OpenAI 2026 hackathon

so cooked for spanish

My eldest kid needs to pass Spanish. So I've made an interactive game site to help her learn. When I told her, she posted online "so cooked for spanish my dads building me an app to learn it"

Solo project by Andy O'Sullivan · 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 #6,818 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 description states that "so cooked for spanish" is an interactive game site built to help a child learn Spanish, with plans to expand to other languages. The author, Andy O’Sullivan, describes it as a personal project developed using OpenAI's Codex and AWS technologies. It includes two main game modes: "Mysteries" and "Scenarios", which use real-time feedback from OpenAI 5.6. The site is self-reported to be live and deployed, with basic admin tools for content management and usage tracking.

There is no evidence of revenue, customers, or traction beyond the author’s own account. The project appears to be a prototype or early-stage product, likely built as part of a hackathon submission. The single most important open question is whether this project has any commercial viability or user adoption beyond its creator's family.

Back to contents

What The Product Actually Is

The description states that "so cooked for spanish" is an interactive game site designed to help users learn languages through two main game modes:

  • Mysteries: Users work through clues to solve a mystery or crime.
  • Scenarios: Users choose answers as they navigate through scenarios like getting groceries or finding transportation.

Key features include:

  • Real-time feedback on user answers via OpenAI 5.6 calls
  • Support for multiple languages (Spanish, German, French, Irish, Japanese, Italian, Polish, and Lakota where available)
  • Ability to change the language being learned from (e.g., learning Irish while speaking French)
  • Audio listening, translation display, and typing/speaking input options

The description also mentions that the site was built using Codex and deployed on AWS services including Lambda, S3, CloudFront, Route53, API Gateway, WAF, and ACM.

Back to contents

Positioning & Claim Evolution

The author states that the project was inspired by a desire to solve a real problem — helping their child learn Spanish. The name "so cooked for spanish" originated from a TikTok post by the child, which the author found motivating enough to adopt as the official title.

The positioning appears to be:

  • A fun, interactive tool for language learning
  • Built with minimal resources (primarily Codex and AWS)
  • Designed for personal use but potentially scalable

There is no evidence of any formal positioning strategy or market research beyond the author’s own experience. The claim evolution seems to have started with a single child's need and evolved into a broader platform supporting multiple languages, though this expansion is not substantiated by data on usage or demand.

Back to contents

Target Customer & ICP

The description states that the initial target was the author’s eldest child who needed help learning Spanish. Later, the project expanded to include friends of the child, suggesting a broader family-oriented or educational audience.

There is no evidence of:

  • Specific customer segments
  • Demographics beyond age (child/teen)
  • Market research or user personas
  • Any formal identification of ideal customer profile (ICP)

The author implies that the product could be useful for anyone learning a new language, but does not provide any data on who actually uses it or how many people are engaged.

Back to contents

Business Model & Pricing Evidence

The description does not contain any information about:

  • Revenue streams
  • Pricing models
  • Monetization strategies
  • Subscription plans or fees

It is unclear whether the product is free to use, paid, or supported by advertising. The author mentions deploying a local admin page with usage stats and token alerting, but no commercial details are provided.

Back to contents

Technical & Delivery Signals

The description states that the site was built using:

  • OpenAI Codex (primarily)
  • AWS services including Lambda, S3, CloudFront, Route53, API Gateway, WAF, ACM
  • The author used "agentic coding" — giving large tasks to Codex and returning later to check progress

The project is described as being live and deployed. It includes:

  • A local admin page for content changes
  • Usage statistics tracking (user activity and token usage)
  • Email alerting for token thresholds

There is no evidence of:

  • Scalability or infrastructure robustness
  • Security measures beyond WAF
  • Performance metrics or error handling
  • Integration with other platforms or APIs

Back to contents

Traction & Maturity Signals

The description states that the site is live and deployed, and that the author has built additional tools for managing content and monitoring usage. However, there is no evidence of:

  • User engagement or retention
  • Number of active users
  • Revenue generation
  • Customer feedback or reviews
  • Product iteration history beyond initial development

It is unclear whether the product has been used by more than just the creator’s family members.

Back to contents

Competitive Context

The description does not provide any information about:

  • Competitors in the language learning space
  • Market size or competitive landscape
  • Differentiation from existing tools
  • Pricing or feature comparisons

No mention of similar products or platforms that might compete with this one.

Back to contents

Key Risks & Red Flags

Key risks and red flags based on the description:

  • Lack of commercial traction: No evidence of users, revenue, or adoption beyond the author’s family.
  • Unproven scalability: The project appears to be a prototype built for personal use rather than a scalable business.
  • Dependency on external tools: Heavy reliance on OpenAI 5.6 and Codex may create dependency risks if those services change or become unavailable.
  • Limited data on effectiveness: No evidence that the games actually improve language learning outcomes.
  • No formal business model: Unclear how the project intends to generate revenue or sustain itself.

Back to contents

Diligence Questions To Ask The Founders

  1. What specific user feedback have you received from people outside your immediate family?
  2. How do you plan to monetize this product, if at all?
  3. Have you identified any target market segments beyond children and their parents?
  4. What are the technical limitations or dependencies that could affect long-term operation?
  5. Are there any plans for content expansion or localization beyond what is currently available?
  6. How do you intend to scale beyond a single developer (the author)?
  7. What metrics do you track to measure success, and how are they currently performing?

Back to contents

Investment/Partnership Verdict

The description indicates that this is a personal project built by one individual for family use, with no evidence of commercial traction or viability. It is not evident whether the project has any potential for investment or partnership opportunities beyond its current state.

There is insufficient evidence to assess:

  • Market demand
  • Product-market fit
  • Financial sustainability
  • Team capability or scalability

This appears to be an early-stage prototype submitted as a hackathon entry, with no demonstrated path to commercial success. The author states that the site is live and deployed, but there is no data on usage, revenue, or customer engagement.

Verdict: Not evidenced for investment or partnership purposes.

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.