OpenAI 2026 hackathon

Sketch2Latex.

Turn sketches into clean LaTeX.

Solo project by Hamza Imouhne · 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 #1,938 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: Sketch2LaTeX is a self-reported tool designed to convert handwritten sketches into clean LaTeX code for STEM students, teachers, and learners. It allows users to draw diagrams on an interactive canvas or over PDFs, with the goal of generating editable LaTeX output that can be used in technical documents.

What changed: The project was built as part of a hackathon submission, using GPT-5.6 and Codex for development. It is described as a prototype with limited functionality at this stage, focused on core features like an interactive canvas and "Draw Over PDF" capability.

Single most important open question: Is there any evidence of user adoption or traction beyond the author’s own use case? The description does not indicate whether Sketch2LaTeX has been used by others, nor does it provide data on usage, revenue, or customer feedback.

Back to contents

What The Product Actually Is

The description states that Sketch2LaTeX is a platform for turning handwritten notes and sketches into editable LaTeX code. It includes two main features:

  • Interactive Canvas: Users can draw diagrams using various tools including shapes, formulas, and physics-related elements. The system generates LaTeX code that can be copied directly into another project.
  • Draw Over PDF: Users upload an existing PDF and draw over it to preserve dimensions and positioning. This feature allows tracing over handwritten sketches and converting the result into LaTeX.

The platform is built using GPT-5.6 and Codex, with TypeScript as the primary language. It supports LaTeX generation for mathematical, scientific, and engineering diagrams.

Note: The author describes this as a hackathon project, not a commercial product or service yet.

Back to contents

Positioning & Claim Evolution

The author positions Sketch2LaTeX as a solution for STEM students, teachers, and learners who want to convert handwritten notes into clean LaTeX without needing advanced knowledge of TikZ or TeX. It is framed as an accessible alternative to manual LaTeX writing or less accurate AI tools like GPT-5.4.

Key claims include:

  • The tool helps users avoid the slow and difficult process of creating diagrams with TikZ.
  • It leverages GPT-5.6 for development, suggesting a modern, AI-driven approach.
  • It aims to become a complete visual workspace for creating professional STEM documents without requiring LaTeX expertise.

Inference: The positioning suggests a niche market focused on education and technical documentation, but no evidence of actual market validation or competitive differentiation beyond the author’s personal experience.

Back to contents

Target Customer & ICP

The description identifies three primary user groups:

  • Students working in mathematics, physics, and engineering.
  • Teachers preparing worksheets, lessons, and technical documents.
  • Learners turning visual ideas into editable technical notation.

Note: No evidence of segmentation or targeting beyond these broad categories. There is no indication of specific customer personas, usage patterns, or feedback from target users.

Back to contents

Business Model & Pricing Evidence

There is no mention of pricing, monetization strategy, or business model in the description. The project is presented as a hackathon prototype with no indication of revenue streams or paid features.

Inference: The lack of any commercial detail suggests that this is not yet a viable product for sale or licensing.

Back to contents

Technical & Delivery Signals

The platform was built using:

  • GPT-5.6 (for planning, coding, debugging)
  • Codex
  • TypeScript
  • Terra and Sol (used in implementation)

Key technical elements include:

  • An interactive canvas with drawing tools.
  • A PDF workflow that preserves dimensions and positioning.
  • LaTeX generation capabilities.

Challenges mentioned include:

  • Making the interface intuitive while maintaining keyboard shortcuts expected from design applications.
  • Handling differences between European and international conventions in diagrams.
  • Ensuring generated elements are easily editable after placement.
  • Generating accurate LaTeX code that maintains PDF element positions.

Inference: The use of AI tools like GPT-5.6 indicates a rapid development process, but no evidence of scalability or production-grade architecture.

Back to contents

Traction & Maturity Signals

The project is described as a hackathon submission, with no evidence of:

  • Revenue
  • Customers
  • User engagement metrics
  • Product adoption beyond the author’s personal use
  • Any form of market testing or feedback

Absence of evidence: There are no signs of traction, growth, or user validation.

Back to contents

Competitive Context

No mention is made of competitors or existing solutions in the space. The description does not reference other tools for converting sketches to LaTeX or diagramming software.

Absence of evidence: No competitive landscape or differentiation strategy is evident.

Back to contents

Key Risks & Red Flags

  • Unproven market demand: No evidence of customer traction or real-world usage.
  • Prototype status: The project is described as a hackathon submission, not a developed product.
  • Limited team size: Only one member (Hamza Imouhne) is listed, which may limit execution capacity.
  • No commercial viability: No pricing, monetization, or business model details provided.
  • Dependency on AI tools: Heavy reliance on GPT-5.6 and Codex raises questions about long-term sustainability or scalability.

Inference: The lack of any commercial or user-facing signals makes it difficult to assess whether this will evolve into a viable product.

Back to contents

Diligence Questions To Ask The Founders

  1. What specific problems are you solving for your users, and how do you know they exist?
  2. Have you tested the tool with actual students or teachers? If so, what were their reactions?
  3. How do you plan to monetize this product if it becomes a full-fledged platform?
  4. What is your roadmap beyond the hackathon prototype?
  5. Are there any existing tools in the market that perform similar functions, and how would you differentiate yourself?

Back to contents

Investment/Partnership Verdict

Not evidenced.

There is no evidence of revenue, traction, or customer validation to support an investment or partnership decision at this stage. The project remains a self-reported hackathon prototype with no indication of commercial viability or market readiness.

Confidence level: Low — based entirely on unverified self-reporting and no external data.

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.