DUP - Food tracker for women

What the company appears to be: DUP is a self-reported food-tracking application for women that integrates menstrual cycle data with nutritional intake and personalized recommendations. The app is built as a bilingual (English/Spanish) progressive web app (PWA), using Next.js, React, TypeScript, and Supabase. It includes features such as meal logging, cycle tracking, goal setting, and a GPT-5.6-powered coaching assistant.

What changed: The project was submitted to the OpenAI 2026 hackathon on Devpost. The author describes it as an evolution from generic food trackers, aiming for a more supportive and contextual approach to nutrition that accounts for hormonal changes and personal habits.

Single most important open question: Is there evidence of user adoption or engagement beyond the single developer's test environment?

The description states that DUP is a bilingual (English/Spanish) PWA designed for food logging, menstrual-cycle context, and nutrition goals. It allows users to log meals, track their cycle, receive practical food ideas based on current phase, set body data and macro goals, and use a "DUP Coach" feature powered by GPT-5.6.

It is built with Next.js, React, TypeScript, and Supabase, and supports guest-first workflows with local persistence for signed-in users. The app uses mobile-first navigation and includes structured interactions (e.g., radio-style choices) to guide users through goal setup and food logging.

The author claims the product was developed using Codex as an implementation collaborator and that GPT-5.6 is used server-side via OpenAI API for coaching guidance, but does not make medical or fertility predictions.

The author states that DUP began with a question: “What would a food tracker look like if it treated a woman’s menstrual cycle, energy, training, mood, and real eating habits as part of the same picture?”

It positions itself as an alternative to "rules-heavy diet apps" — aiming for a calmer, more supportive tone, without shaming or offering false certainty. The app is described as being user-centered, starting with what someone already eats and adjusting from their own data rather than prescribing a perfect diet.

The evolution of the positioning appears to be from a generic food tracker to one that integrates hormonal context into nutrition advice, using practical examples instead of complex vocabulary.

The description indicates that DUP is intended for women who want to train, feel more supported by food, and understand their own patterns without being shamed or given fake certainty.

It also targets users who are interested in understanding their body’s needs during different phases of the menstrual cycle, and those looking for a more personalized approach to nutrition than standard calorie-counting tools.

The author notes that the app was inspired by a friend struggling with weight loss, suggesting a target audience that may include individuals seeking guidance or support around body transformation.

Not evidenced. The description does not provide any information on pricing models, monetization strategies, or business structure beyond the fact that it is a self-developed PWA.

The app is built using Next.js, React, TypeScript, and Supabase, with a responsive PWA shell and mobile-first navigation. It supports both English and Spanish languages at the interaction level.

Key technical elements mentioned:

• Guest-first local workflows
• Supabase persistence for signed-in food, history, and cycle records
• Use of GPT-5.6 via OpenAI API for coaching guidance
• Implementation with Codex as a collaborator

The author reports using Codex to implement interactions, diagnose deployment issues, write documentation, and translate feedback into product changes.

Not evidenced. There is no mention of users, customers, revenue, or usage metrics beyond the developer’s own testing and feedback from a real-user test.

The project was submitted to a hackathon, indicating early-stage development rather than a mature product in the market.

Not evidenced. The description does not reference competitors or existing solutions in the space of menstrual-cycle-aware food tracking or women's health nutrition apps.

• Single developer team: Only one member listed (Esteban Saa), which raises concerns about scalability and long-term maintenance.
• Unverified claims: The app makes several claims about user experience, tone, and effectiveness that are based on self-reported feedback from limited testing.
• Use of GPT-5.6: While the author notes that the AI does not make medical claims, there is no indication of how this is enforced or audited in practice.
• No commercial traction: No evidence of revenue, customers, or adoption beyond the developer’s own experience and a small test group.
• Limited scope: The app focuses on food logging and cycle context but lacks features like integration with wearables, advanced analytics, or community elements.

1. What specific user feedback did you gather from your real-user test, and how was it incorporated into the product?
2. How do you plan to scale beyond a single developer’s capacity?
3. Are there any plans for monetization or revenue models?
4. What safeguards are in place to ensure that GPT-5.6 does not inadvertently provide medical advice or fertility-related guidance?
5. How do you intend to validate the accuracy of nutritional recommendations and cycle-based insights?