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 #3,520 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
The project described as cookedUserStory is a self-reported tool that converts informal purchasing requests into structured, evidence-backed recommendations. It operates through four stages: describe, confirm, compare, and recommend. The system uses AI for interpreting user needs and retrieving product data, but makes deterministic decisions based on structured scoring.
What changed
The author states this was originally built as a hackathon prototype and has since evolved into a portfolio project with plans to complete provider integrations and expand functionality.
Single most important open question
Is there any evidence of traction, revenue, or customer adoption beyond the author's own development efforts?
What The Product Actually Is
The description states that cookedUserStory is a system that guides users through four stages:
- Describe: User enters a purchasing need in natural language.
- Confirm: System extracts structured requirements (category, mandatory criteria, preferences, weights).
- Compare: Three candidate products are evaluated using structured product specifications and supporting evidence.
- Recommend: Provides a deterministic recommendation with explanations of trade-offs, missing or conflicting information, and links back to sources.
It supports three product categories: laptops, air purifiers, and laboratory ovens. Each product is assigned one of three qualification states:
- qualified
- disqualified
- needs_confirmation
The system uses weighted scoring (S = Σ(s_i × w_i)) where scores are from 0 to 10 and weights are user-editable.
Evidence
- The author describes the workflow stages.
- It supports specific product categories.
- It includes a scoring mechanism with mandatory requirements and preference weights.
- It distinguishes between live, cached, fixture, synthetic, calculated, missing, and conflicting claims.
Inference The system is designed to be deterministic in its decision-making process, relying on structured data rather than AI-generated choices alone.
Positioning & Claim Evolution
The description states that the tool treats purchasing decisions like engineering decisions — defining requirements, gathering evidence, identifying uncertainties, comparing alternatives consistently, and explaining recommendations.
It positions itself as a system that:
- Turns vague buying requests into structured decision briefs.
- Provides transparent, evidence-backed recommendations.
- Highlights missing or conflicting information.
- Links results back to sources.
Evidence
- The author claims it "converts an informal purchasing need into a structured, evidence-aware decision brief."
- It aims to avoid generic product lists or sponsored rankings.
- It emphasizes transparency in how recommendations are made.
Inference The tool is positioned as a decision-support system that prioritizes clarity and traceability over convenience or marketing-driven suggestions.
Target Customer & ICP
The description does not explicitly state who the target customer is. However, it implies a user base that:
- Makes purchasing decisions involving technical products.
- Values structured information and evidence-based choices.
- May be engineers, researchers, or professionals seeking reliable product comparisons.
Evidence
- The example use case involves an engineering need for a laptop.
- It supports laboratory ovens, suggesting a scientific or industrial audience.
- The system is built to handle complex technical requirements.
Inference The ICP likely includes users who make high-stakes purchasing decisions and require detailed, verifiable product comparisons.
Business Model & Pricing Evidence
There is no evidence in the description of any business model or pricing strategy. The project is described as a prototype developed by one person for a hackathon and later continued as a portfolio piece.
Evidence
- No mention of monetization.
- No indication of pricing tiers or subscription models.
- No reference to customer acquisition or retention strategies.
Inference The business model remains undefined. It may be intended for personal use, future commercialization, or educational purposes.
Technical & Delivery Signals
The project was built as a single Next.js and TypeScript application using the App Router. The architecture separates responsibilities among:
- AI& (interprets user request)
- Oxylabs (retrieves public product data)
- Doubleword (converts content into validated claims)
- Local TypeScript scoring
- Daytona (executes scoring in sandbox)
- Nosana (reviews evidence quality)
The system distinguishes between different types of data and handles provider failures gracefully.
Evidence
- Built with Next.js, TypeScript.
- Uses App Router.
- Integrates five external services with defined roles.
- Handles failures safely without crashing the application.
- Supports live execution paths for some providers but uses fallbacks where needed.
Inference The technical stack and architecture suggest a modular, robust system designed to manage complexity and uncertainty in data retrieval and processing.
Traction & Maturity Signals
There is no evidence of traction or adoption beyond the author’s own development. The project is described as a prototype built during a hackathon and later continued as a portfolio project.
Evidence
- No revenue, ARR, or customer base mentioned.
- No mention of user testing or feedback loops.
- No indication of product-market fit or market validation.
Inference The system has not yet demonstrated real-world usage or commercial viability.
Competitive Context
The description does not provide any information about competitors. It does not reference existing tools in the space of purchasing decision support, AI-driven shopping assistants, or structured recommendation engines.
Evidence
- No mention of competitive landscape.
- No comparison to other platforms or services.
Inference There is no evidence of awareness of or competition from similar offerings.
Key Risks & Red Flags
Several risks and red flags are present based on the self-reported description:
- No traction or revenue: The system has not been validated in a real-world setting.
- Unproven scalability: Only one developer is involved, and the project is described as a hackathon prototype.
- Incomplete integrations: Some components (Daytona, Nosana) are not fully functional in live mode.
- Unclear monetization path: No business model or pricing strategy is evident.
- Limited product scope: Only three categories supported currently.
Evidence
- The author states that the project was built for a hackathon and later continued as a portfolio piece.
- Some integrations are still in development or use fallbacks.
- No evidence of real-world usage or feedback.
Inference This is an early-stage idea with limited validation, potentially risky from a commercial perspective.
Diligence Questions To Ask The Founders
- What is the expected timeline for completing all provider integrations?
- Are there any plans to monetize this tool? If so, how?
- How do you plan to validate the accuracy and reliability of the evidence gathered from external sources?
- Have you considered how to scale beyond a single developer?
- What are your thoughts on expanding into new product categories or markets?
- How will you handle edge cases such as missing mandatory data or conflicting claims?
Investment/Partnership Verdict
There is no evidence of traction, revenue, or customer adoption. The project is described as a hackathon prototype that has since been continued as a portfolio piece.
Evidence
- No financials, customers, or usage metrics provided.
- No indication of market validation or product-market fit.
- Only one team member involved.
Inference At this stage, the project lacks commercial viability indicators and is more of an experimental idea than a ready-to-invest or partner opportunity. It may be suitable for incubation or early-stage funding if further development shows promise, but it does not currently meet criteria for investment or partnership consideration based on the available information.
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.