OpenAI 2026 hackathon

Scenariocraft

My kids (7, 10, 17) aren't players - they're co-creators: inventing scenarios, setting rules, auditing the GPT judges. Codex turns their words into real Minecraft games. Imagination, shipped on repeat

Solo project by agorokh Gorokh · 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 #6,555 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

Scenariocraft is a self-reported family-oriented project that enables children and parents to co-create digital games using AI agents (specifically Codex) and Minecraft. The author describes it as an experiment in family collaboration, where kids invent game ideas and an AI agent builds them.

What changed

The project was developed over a weekend during a hackathon, with the author stating that it began as a family experiment to allow children to become creators rather than consumers of games. It evolved from a prototype into a repeatable process involving GitHub issues, Codex-driven development, and AI referees.

Single most important open question

Is there evidence of any real-world adoption or traction beyond this single-family experiment? The description contains no data on usage, customers, revenue, or product-market fit beyond the author’s own account.

Back to contents

What The Product Actually Is

The description states that Scenariocraft is a system that turns children's game ideas into playable Minecraft games using AI tools like Codex and ChatGPT. It includes:

  • A repeatable loop where kids invent scenarios, the family specs them together, an agent builds them, and an AI panel referees.
  • A reference scenario called "Speed Build", which is described as a party game for Paper Minecraft servers.
  • The use of GitHub issues to track development, with Codex implementing features via pull requests.
  • An AI judge system (GPT-5.6) that evaluates builds based on rubrics like theme, creativity, effort, and detail.

The product is not described as a commercial offering or a scalable platform but rather as an experiment in family collaboration using AI tools.

Inference: Based on the author's description, Scenariocraft appears to be a proof-of-concept tool for enabling children to co-create digital games with AI assistance. It is not yet a product with a defined market or monetization strategy.

Back to contents

Positioning & Claim Evolution

The author positions Scenariocraft as an experiment in redefining how children engage with digital play — shifting from consumption to creation, using AI agents like Codex and ChatGPT.

Key claims include:

  • The project allows families to stop being consumers of games and become creators.
  • It enables a repeatable loop where kids invent, the family specs it, an agent builds it, and AI referees it.
  • The goal is to create “family rituals” through digital game creation.

There is no indication that Scenariocraft has evolved beyond this initial experiment or that it has moved toward commercial positioning. It remains framed as a personal project with family-oriented goals.

Claim: Scenariocraft aims to empower children to invent and build games using AI tools.

Inference: The positioning is rooted in family engagement, not market expansion or product scalability.

Back to contents

Target Customer & ICP

The description states that the target customer is families with children aged 7, 10, and 17. These are described as active participants in the game creation process:

  • The 7-year-old invents challenges and audits judges.
  • The 10-year-old designs the game and contributes to branding.
  • The 17-year-old provides engineering support through Codex.

There is no evidence of any broader customer base beyond this single family. No external users, partners, or customers are mentioned.

Claim: Scenariocraft targets families with children who want to co-create digital games.

Inference: The ICP is narrow and limited to a specific demographic — a single family engaged in creative play.

Back to contents

Business Model & Pricing Evidence

There is no evidence of any business model or pricing structure. The project is described as an experiment, not a commercial product. No revenue streams, subscriptions, or monetization methods are mentioned.

Claim: There is no stated business model or pricing.

Inference: The lack of any financial or commercial framework suggests this is a non-commercial prototype.

Back to contents

Technical & Delivery Signals

The author reports:

  • Use of GitHub for issue tracking and pull request-based development.
  • Codex as the primary tool for implementing game features.
  • A Docker-based deployment system that allows strangers to run the game in about ten minutes.
  • A deterministic voxel renderer for AI judges to evaluate builds.
  • GPT-5.6 judges with a fail-closed quorum to ensure fairness.

There is no mention of scalability, infrastructure, or production-grade delivery mechanisms beyond this single-family project.

Claim: The technical stack includes GitHub, Codex, Docker, and custom AI judge systems.

Inference: The technical approach is experimental and not scalable beyond the author’s immediate use case.

Back to contents

Traction & Maturity Signals

There is no evidence of traction or maturity beyond the single-family experiment. No users, customers, or adoption metrics are provided. The project is described as a weekend hackathon effort with no indication of ongoing development or market interest.

Claim: Scenariocraft has no demonstrated traction or user base.

Inference: The product remains in early-stage experimentation and lacks any signs of commercial viability or growth.

Back to contents

Competitive Context

The description does not mention any competitors. It is unclear whether there are existing tools or platforms that enable similar family-based game creation using AI. No market analysis or competitive positioning is provided.

Claim: No competitive context is described.

Inference: Without reference to other players, it’s impossible to assess how Scenariocraft fits into the broader ecosystem of AI-powered creative tools or family games.

Back to contents

Key Risks & Red Flags

  • Lack of commercial viability: The project is framed as a family experiment with no indication of scalability or monetization.
  • No external validation: There are no users, customers, or third-party endorsements.
  • Unproven market demand: No evidence that there is a broader market need for this type of product.
  • Limited scope: The entire system is built around one family’s experience and lacks generalizability.

Inference: Scenariocraft appears to be an experimental tool with no clear path to commercialization or market traction.

Back to contents

Diligence Questions To Ask The Founders

  1. What is the intended long-term vision for Scenariocraft beyond this family experiment?
  2. Are there any plans to expand beyond a single family or to build a product that others can use?
  3. How do you plan to validate demand from users outside of your own family?
  4. Have you considered how to scale the AI-driven development process for broader adoption?
  5. What would constitute success for this project, and how will you measure it?

Back to contents

Investment/Partnership Verdict

There is no evidence that Scenariocraft has reached a stage where it could be considered for investment or partnership. It remains an experimental family project with no demonstrated traction, revenue, or commercial framework.

Claim: Scenariocraft is not currently suitable for investment or partnership.

Inference: The lack of any measurable impact, user base, or business model makes it a high-risk, unproven opportunity at this stage.

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.