OpenAI 2026 hackathon

Chart Dungeon

An AI-powered chart-reading practice RPG where players analyze live market data, clear dungeons, collect gear, and turn their decisions into personalized learning feedback.

Solo project by usrm gray · 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 #3,213 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

Chart Dungeon is a self-reported educational game that combines live market data with an RPG-style dungeon experience to teach chart reading. The author states it is not a trading platform, does not connect to wallets or execute trades, and is strictly for practice.

What changed

The project evolved from an early public-test version into a more polished demo for OpenAI Build Week. Key changes include: a no-account guest dungeon funnel, server-authoritative reward handling, improved chart visibility during gameplay, and AI-assisted development of onboarding and educational elements.

The single most important open question

Is there any evidence of actual user engagement or learning outcomes beyond the author's self-reported claims?

Back to contents

What The Product Actually Is

The description states that Chart Dungeon is "an AI-powered chart-reading practice RPG where players analyze live market data, clear dungeons, collect gear, and turn their decisions into personalized learning feedback."

It combines:

  • Live Coinbase USD market charts
  • Pixel-art dungeon gameplay
  • Evidence-based questions
  • Educational progression through battles

The author describes it as a "strictly educational game" that does not connect to wallets or execute trades.

Not evidenced: The actual mechanics of how chart data translates into gameplay decisions, or whether the AI is used for generating questions or analyzing player behavior.

Back to contents

Positioning & Claim Evolution

The author positions Chart Dungeon as:

  • An alternative to traditional chart education (textbooks or trading terminals)
  • A beginner-friendly way to learn chart reading through gamification
  • A tool that makes market analysis approachable and engaging

The project evolved from an early public-test version into a more polished demo for OpenAI Build Week. The author notes they used AI tools like Codex and GPT-5.6 to extend educational experience, improve user flow, and refine the demo video.

Claims:

  • "Chart education is usually presented as either a textbook or a professional trading terminal. Both can feel intimidating to beginners."
  • "Chart Dungeon is strictly an educational game."

Not evidenced: Whether this positioning resonates with actual users, or if there's evidence of adoption or learning impact beyond the author's claims.

Back to contents

Target Customer & ICP

The description states that Chart Dungeon targets:

  • Beginners who find traditional chart education intimidating
  • People interested in learning chart reading through a gamified experience

It mentions a "no-account guest dungeon funnel" for new players, suggesting an initial focus on low-friction entry.

Not evidenced: Specific customer segments, personas, or user acquisition strategies. No mention of target demographics or market size.

Back to contents

Business Model & Pricing Evidence

The description states:

  • Chart Dungeon is strictly educational and does not connect to wallets
  • It does not accept deposits, execute trades, or provide investment advice
  • It does not charge for access or use

There is no evidence of pricing, monetization, or revenue streams in the self-reported description.

Not evidenced: Any business model, pricing structure, or monetization strategy beyond the author's claim that it’s educational and non-commercial.

Back to contents

Technical & Delivery Signals

The project uses:

  • Frontend: React, TypeScript, Vite
  • Backend: Supabase (authentication, PostgreSQL, Edge Functions), Cloudflare (hosting, AI analysis)
  • Data source: Coinbase USD market charts
  • AI tools: Codex, GPT-5.6, Google Gemma

Key technical decisions:

  • Server-authoritative handling of guest sessions and rewards
  • Idempotent reward processing to prevent duplicate claims
  • Privacy-conscious funnel tracking (no email or user ID collection)
  • Error recovery for expired questions and failed connections

Not evidenced: Performance metrics, scalability, or production stability beyond the author’s description.

Back to contents

Traction & Maturity Signals

The description states:

  • Chart Dungeon existed as an early public-test project before OpenAI Build Week
  • A stable demo deployment is available at https://8e484b64.chartdungeon-buildweek.pages.dev/
  • Live production service is hosted at https://chartdungeon.com
  • Guest dungeon flow works from chart to dungeon, boss, and saved pack

Not evidenced: Any user engagement metrics, retention data, or adoption statistics.

Back to contents

Competitive Context

The author does not reference any direct competitors. The description implies Chart Dungeon is unique in combining live market charts with an RPG-style educational experience.

Not evidenced: Market analysis, competitive landscape, or differentiation from existing chart-reading tools or gamified learning platforms.

Back to contents

Key Risks & Red Flags

Inferences based on the self-reported description:

  • Lack of traction evidence: No data on user engagement, retention, or learning outcomes.
  • AI dependency risk: Heavy reliance on AI tools (Codex, GPT-5.6) for development and content generation raises questions about scalability and consistency.
  • Security vs. UX trade-offs: The approach of server-authoritative rewards while maintaining client-side presentation is complex and may introduce vulnerabilities if not rigorously tested.
  • Non-commercial nature: As a strictly educational tool with no monetization, there’s limited commercial viability or path to growth without additional features or funding.

Not evidenced: Any risk assessments, user feedback, or performance data that would validate these concerns.

Back to contents

Diligence Questions To Ask The Founders

  1. What specific learning outcomes have you observed from users who completed the guest dungeon?
  2. How do you plan to scale beyond a single developer's capacity?
  3. Have you tested the AI tools used for content generation with real users or in production?
  4. Is there any intention to monetize the educational platform, and if so, how?
  5. What is your long-term vision for the product beyond the current demo?

Back to contents

Investment/Partnership Verdict

Not evidenced: No financials, traction data, or clear commercial path.

The author describes Chart Dungeon as a self-contained educational game with no revenue or customer base. It appears to be an early-stage prototype built primarily for demonstration purposes during a hackathon.

Confidence level Low — the description is entirely self-reported and lacks any evidence of traction, users, or commercial viability.

Verdict This project is not ready for investment or partnership consideration based on the provided information. It remains a concept with no demonstrated market or user engagement.

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.