OpenAI 2026 hackathon

Ghostline: City Sprint

Every run has a rival—beat the ghost, improve your line, and climb the city leaderboard.

Solo project by Shakti Pattanaik · 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 #4,312 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

The company appears to be a solo developer project named Ghostline: City Sprint, an Android racing game built during a hackathon using Unity 6 and OpenAI Codex. The author states the goal was to create one fun race with replayability through a ghost-racing system, where players compete against their own best times.

What changed: The description indicates development occurred over time, including during a Build Week event, but no evidence suggests any prior version or iteration beyond this prototype. The project is described as a small prototype with no campaign, car collection, traffic, police, or live multiplayer features.

The single most important open question: Is there any evidence of user engagement or feedback from real players beyond the author's own testing and development?

Analysis basis: Self-reported only. No archived history, third-party verification, revenue data, customer names, or traction metrics are available. All claims in this summary are based on the author’s own description.

Back to contents

What The Product Actually Is

  • The description states that Ghostline: City Sprint is a short Android racing game.
  • It features one car and one city route.
  • Players race against a ghost opponent — their own previous best time becomes the next rival.
  • The game includes basic mechanics such as retrying immediately, recovering if off-road, and comparing times on an online leaderboard.
  • It uses Unity 6 for development and Cloudflare Workers/D1 for backend functionality.
  • Firebase is used only for crash reports.
  • The project is described as a prototype with no campaign, car collection, traffic, police, or live multiplayer features.

Inference: The product is a minimal racing game focused on looped gameplay and competitive replayability. It does not appear to be a full-fledged commercial offering.

Back to contents

Positioning & Claim Evolution

  • The tagline “Every run has a rival—beat the ghost, improve your line, and climb the city leaderboard” positions the game around personal improvement and competition.
  • The author claims the goal was to make one race that players would want to try again.
  • There is no indication of evolving positioning beyond this core concept.
  • The project description does not mention any branding, marketing strategy, or customer acquisition plans.

Inference: Positioning remains static and centered on simplicity and replayability. No evidence of a broader brand or market strategy.

Back to contents

Target Customer & ICP

  • Not evidenced. The description does not identify specific user personas, demographics, or use cases.
  • The author mentions that the game is designed for new players who can start driving immediately.
  • There is no mention of target audience beyond general gamers or mobile users.

Finding: No evidence of defined customer segments or ideal customer profile (ICP).

Back to contents

Business Model & Pricing Evidence

  • Not evidenced. No information about monetization, pricing models, subscriptions, in-app purchases, or revenue streams.
  • The project is described as a prototype with no commercial features.

Finding: No business model or pricing evidence provided.

Back to contents

Technical & Delivery Signals

  • Built with Unity 6.
  • Uses Cloudflare Workers and D1 for leaderboard functionality.
  • Firebase is used only for crash reporting.
  • OpenAI Codex (with GPT-5.6) was used to assist in fixing bugs, improving builds, writing tests, and inspecting logs.
  • The author notes they tested changes manually rather than accepting all suggestions automatically.
  • There are currently 84 passing Unity tests and 18 passing backend tests.
  • Android build is functional and verified.

Inference: Technical delivery shows a working prototype with some automation via AI tools, but no evidence of scalability or production-grade infrastructure.

Back to contents

Traction & Maturity Signals

  • Not evidenced. No data on downloads, active users, retention rates, or user feedback.
  • The project is described as a small prototype.
  • There is no indication of any campaign, marketing, or user engagement beyond the author’s own testing.
  • No mention of beta testing, user trials, or product maturity beyond initial development.

Finding: No traction or maturity signals are evident.

Back to contents

Competitive Context

  • Not evidenced. No mention of competitors, market analysis, or competitive positioning.
  • The description does not reference similar games or platforms in the mobile racing genre.

Finding: No evidence of competitive landscape awareness or differentiation strategy.

Back to contents

Key Risks & Red Flags

  • Solo developer risk: Only one team member is mentioned (Shakti Pattanaik), which may limit scalability and long-term maintenance.
  • Prototype-only status: The project is described as a small prototype with no commercial features, suggesting it has not yet reached market readiness.
  • No user feedback loop: No evidence of real users or feedback mechanisms beyond the author’s own testing.
  • AI dependency risk: Heavy reliance on Codex for development raises questions about whether the solution would be maintainable without AI assistance.
  • Limited scope: The game lacks features like multiple cars, tracks, or multiplayer — potentially limiting appeal.

Inference: High risk of limited viability due to lack of traction, user feedback, and commercialization strategy.

Back to contents

Diligence Questions To Ask The Founders

  1. What is the current status of user testing with real players?
  2. Are there any plans for monetization or revenue generation beyond the prototype stage?
  3. How do you intend to scale beyond a single developer and prototype?
  4. What specific feedback have you received from users during playtesting?
  5. Do you plan to add features like multiplayer, multiple routes, or cars in future versions?
  6. Are there any technical dependencies (e.g., Codex) that could pose risks if access is limited?

Note: These questions are based on the absence of evidence in the description.

Back to contents

Investment/Partnership Verdict

  • Not evidenced. No information about funding, valuation, or partnership interest.
  • The project is described as a solo developer prototype with no commercial traction or revenue.
  • It does not appear to be at a stage suitable for investment or strategic partnership.

Inference: Based on the lack of evidence for traction, business model, or user engagement, there is insufficient basis to recommend investment or partnership.

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.