OpenAI 2026 hackathon

Ivrit Sheli — Adaptive Hebrew Learning OS

Turn real Hebrew messages, appointments, and conversations into clear understanding, confident replies, and adaptive practice—privately, in Hebrew, English, and Spanish.

Solo project by Kevin Cusnir · 1 likes · 0 comments

Archive position — measured, not model output

1 like on Devpost

506 of the 7,856 archived projects have more likes, and 1,758 share exactly 1 — so this project's #1,251 place in the like-ranked listing is a tie-break inside that group, not a ranking.

Projects (log scale)

1
10
100
1k
10k
05,592
11,758
2285
3–4132
5–975
10+14

Likes on Devpost. ▲ marks this project's group.

Show the figures
LikesProjectsShare of archive
05,59271.2%
11,75822.4%
22853.6%
3–41321.7%
5–9751.0%
10+140.2%
Devpost like counts for all 7,856 archived projects, captured when this archive was built.

Executive Summary

What the company appears to be

The author describes Ivrit Sheli as an adaptive Hebrew learning operating system that turns real-world Hebrew messages, appointments, and conversations into clear understanding, confident replies, and adaptive practice—privately, in Hebrew, English, and Spanish. It is a self-contained, beginner-friendly tool for Hebrew language learners, built with React, FastAPI, and AI integration (GPT-5.6), designed to support real-life language use through visual dictionaries, pronunciation tools, and personalized learning paths.

What changed

The version 2.4 contest edition introduces a warm, illustrated beginner journey, trilingual support (English, Spanish, Hebrew), a connected visual dictionary with niqqud, transliteration, grammar, and examples, voice selection for masculine/feminine styles, persistent saved vocabulary, identity-only Google sign-in, and local/cloud persistence options.

The single most important open question

Is there evidence of real-world usage or learner engagement beyond the author’s own testing and contest demo? The description states no revenue, customers, or traction data are available.

Back to contents

What The Product Actually Is

  • The description states that Ivrit Sheli is an adaptive Hebrew learning OS.
  • It supports practice in Hebrew, English, and Spanish.
  • It uses visual cues, niqqud, transliteration, audio, translations, and real examples.
  • It includes a pronunciation studio with masculine/feminine voice options.
  • It offers a guided lesson tour, visual dictionary, and adaptive progress tracking.
  • It allows users to save vocabulary with review history and mastery levels.
  • The product is built using React, FastAPI, Python, PostgreSQL, Docker, and AI tools like GPT-5.6.

Inference The product appears to be a self-contained language learning tool focused on practical Hebrew use, not a platform or marketplace.

Back to contents

Positioning & Claim Evolution

  • The author states that Ivrit Sheli aims to be "one calm place where a real word or phrase could become a complete learning journey."
  • It is positioned as an adaptive system that connects real-life encounters with structured learning.
  • The product claims to support right-to-left layout, niqqud, roots and binyanim, gendered forms, homographs, register, pronunciation, and mixed Hebrew/English content.
  • It emphasizes privacy, accessibility, and degraded-mode behavior as core features.

Inference The positioning evolved from a personal project into a tool for beginner learners with practical language needs. The claim is that it adapts to real-world usage rather than fixed curricula.

Back to contents

Target Customer & ICP

  • The description states that the product targets beginners learning Hebrew.
  • It supports learners who encounter urgent language needs in work, healthcare, transport, bureaucracy, messages, and relationships.
  • It is designed for non-technical users with a warm, illustrated beginner journey.
  • Learners can choose English, Spanish, or Hebrew as their primary language.

Inference The ICP appears to be self-directed Hebrew learners who are not enrolled in formal classes and need practical, real-life language support.

Back to contents

Business Model & Pricing Evidence

  • Not evidenced.

Explanation

There is no mention of pricing, monetization strategy, or business model in the description. The author does not state whether the product will be free, subscription-based, or otherwise monetized.

Back to contents

Technical & Delivery Signals

  • Built with React 19, TypeScript, Vite, PWA shell, browser Speech APIs, MediaRecorder.
  • Backend uses Python, FastAPI, Pydantic, SQLAlchemy, Alembic, SQLite FTS5, PostgreSQL 17.
  • Cloud architecture includes OIDC/OAuth with PKCE, HMAC-hashed sessions, CSRF controls, row-level security, structured logs, health/version endpoints, Docker image deployment, Railway CI/CD.
  • Dictionary data is imported from Kaikki/Wiktionary and supports source-aware extensibility.
  • Includes optional OpenAI Responses API adapter with JSON Schema outputs for corrections, register analysis, niqqud, transliteration, contextual exercises, dialogues, weekly plans, missions, and bounded recommendations.
  • Supports local SQLite mode and cloud PostgreSQL persistence.
  • The app includes identity-only Google sign-in using only openid and profile scopes.

Inference The technical stack suggests a modern, secure, and scalable architecture with privacy-first design. The use of AI tools like GPT-5.6 indicates an emphasis on automation in development and learning support.

Back to contents

Traction & Maturity Signals

  • Not evidenced.

Explanation

There is no evidence of revenue, customers, or adoption beyond the author’s own testing and contest demo. The product is described as a self-contained tool with no external usage data provided.

Back to contents

Competitive Context

  • Not evidenced.

Explanation

The description does not mention competitors or market positioning in relation to existing Hebrew learning tools or platforms.

Back to contents

Key Risks & Red Flags

  • No traction or user feedback: The product is described as a self-contained tool with no evidence of real-world usage.
  • Self-reported only: All claims are from the author and lack independent verification.
  • No monetization strategy: No indication of how the product will generate revenue or sustain itself.
  • Limited scope: The focus on beginners and contest demo may not reflect long-term viability or scalability.
  • AI dependency: Heavy reliance on GPT-5.6 raises questions about control, cost, and consistency in learning outcomes.

Inference The lack of real-world usage data and monetization strategy raises significant concerns about product-market fit and sustainability.

Back to contents

Diligence Questions To Ask The Founders

  1. What is the actual user base or feedback from learners beyond your own testing?
  2. How do you plan to scale beyond a single developer’s effort?
  3. Are there any plans for monetization or revenue generation?
  4. How do you intend to validate that the learning paths are effective for real users?
  5. What are the long-term plans for content expansion and localization beyond Hebrew?

Back to contents

Investment/Partnership Verdict

  • Confidence: Low.
  • Verdict: The project is a self-contained, developer-built tool with strong technical execution but no evidence of traction, revenue, or customer adoption. It appears to be a prototype or proof-of-concept submitted for a hackathon. There is insufficient evidence to support an investment or partnership decision at this stage.

Inference While the product shows promise in terms of design and technical implementation, its lack of real-world usage and business model makes it unsuitable for investment or partnership without further validation.

Back to contents

Source

Submitted to the OpenAI 2026 hackathon on Devpost. Project home on DevPost.

The analysis above was generated by a language model from the project's own one-line description. It is not independent research and contains no verified traction, revenue or customer data.