter for cross-platform client (Android/iOS/web)
• Supabase backend
• Native Android Kotlin layer for features like exact alarms and foreground microphone services
• AI tools including Codex and Claude for development

The system is described as having a full pipeline: record → transcribe → notes → quiz → review, with additional components such as:

• A lesson-grounded explanation assistant that refuses to answer without citing real transcript segments
• A signal-fused study-insights engine replacing simple quiz miss heuristics
• Automatic timetable-driven recording (no manual start required)

The app is built to be secure and privacy-conscious, including row-level security policies in Postgres, consent models, and deletion practices.

Inference This appears to be a prototype or MVP built for a hackathon. The author describes it as a "real product" but does not provide evidence of deployment or user engagement beyond the development process.

The description states that My Class Twin was inspired by personal experience with ADHD and aims to solve problems around classroom recordings being unusable due to lack of structure, poor note-taking, and disconnected learning loops. It positions itself as a tool that treats raw audio as material for an actual study loop — not just a file.

It also emphasizes honesty about technical constraints (e.g., iOS microphone limitations) and ethical concerns (consent, retention, deletion). These are framed as design decisions rather than obstacles.

Inference The positioning is centered on accessibility for students with ADHD and improving learning efficiency through AI automation. However, the claim of solving real-world problems is based on self-reporting without external validation or user feedback.

The description states that My Class Twin targets students with ADHD who struggle with attention and retention during lectures — especially those who find traditional note-taking ineffective or incomplete.

It also implies a broader audience: anyone who wants to improve study efficiency from classroom recordings, though it's not clear if this extends beyond students with diagnosed conditions.

Inference The ICP is likely students with ADHD or similar attention challenges. The description does not indicate whether the team plans to expand beyond this niche or target educators or institutions.

There is no evidence in the description of a business model, pricing strategy, monetization plan, or revenue streams. The project is described as a hackathon submission with no mention of commercial viability or customer acquisition strategies.

Inference No information exists on how this would be monetized or whether it has any commercial intent beyond its current prototype form.

The team treated the build like a real product:

• They wrote down consent models, AI provider tradeoffs, and unit economics before coding
• Validated transcription pipeline against real audio before building UI
• Used Codex for rapid MVP development and Claude Code for native integration
• Built a secure backend with Supabase, including row-level security policies
• Implemented platform-specific features (e.g., exact alarms, foreground services) via Kotlin
• Conducted on-device testing and integration validation using emulators and physical devices

Inference The technical execution shows strong engineering discipline for a hackathon project. However, the lack of production data or scalability considerations suggests this is still in early-stage development.

There is no evidence of traction, user adoption, or product-market fit beyond the author’s own account. The project was submitted to a hackathon and described as a prototype built in one continuous session using AI tools.

Inference No data on users, usage metrics, or product maturity exists. This is clearly an early-stage idea or proof-of-concept.

The description does not mention competitors or market analysis. It focuses on the internal development process and personal motivation rather than existing solutions in the educational AI space.

Inference No competitive context is provided. The team may be unaware of similar tools or platforms, or they may not have conducted a competitive landscape review.

• Unverified claims: All statements are self-reported and unverified.
• No traction or revenue: No evidence of users, customers, or monetization.
• Limited commercial intent: The project is described as a hackathon effort with no indication of future plans to scale or launch.
• Privacy-sensitive features: Automatic recording raises privacy concerns that may require legal compliance or user trust-building — but there’s no mention of how these are addressed in practice.
• Technical complexity vs. execution: While the team shows technical capability, they have not demonstrated real-world deployment or scalability.

Inference The project lacks commercial viability indicators and is likely far from market-ready. The lack of traction or monetization signals raises significant risk for any investment or partnership interest.

1. What is the intended path to market? Is there a plan to launch beyond this prototype?
2. How do you intend to address privacy and consent issues, especially around automatic recording?
3. Have you tested the app with real users (especially students with ADHD)?
4. Are you planning to pursue funding or partnerships to develop this further?
5. What is your long-term vision for the product? Is it intended to be a standalone tool or integrated into larger platforms?