IELTS Focus

This analysis is based solely on the self-reported project description provided by the author. No third-party verification, traction data, revenue figures, or customer feedback are available.

The description states that IELTS Focus follows a learning loop:

• study
• capture evidence
• diagnose weakness
• prescribe repair
• verify progress
• repeat

It includes:

• Timed practice sessions (Writing, Reading, Listening, Speaking)
• Coach Brief, Review, adaptive planning
• Vocabulary and Weekly Review features
• Archive that acts as a study memory

AI is used for:

• Explaining evidence
• Comparing learner attempts
• Supporting scoring and generation workflows
• Helping learners act on feedback

It also includes:

• A desktop app built with Electron
• Web-based components using React, TypeScript, Tailwind, Vite
• Supabase backend with PostgreSQL
• Stripe integration for payments
• Playwright for testing
• Codex and GPT-5.6 for development assistance

The product is described as a hybrid local-first + hosted model, where learner history remains local by default but identity, backups, and billing are managed remotely.

The project claims to offer:

• An affordable AI IELTS coach
• Personalized feedback based on learner practice history
• Focused repairs and clear learning paths
• A deterministic teacher layer that owns diagnosis and progression decisions

It emphasizes:

• Memory: what went wrong, which weakness matters most, what to try next
• Avoiding repetition of mistakes
• Not relying on general chat models for curriculum control

The founder notes that the product was initially built for personal use during IELTS preparation, achieving an IELTS score of 7.5 and securing university offers.

These claims are self-reported and not independently verified. The project does not make guarantees about outcomes or official affiliations.

The target customer is:

• Learners preparing for the IELTS exam
• Individuals who cannot afford private tutoring (priced at over $100/month)
• People seeking structured, adaptive learning with AI support

The ICP appears to be:

• Self-motivated learners who prefer independent study
• Those looking for affordable alternatives to expensive coaching
• Users interested in privacy-preserving tools

No explicit segmentation or persona data is provided. The description does not indicate whether the tool targets specific demographics, proficiency levels, or regions.

The business model includes:

• A free trial experience (7-Day Reading Challenge)
• Paid subscription via Stripe
• Recurring billing with idempotent webhook handling for subscriptions, invoices, refunds, and disputes
• Self-service billing portal

Key features related to monetization:

• Trial AI debrief with atomic one-per-learner claims
• Signed 30-day offline access for paid desktop product
• Optional, revocable marketing consent
• Public privacy, terms, non-affiliation, and no-score-guarantee language

There is no evidence of pricing tiers, revenue models beyond subscriptions, or customer acquisition costs. The description does not mention any paid features beyond the subscription model.

Technical elements include:

• Built with Electron, React, TypeScript, Tailwind, Vite
• Supabase backend with PostgreSQL
• Stripe integration for payments
• Playwright for automated testing
• Codex and GPT-5.6 used in development
• Row Level Security (RLS) on database tables
• Idempotent webhook handling for Stripe events
• Offline access via signed entitlements

Delivery signals:

• Unit tests (302), browser tests (96), ML pipeline tests (4)
• UI policy checks, TypeScript checking, production build validation
• Public privacy, terms, and no-score-guarantee disclosures
• Anonymous demo with synthetic data for judges

There is no evidence of scalability, performance metrics, or infrastructure beyond the current build week extension.

The project has:

• A live public site, Reading Challenge, and anonymous demo
• A working prototype used by the founder during personal IELTS prep
• Achieved an IELTS score of 7.5 (not guaranteed or causally linked to product use)
• Unit and browser tests covering core functionality
• Repository passing multiple test suites

However:

• No customer base, user engagement data, or retention metrics are reported
• No revenue figures or paid users are mentioned
• The founder’s personal success is not presented as a promised outcome

The maturity of the product is limited to a functional prototype with no external validation or real-world usage.

The description does not provide any information about competitors, market size, or competitive positioning. It does not mention:

• Other IELTS prep platforms
• AI-powered language learning tools
• Educational SaaS offerings in the test prep space

No competitive landscape is described; this is a gap in the evidence.

Key risks and open questions include:

• Single-founder dependency: The team size is listed as one.
• Unverified claims: Personal success (IELTS 7.5) is not tied to product use.
• No outcome guarantees: The product explicitly states it does not claim official affiliation or guaranteed scores.
• Limited testing: No evidence of controlled trials, A/B tests, or user feedback loops.
• Privacy vs. AI utility trade-off: The ML layer is intentionally not presented as authoritative, limiting its potential impact.
• No commercial traction: No revenue, customers, or usage data beyond the founder’s experience.

These issues suggest a high risk of failure if scaling beyond personal use without external validation.

1. What specific learning outcomes have you observed from users who completed the 7-Day Reading Challenge?
2. How do you plan to validate that AI feedback improves actual IELTS scores?
3. Can you demonstrate any evidence of learner engagement or retention beyond your own use case?
4. What is your strategy for expanding beyond a single founder and building a sustainable team?
5. Are there plans to integrate with official IELTS content or organizations like Cambridge or the British Council?
6. How do you intend to scale the product beyond the current build week extension?
7. What are your long-term goals for AI integration, especially regarding machine learning models that could enhance adaptive guidance?

These questions aim to uncover whether the founder has a realistic path from prototype to scalable product.