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 #3,778 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
A single-person project named Document AI — Épure 3D, submitted to the OpenAI 2026 hackathon. The author describes it as a tool that turns scanned technical drawings into interactive 3D geometry for learning.
What changed
No evidence of prior version, traction or commercial activity is provided. This is a self-reported project submitted in a hackathon context.
Single most important open question
Is there any evidence of product-market fit, customer feedback, or revenue generation beyond the author’s own description?
What The Product Actually Is
The description states: “Turn scanned technical drawings into honest, interactive 3D geometry for learning.”
- Evidenced claim: The product is described as converting scanned technical drawings into interactive 3D geometry.
- Inferred claim: The tool may be used in educational or training contexts.
- Not evidenced: No details on how the conversion works, what format the input/output takes, or whether it supports specific drawing types (e.g., CAD, PDF, etc.).
Positioning & Claim Evolution
The tagline is: “Turn scanned technical drawings into honest, interactive 3D geometry for learning.”
- Evidenced claim: The product is positioned as a tool that converts static drawings into interactive 3D models for educational use.
- Not evidenced: No indication of prior positioning, evolution of claims, or differentiation from other tools in the space.
Target Customer & ICP
The description states: “for learning.”
- Evidenced claim: The intended audience is users engaged in learning or education.
- Inferred claim: Likely includes students, educators, or professionals in technical fields (e.g., engineering, architecture).
- Not evidenced: No specific customer segments, personas, or use cases are described.
Business Model & Pricing Evidence
The description provides no information on pricing, monetization, or business model.
- Not evidenced: No mention of how the product will be sold, who pays, or whether it is free, subscription-based, or one-time purchase.
Technical & Delivery Signals
The author lists technologies used:
- Built with: codex, express.js, gpt-5.6, openai, react, sqlite, three.js, typescript, vite
- Evidenced claim: The project uses a stack including GPT models, React, Express.js, and Three.js.
- Inferred claim: The tool likely leverages AI for processing scanned drawings and rendering 3D models.
- Not evidenced: No information on performance, scalability, or delivery mechanism (e.g., web app, API, desktop).
Traction & Maturity Signals
The project is described as a hackathon submission.
- Evidenced claim: The product was submitted to the OpenAI 2026 hackathon.
- Not evidenced: No evidence of user adoption, customer feedback, revenue, or post-hackathon development.
Competitive Context
No information is provided on competitors or market positioning.
- Not evidenced: No mention of existing tools for converting drawings into 3D geometry or similar AI-powered solutions.
Key Risks & Red Flags
- Risk: The project is a single-person hackathon submission with no evidence of traction, product-market fit, or commercial viability.
- Red flag: Lack of any user feedback, revenue model, or customer data.
- Inferred risk: If the tool is not further developed, it may remain a prototype without real-world utility.
Diligence Questions To Ask The Founders
- What specific technical drawings does the tool support?
- How does the AI process scanned drawings to generate 3D geometry?
- Is there any feedback from users or educators who tested the tool?
- What is the intended monetization strategy, if any?
- Are you planning to develop this beyond the hackathon?
Investment/Partnership Verdict
Not evidenced: No basis for evaluating investment or partnership potential.
- The project is a self-reported hackathon submission with no evidence of traction, revenue, or customer engagement.
- The author has not provided any information on product-market fit, scalability, or commercial viability.
- Confidence level: Low. This is a single-person project in early-stage development with no external validation.
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.