Archive position — measured, not model output
0 likes on Devpost
2,264 of the 7,856 archived projects have more likes, and 5,592 share exactly 0 — so this project's #5,579 place in the like-ranked listing is a tie-break inside that group, not a ranking.
Projects (log scale)
Likes on Devpost. ▲ marks this project's group.
Show the figures
| Likes | Projects | Share of archive |
|---|---|---|
| 0 | 5,592 | 71.2% |
| 1 | 1,758 | 22.4% |
| 2 | 285 | 3.6% |
| 3–4 | 132 | 1.7% |
| 5–9 | 75 | 1.0% |
| 10+ | 14 | 0.2% |
Executive Summary
What the company appears to be
NoBS is a self-reported vocabulary-learning tool for children, built in 2 days using OpenAI's Codex, Supabase, and the OpenAI API. It claims to use AI to adaptively teach words based on age, track retention via spaced repetition, and generate contextual stories and pronunciation. The author states it was tested with two children and that they preferred it over existing curricula.
What changed
The project is a self-reported prototype built for a hackathon. No commercial product, revenue, or customer base exists beyond the author’s own testing with children.
Single most important open question
Is there evidence of actual user traction or adoption beyond the author’s personal testing? The description does not indicate any measurable usage or feedback from users outside the founder's family.
What The Product Actually Is
The description states that NoBS is a vocabulary-learning app for children. It uses AI to:
- Select age-appropriate words
- Test spelling and meaning
- Provide teaching if needed
- Use spaced repetition for review
- Generate sample sentences, TTS (text-to-speech), dictation (for verbal explanations)
- Create stories using multiple learned words
It is built with OpenAI Codex, Supabase, and the OpenAI API. The app was developed in 2 days by one person (Haoyang Feng) and tested with two children.
Evidence
- The author states: “It chooses a word that's suitable for the child based on their age...”
- “The OpenAI API is used to generate sample sentences, TTS (to pronounce the word), dictation (for children to explain what a word does if typing is too hard for them), and to judge the child's explanation of the word.”
- “It also generates stories using multiple words they are learning to further test comprehension in context.”
Inference The app appears to be a proof-of-concept prototype, not a commercial product.
Positioning & Claim Evolution
The author positions NoBS as an AI-powered vocabulary tool that helps children learn faster and more efficiently than traditional methods. It is described as:
- Personalized for age
- Adaptive in difficulty
- Using spaced repetition
- Incorporating multiple learning modalities (spelling, meaning, dictation, TTS, storytelling)
The author claims it was preferred by two children over existing curricula.
Evidence
- “Help children learn vocabulary fast”
- “It adapts the difficulty based on the test results and uses spaced repetition to help the child review the words they're learning.”
- “We were able to come up with an app in 2 days that 2 children of different age brackets reported they preferred this over their existing vocabulary curriculum/app.”
Inference The positioning is early-stage, focused on solving a specific problem (inefficient vocabulary learning) for a narrow audience (children). No commercial or market positioning beyond the hackathon submission.
Target Customer & ICP
The description states that NoBS targets children learning vocabulary. It adapts to age and uses spaced repetition to track retention.
Evidence
- “It chooses a word that's suitable for the child based on their age”
- “It tracks which words the child knows and which they should be learning”
Inference The ICP appears to be children aged 5–12, with a focus on vocabulary acquisition. No evidence of segmentation or targeting beyond this.
Business Model & Pricing Evidence
No business model or pricing information is provided in the description.
Evidence
- Not evidenced
Inference There is no indication of monetization, subscription plans, or pricing structure.
Technical & Delivery Signals
The app was built using:
- OpenAI Codex
- Supabase
- OpenAI API (for sentence generation, TTS, dictation, and evaluation)
It was built in 2 days by one person, tested with two children.
Evidence
- “100% built with the codex mac app...”
- “Built with (author-declared): codex, openai, supabase”
- “Tested with my children”
Inference The technical stack is minimal and hackathon-focused. No evidence of scalability or production-grade infrastructure.
Traction & Maturity Signals
There is no evidence of traction or adoption beyond the author’s own testing with two children.
Evidence
- “Tested with my children”
- “We were able to come up with an app in 2 days that 2 children of different age brackets reported they preferred this over their existing vocabulary curriculum/app.”
Inference No data on user engagement, retention, or broader adoption. No evidence of product-market fit beyond a single use case.
Competitive Context
The description does not mention any competitors or market context.
Evidence
- Not evidenced
Inference No indication of existing solutions in the vocabulary-learning space for children, nor how this project differentiates from them.
Key Risks & Red Flags
- No commercial traction or user data: The app is a prototype tested with only two children.
- Unproven scalability: Built in 2 days by one person; no evidence of production infrastructure.
- Unclear monetization strategy: No pricing, business model, or revenue plan.
- Self-reported claims: All evidence is from the author’s own account — no independent validation.
- No market positioning beyond hackathon: No indication of broader commercial intent.
Diligence Questions To Ask The Founders
- What specific metrics were used to evaluate whether children preferred NoBS over existing tools?
- How does the app plan to scale beyond one developer and two test users?
- Are there any plans for monetization or user acquisition?
- What is the long-term vision for expanding beyond vocabulary into other learning areas?
- Has the app been tested with more than two children, or in a broader educational setting?
Investment/Partnership Verdict
Not evidenced
The description provides no evidence of commercial traction, revenue, customer base, or product-market fit. It is a self-reported hackathon prototype with limited validation.
Confidence Low This analysis is based entirely on the author’s own account and lacks any external corroboration or data points to support claims of viability, scalability, or market readiness.
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.