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 #7,291 place in the like-ranked listing is a tie-break inside that group, not a ranking.
Projects (log scale)
Likes on Devpost. ▲ marks this project's group.
Show the figures
| Likes | Projects | Share of archive |
|---|---|---|
| 0 | 5,592 | 71.2% |
| 1 | 1,758 | 22.4% |
| 2 | 285 | 3.6% |
| 3–4 | 132 | 1.7% |
| 5–9 | 75 | 1.0% |
| 10+ | 14 | 0.2% |
Executive Summary
What the company appears to be
Three Notebooks is a self-reported AI-powered productivity tool designed to help users sort mental clutter into past, present, and future categories using natural language input (voice or text). It uses GPT-5.6 for classification and structured outputs, with local browser storage. The product includes features like a White Note for AI interaction without decision-making, Boost for small actions, and Today’s Smile to acknowledge present moments.
What changed
The project evolved from an initial version with basic interface and manual inputs into a more sophisticated tool during Build Week, incorporating voice/text extraction, GPT-5.6 Structured Outputs, editable candidates, bilingual support (English/Japanese), and regression testing.
Single most important open question
Is there evidence of user adoption or engagement beyond the author’s own use and development? The description does not indicate any external users, revenue, or traction data — only self-reported functionality and design decisions.
What The Product Actually Is
The description states that Three Notebooks is a Next.js application using the OpenAI Responses API, GPT-5.6, and Structured Outputs. It allows users to input tasks, plans, feelings, or dreams via speech or text. GPT-5.6 processes this input into editable candidates categorized by cause and direction:
- Past: unfinished work from earlier
- Today: daily life, recovery, rest, enjoyment
- Future: actions creating something new
The user reviews and corrects these classifications before saving them to a ToDo list, timeline chart, or calendar. A White Note feature enables AI interaction without making decisions for the user. Additional features include Boost, which suggests one small action upon request, and Today’s Smile, which prompts users to notice something good in the present.
Data is stored locally in the browser. The public demo supports English and Japanese.
Evidence
- Built with Next.js and OpenAI
- Uses GPT-5.6 for classification and structured outputs
- Input via speech or text
- Local storage only
- Features include White Note, Boost, Today’s Smile
Inference The product is a personal productivity tool, not a commercial SaaS offering.
Positioning & Claim Evolution
The author states that the inspiration behind Three Notebooks was to address how tasks labeled “today” may actually belong to three timelines — past, present, or future. The tool aims to help users reclaim time and emotional space by sorting these items correctly.
It positions itself as a tool for mental clarity, not just task management, emphasizing the importance of distinguishing between what belongs in the past, today, or future. It also emphasizes that AI should support agency without taking decisions away from the user.
Evidence
- “A task labeled ‘today’ may actually belong to three different timelines”
- “Three Notebooks was designed to return that time, attention, and emotional space to the user.”
- “A productivity tool should not only help people do more. It should reveal where their limited attention is going and help them reclaim the ability to live today while still creating a future.”
Inference The positioning has evolved from a personal hackathon project into a conceptual framework for AI-assisted mental organization, with an emphasis on user autonomy.
Target Customer & ICP
The description does not explicitly name or define a target customer. However, it implies that the tool is intended for individuals who struggle with mental clutter and want to better organize their thoughts across time — particularly those who feel overwhelmed by unfinished work from the past affecting their present and future.
It suggests a personal user base, likely self-reported as someone seeking clarity in daily life or productivity.
Evidence
- The tool is described as helping people “reclaim today” and “make room for tomorrow.”
- It targets users who experience mental clutter due to overlapping timelines.
Inference The ICP appears to be individuals focused on personal productivity, mindfulness, or time management, possibly in high-stress or overworked environments.
Business Model & Pricing Evidence
There is no evidence of a business model or pricing structure in the description. The product is presented as a public demo with rate-limiting, but there is no mention of monetization, subscriptions, or paid features.
Evidence
- Public demo exists with rate limiting
- No mention of revenue, pricing, or commercial use
Inference The project is currently in a demo or prototype phase, and no business model has been implemented or described.
Technical & Delivery Signals
Three Notebooks is built using Next.js, integrates with the OpenAI API (GPT-5.6), and uses Structured Outputs for classification. It includes browser speech recognition, local data storage, and supports bilingual English/Japanese input.
Key technical features include:
- Voice/text input processing
- GPT-5.6-based categorization
- Editable candidates
- Regression tests for initialization, saving, reloading, incomplete tasks, and duplicate calendar events
- Local browser storage
The author notes that Codex was used for debugging, testing, Git history management, deployment, and implementation acceleration.
Evidence
- Built with Next.js and OpenAI API
- Uses GPT-5.6 Structured Outputs
- Browser speech recognition
- Local data storage
- Regression tests included
- Bilingual support (English/Japanese)
Inference The tool is a technical prototype, not yet a scalable SaaS product.
Traction & Maturity Signals
There is no evidence of traction, customers, or adoption beyond the author’s own development and use. The project is described as a hackathon submission, and there are no mentions of user feedback, usage metrics, or market validation.
Evidence
- Submitted to OpenAI 2026 hackathon
- Public demo exists but no data on engagement or users
- No revenue, customer base, or adoption metrics
Inference The project is in a pre-product-market-fit stage, with no demonstrated traction.
Competitive Context
There is no mention of competitors or market positioning beyond the author’s own claims. The description does not reference existing tools such as Notion, Todoist, or other AI productivity apps.
Evidence
- No competitor names or references
- No discussion of how it compares to existing solutions
Inference The competitive landscape is unexplored, and no clear differentiation from similar tools is evident.
Key Risks & Red Flags
- No traction or user data: The project is described as a personal tool with no evidence of external adoption.
- Unproven business model: No indication of monetization, pricing, or commercial viability.
- Limited scope: Only local browser storage and no synchronization or backup features are mentioned.
- Self-reported only: All claims are unverified; no third-party validation exists.
- No team or funding: The project is attributed to a single individual (Grandma), with no indication of team size, funding, or investor involvement.
Evidence
- Single-person team
- No revenue or customer data
- No mention of funding or investors
- Public demo only
Inference The risk of market failure or lack of scalability is high due to the absence of traction and a clear path to monetization.
Diligence Questions To Ask The Founders
- What is the actual user base, if any?
- How does the product plan to scale beyond a single-person demo?
- Is there any intention to monetize or build a sustainable business model?
- What are the technical limitations of local browser storage and how will they be addressed?
- Are there plans for broader accessibility testing or localization beyond English/Japanese?
- How does the team plan to validate the product’s utility in real-world use cases?
Investment/Partnership Verdict
Not evidenced.
The description provides no information on financials, traction, customer data, or business model. It is a self-reported hackathon project with no evidence of commercial viability or market validation.
Confidence Low
Reasoning
The project is described as a prototype with no external users, revenue, or funding. It lacks any indication of product-market fit or scalability.
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.