OpenAI 2026 hackathon

Outside the box

Capture the thought. Sleep on it.

Solo project by Sachithra Sayuranga Jayasinghe · 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 #5,779 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

Company: Outside the Box

Self-reported purpose: A mobile-first nighttime thought-capture app designed to allow users to save ideas without seeing the time or being distracted by notifications. The app uses AI in the morning to organize thoughts into titles, cleaned-up versions, and next steps.

What changed: The author describes a personal problem — capturing ideas at night without being pulled into phone distractions — and built a prototype to solve it. It was submitted as a hackathon project.

Single most important open question: Is there a meaningful user need beyond the author’s personal experience, and how would this product scale or monetize if it were to move beyond a prototype?

Back to contents

What The Product Actually Is

The description states that Outside the Box is:

  • A mobile-first web application
  • Designed for nighttime thought capture
  • Uses a dark interface to avoid showing time or distractions
  • Allows users to save thoughts while the app remains open beside their bed
  • Preserves original wording and uses AI in the morning to organize thoughts into:
    • A title
    • A clearer version of the thought
    • One next step

The app is built with:

  • Next.js, React, TypeScript, Tailwind CSS
  • OpenAI Responses API, Structured Outputs, Zod validation
  • browser localStorage for storage
  • GitHub and Vercel for deployment
  • Codex for development assistance

It is described as a prototype, not yet requiring an account or cloud database. The current version stores data locally on the user’s device.

Inference: The app is a minimal, privacy-focused tool that leverages AI to enhance thought capture after it has been saved, rather than being an AI-first product.

Back to contents

Positioning & Claim Evolution

The description states:

  • The app was inspired by the author's personal experience of capturing ideas at night.
  • It aims to avoid time reminders and phone distractions during sleep.
  • The core positioning is: “Capture the thought. Don’t see the time.”
  • The app does not claim to be productivity-focused, but rather to give users permission to let go of thoughts they’ve captured.

Inference: The product evolved from a personal solution into a public prototype, with a focus on emotional benefit (letting go of thoughts) over functional productivity.

Back to contents

Target Customer & ICP

The description states:

  • The app targets people who have ideas at night.
  • It is designed for users who want to avoid distractions and time reminders while capturing thoughts.
  • The intended user experience is for someone to open the app before sleeping, leave it running, and capture thoughts during the night.

Inference: The ICP is likely a subset of people with high cognitive load or creative thinking patterns who are sensitive to phone interruptions at night. No explicit demographic or persona data is provided.

Back to contents

Business Model & Pricing Evidence

The description states:

  • The app currently uses localStorage for storage.
  • It does not require an account or cloud database.
  • There is no mention of pricing, monetization, or business model.
  • The author notes that the next version may include features like exports to productivity tools and deeper AI development.

Inference: No evidence of a business model or pricing structure. The current prototype is self-contained with no commercial layer.

Back to contents

Technical & Delivery Signals

The description states:

  • Built using Next.js, React, TypeScript, Tailwind CSS
  • Uses OpenAI API for structured outputs and Zod validation
  • Implements browser localStorage for privacy
  • Deployed via Vercel with GitHub integration
  • Uses Codex for development assistance
  • The app has three main states: night, capture, morning

Inference: The technical stack is modern and well-suited to a web-based prototype. The use of structured AI output and validation shows attention to quality control.

Back to contents

Traction & Maturity Signals

The description states:

  • This is a hackathon submission.
  • It is a prototype with no revenue, customers or adoption data.
  • The author built it in a short time despite limited prior experience with some technologies.
  • No evidence of user testing, retention, or usage metrics.

Inference: No traction or maturity signals. The product is at the prototype stage and not yet in production use.

Back to contents

Competitive Context

The description does not mention any competitors.

Inference: No competitive context provided. It is unclear whether similar products exist or how this one would differentiate.

Back to contents

Key Risks & Red Flags

  • No commercial traction or user data: The product is a prototype with no evidence of adoption or revenue.
  • Unproven market need: The author’s personal experience is the only evidence of demand.
  • Limited scalability: The app currently uses localStorage and does not support cloud sync or multi-device access.
  • AI dependency without clear value: The AI is used in the morning, but its utility is not demonstrated beyond the prototype.
  • No monetization path: No indication of how this would become a sustainable business.

Back to contents

Diligence Questions To Ask The Founders

  1. What evidence do you have that others share your personal experience of needing to capture thoughts at night?
  2. How do you plan to scale beyond a single-user, local-storage prototype?
  3. What is the expected user journey for someone who wants to use this product long-term?
  4. Are there any plans to integrate with existing productivity or note-taking tools?
  5. How would you monetize this product if it were to evolve into a commercial offering?

Back to contents

Investment/Partnership Verdict

Self-reported basis only: This is a hackathon prototype with no evidence of traction, revenue, or customer adoption.

Confidence level: Low

Verdict: Not ready for investment or partnership. The idea has emotional resonance and technical execution, but lacks commercial viability signals. It would require significant development to become a product with market appeal or monetization potential.

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.