OpenAI 2026 hackathon

Chronorama

Learn about Human history by interacting in various 3d dioramas as a " hands on " way of learning about our common history, powered by LLMs.

Solo project by B D · 0 likes · 0 comments

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 #3,243 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

Chronorama is described as an educational 3D web experience that allows young learners to explore historical periods through interactive dioramas. The product uses LLMs for character dialogue and is built using AI-assisted development tools like OpenAI Codex Work, GPT-5.6 Sol, and Three.js. It is presented as a prototype created in two to three hours by one person, with the goal of combining immersive exploration, game mechanics, and open-ended AI dialogue to teach history.

The author states that the core concept has been demonstrated in a hackathon prototype containing two playable dioramas: Neolithic villages and Ancient Egypt. The experience includes movement, interaction with objects, problem-solving, and character-based LLM dialogue, all within historical contexts designed to be age-appropriate and grounded in curated knowledge bases.

What Changed: This is a solo hackathon project submitted to the OpenAI 2026 hackathon. No prior version or commercial product exists beyond this prototype.

Single Most Important Open Question: Is there evidence that young learners engage with the experience, find it meaningful, and retain historical knowledge through play? The description does not provide any data on user testing, engagement metrics, or learning outcomes.

Back to contents

What The Product Actually Is

The description states that Chronorama is an educational 3D web experience in which users interact with historical dioramas using a browser-based interface. It includes:

  • Interactive exploration of 3D environments;
  • Dialogue with historical characters powered by LLMs;
  • Object manipulation and crafting mechanics;
  • Quest-based learning;
  • A journal system for discoveries.

It is built using:

  • OpenAI Codex Work and GPT-5.6 Sol for AI-assisted development;
  • Three.js, React Three Fiber, and Drei for 3D rendering;
  • TypeScript, React, and Vite for frontend infrastructure.

The experience is designed to be playable in a web browser, with no external hardware required. It does not include a separate chatbot but instead integrates LLM dialogue directly into character interactions.

Claim: The product is an immersive 3D educational platform.

Evidence: The description states the product uses 3D environments, interactive elements, and LLM-powered character conversations.

Back to contents

Positioning & Claim Evolution

The author positions Chronorama as a modern, playable pop-up history book. It aims to make learning history more engaging by allowing users to step inside historical worlds rather than read about them.

Key claims include:

  • Learning history through exploration and play;
  • Combining game mechanics with educational content;
  • Using LLMs to support curiosity-driven learning;
  • Making history accessible and personal for young learners.

The project is described as evolving from a previous VR language-learning app, suggesting an evolution in how digital environments can be used for education.

Claim: Chronorama is positioned as a new kind of educational tool that blends immersion, interactivity, and AI.

Evidence: The description compares it to a “playable pop-up history book” and references prior work in VR language learning.

Back to contents

Target Customer & ICP

The target customer is described as young people, particularly those who may be more engaged by games like Minecraft than traditional history lessons. The experience is intended for learners aged around 10–16 years old, based on the age-appropriate tone and design choices.

It is designed to appeal to:

  • Students in primary or secondary education;
  • Educators looking for innovative teaching tools;
  • Parents or caregivers interested in educational games.

The ICP appears to be young learners who benefit from experiential and curiosity-driven learning, with a focus on historical understanding through play.

Claim: The target is young learners seeking immersive, game-based history education.

Evidence: The description mentions “young people,” “age-appropriate level,” and references the need for engagement over memorization.

Back to contents

Business Model & Pricing Evidence

There is no evidence of a business model or pricing structure in the project description. The product is described as a hackathon prototype with no mention of monetization, licensing, or distribution plans.

Claim: No commercial model or pricing information is provided.

Evidence: The description does not reference any revenue streams, subscriptions, sales, or partnerships.

Back to contents

Technical & Delivery Signals

Chronorama is built using:

  • AI-assisted development tools (Codex Work, GPT-5.6 Sol);
  • Web-based 3D rendering with Three.js and React Three Fiber;
  • TypeScript, React, Vite, HTML/CSS for UI;
  • OpenAI APIs for dialogue generation.

It is a browser-based experience, not requiring native apps or hardware. The prototype was built in approximately two to three hours by one developer.

Claim: The product uses modern web technologies and AI tools for rapid prototyping.

Evidence: The description lists the tech stack and mentions AI-assisted development.

Back to contents

Traction & Maturity Signals

The project is described as a hackathon prototype with no evidence of traction, users, or adoption. It was built in two to three hours by one person and has not been tested with real learners beyond internal iteration.

Claim: No traction or user data is reported.

Evidence: The description states that the experience is untested with real users, and no metrics, customers, or usage data are provided.

Back to contents

Competitive Context

The author does not reference any competitors. However, based on the description, potential categories include:

  • Educational game platforms;
  • Immersive history apps or VR experiences;
  • AI-powered learning tools for children.

No direct competitor names or products are mentioned.

Claim: No competitive landscape is described.

Evidence: The description does not name any competitors or reference existing similar tools.

Back to contents

Key Risks & Red Flags

Key risks include:

  • Lack of user testing or validation — the experience has not been tested with real learners;
  • Unproven educational impact — no data on learning outcomes or retention;
  • Dependency on AI quality — reliance on LLMs for dialogue may lead to inconsistent or inaccurate responses if not carefully curated;
  • Prototype limitations — the product is described as incomplete, with UI and 3D fidelity needing refinement;
  • No commercialization plan — no evidence of a path to market or monetization.

Claim: Risks include lack of testing, AI reliability, and unproven impact.

Evidence: The description highlights challenges in UI design, LLM grounding, and the prototype nature of the product.

Back to contents

Diligence Questions To Ask The Founders

  1. What were the results of any internal playtesting with young learners?
  2. How is historical accuracy ensured when using LLMs for character dialogue?
  3. Are there plans to expand beyond the two current dioramas, and what is the roadmap?
  4. Has the team considered how to scale this experience for broader educational use?
  5. What are the technical limitations of the current prototype that would need to be addressed before release?

Back to contents

Investment/Partnership Verdict

Not evidenced.

The project is described as a hackathon prototype, with no evidence of traction, revenue, or commercial viability. The author states that the real value will only become clear through playtesting, which has not yet occurred.

Claim: No investment or partnership potential is evident.

Evidence: The description does not include any data on users, customers, funding, or market readiness.

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.