OpenAI 2026 hackathon

Liens (French learning)

A local first French learning platform that combines a source backed language graph with AI teaching, without mixing AI into linguistic truth.

Solo project by Jason Sun · 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 #1,354 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

Liens (French learning) is a self-reported language-learning platform built as a local-first, source-backed language graph with AI teaching assistance. The author states it combines verified linguistic knowledge with AI-generated resources in a single interface, without allowing AI to overwrite linguistic truth.

What changed

The project was submitted to the OpenAI 2026 hackathon and is described as an experiment in structuring French learning through a language graph architecture that separates deterministic linguistic data from AI assistance.

Single most important open question

Is there evidence of user adoption, feedback or traction beyond the author’s own development efforts?

Back to contents

What The Product Actually Is

The description states that Liens is a French learning platform built around a source-backed language graph, where verified linguistic knowledge is stored separately from AI-generated learning resources. It accepts either a French word or sentence through a single search box.

  • For words, it provides lemma, pronunciation, definitions (English and Chinese), conjugations, collocations, CEFR level, frequency, and example sentences.
  • For sentences, it performs deterministic grammatical analysis before offering AI learning assistance.
  • Every word is clickable to explore related language concepts.
  • Users can save content into collections for later review using flashcards or list view.

The app uses a local-first architecture, meaning that verified knowledge comes from the local graph and only calls external AI (e.g., Gemini) as a last resort. The author states this approach avoids mixing AI into linguistic truth.

Inference It appears to be a personal project built by one developer, likely for experimentation or early-stage testing rather than commercial deployment.

Back to contents

Positioning & Claim Evolution

The description claims Liens is a "local first French learning platform" that combines a source-backed language graph with AI teaching, without mixing AI into linguistic truth.

  • The author positions it as an alternative to fragmented tools (dictionaries, grammar websites, flashcards).
  • It aims to provide a connected learning journey, where every element of the French language can be explored and reviewed together.
  • The platform is described as not focused on adding more AI, but on reducing friction and structuring language elements clearly.

Inference The positioning reflects an author-driven vision for a better language-learning experience, not yet validated by market feedback or user behavior.

Back to contents

Target Customer & ICP

The description does not state who the target customer is. It only describes the author’s own motivation: to find a tool that matched how he wanted to learn French.

  • The platform is built for French learners, but no specific learner segment (e.g., beginner, intermediate, professional) is identified.
  • No mention of whether it targets students, professionals, or hobbyists.

Inference The ICP is not defined beyond the author’s personal use case. There is no evidence of market segmentation or user research.

Back to contents

Business Model & Pricing Evidence

There is no evidence in the description of a business model or pricing structure.

  • The project is described as a hackathon submission.
  • No mention of monetization, subscriptions, freemium tiers, or sales channels.

Inference No commercial model has been reported. The product appears to be experimental and not yet monetized.

Back to contents

Technical & Delivery Signals

The description provides some technical details:

  • Built with CSS3, HTML5, JavaScript, Python, SQLite, IndexedDB, and integrated with Google AI Studio and Gemini API.
  • Uses a local-first architecture where verified knowledge is stored locally.
  • AI is used only as a last resort, after checking the local graph and dedicated AI learning database.
  • The app supports deterministic grammatical analysis for sentences.

Inference The technical approach suggests a prototype or MVP built with minimal infrastructure. It’s not clear if this is scalable or production-ready.

Back to contents

Traction & Maturity Signals

There is no evidence of traction, customers, or adoption beyond the author’s own development.

  • The project was submitted to a hackathon.
  • No mention of users, downloads, retention, or usage metrics.
  • No data on how many people are using it or what feedback they’ve given.

Inference The product is at an early stage and lacks any demonstrated user engagement or market traction.

Back to contents

Competitive Context

There is no evidence in the description of competitors or competitive positioning.

  • The author does not name or describe existing French learning platforms.
  • No comparison to other tools (Duolingo, Babbel, Anki, etc.) is made.

Inference No competitive analysis is provided. The project may be a new idea or an untested variant of existing tools.

Back to contents

Key Risks & Red Flags

  • Single-person development: The team size is listed as 1, suggesting limited capacity for scaling or iteration.
  • No traction or revenue: No evidence of users, customers, or monetization.
  • Unproven commercial viability: The product is described as a hackathon submission and not yet in production or market-ready form.
  • Unclear target audience: No defined ICP or user research.
  • Limited technical maturity: The use of local storage (SQLite, IndexedDB) suggests a prototype, not a scalable platform.

Inference The project is experimental and lacks any commercial validation. It may be a proof-of-concept rather than a viable business.

Back to contents

Diligence Questions To Ask The Founders

  1. What specific linguistic data sources are used to build the language graph?
  2. How do you plan to validate or update the language graph over time?
  3. Have you tested this with actual French learners, and what feedback have you received?
  4. What is your roadmap for monetization or scaling beyond a single developer?
  5. How do you intend to differentiate from existing tools like Anki, Duolingo, or Memrise?

Back to contents

Investment/Partnership Verdict

Not evidenced.

The description provides no information on financials, funding, revenue, or customer data. It is unclear whether this project has moved beyond a prototype or if it is a personal experiment.

  • The author states the product is built around a language graph and AI, but there is no evidence of traction, no business model, and no commercial viability.
  • The project appears to be a hackathon submission with no indication of market readiness or investment potential.

Inference This is not a viable candidate for investment or partnership at this stage. It requires further development, user testing, and commercial validation before any due-diligence assessment can proceed.

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.