Willa: Personal PCOS Companion

Company: Willa: Personal PCOS Companion

Self-reported basis: The entire analysis is based on a single project description submitted by the author to the OpenAI 2026 hackathon on Devpost. No independent verification or additional data sources are available.

What the company appears to be: A mobile application designed as a non-judgmental, AI-powered companion for women with PCOS, intended to support day-to-day health decisions and reduce the stigma associated with managing the condition.

What changed: The author describes building this app after using ChatGPT personally to manage her own PCOS symptoms. She identified limitations in existing tools and set out to create a more context-aware, supportive companion that remembers user history and helps translate general advice into actionable steps.

Single most important open question: Is there evidence of real-world usage or feedback from women with PCOS, beyond the author’s personal experience and the app's prototype status?

The description states that Willa is a non-judgmental health coach for women with PCOS, built using React Native and Convex AI Agent component, with an AI backend powered by Vercel AI gateway. It is described as an app that remembers user history, helps spot patterns over time, and supports realistic day-to-day choices without pretending to be a doctor.

The author notes that the app was built using Codex, and that the UI was designed by someone with no coding experience, indicating significant reliance on AI-assisted development tools.

Inference: The product is a mobile application (iOS/Android) that leverages generative AI for conversational support in managing PCOS symptoms. It is not a dashboard or tracking tool but rather an interactive companion focused on context-aware advice and emotional support.

The author positions Willa as a supportive companion between doctor visits, helping users make "realistic everyday choices" without shame or judgment. The app is framed as a personal assistant, not a replacement for medical professionals.

Key claims:

• It helps users remember their story and notice patterns.
• It supports day-to-day decisions like meals, routines, and symptom tracking.
• It avoids stigmatizing topics such as weight or rigid tracking.
• It is designed to reduce shame, not increase it.

The evolution of the positioning appears to be from a personal experiment with ChatGPT to a structured tool for PCOS management, driven by user needs and feedback during its development phase.

Inference: The app’s positioning reflects an attempt to address emotional and practical gaps in existing health tools, particularly around stigma and lack of continuity in conversations.

The description states that Willa is intended for women with PCOS, specifically those who:

• Are managing symptoms like hormonal changes, weight gain, and unwanted hair growth.
• Want support between doctor visits.
• Prefer not to use traditional tracking apps or dashboards.
• Are looking for a non-judgmental space to discuss their health.

The app is described as being built with the goal of making "lifestyle changes" an actual part of life, suggesting it targets users who are already aware of their condition and seeking practical, supportive tools.

Inference: The target customer is a woman with PCOS who wants emotional and practical support in navigating her health journey outside of clinical settings. The ICP likely includes early adopters or individuals deeply engaged with self-management strategies.

There is no evidence of any business model, pricing strategy, monetization plans, or revenue streams mentioned in the description.

The project appears to be a prototype, submitted for a hackathon, and no indication exists that it has moved beyond this stage.

Inference: No commercial structure is evident. The app may eventually seek funding or partnerships, but there is no evidence of current or planned monetization.

The app is built with:

• React Native (Expo)
• Convex AI Agent component
• Vercel AI gateway
• Built using Codex for UI and development

The team size is stated as 2, including two founders: Janet Paul and Ali Zahid.

The project was started on July 18th, and the app was shipped before a hackathon deadline, suggesting rapid prototyping and minimal iteration cycles.

Inference: The technical stack suggests a modern, AI-integrated mobile application. The use of AI tools like Codex indicates a fast development cycle with limited traditional engineering resources.

There is no evidence of any traction or adoption beyond the prototype phase. The app was submitted to a hackathon and has not yet been published on App Store or Google Play.

The description states:

• It was built in a short timeframe (less than a month).
• It was not yet available for public use.
• No user feedback, reviews, or usage metrics are provided.

Inference: The product is at the early prototype stage, with no evidence of real-world deployment or user engagement. It has not reached market maturity.

The description does not mention any direct competitors. However, it implies that existing PCOS apps do not meet user needs because:

• They focus on weight tracking.
• They are judgmental or shaming.
• They don’t remember context between conversations.
• They don’t support day-to-day decision-making.

The author explicitly states that Willa is better than traditional PCOS apps, but does not name them or provide comparative data.

Inference: The app positions itself as a differentiator in the PCOS health space, addressing perceived shortcomings of current tools. However, no competitive landscape is described.

• No commercial traction or revenue: The app has not launched publicly and lacks any evidence of user adoption.
• Unverified claims: All descriptions are self-reported and unverified; there is no independent validation of the app’s utility or impact.
• Prototype-only status: It is a hackathon submission, not a product in development or production.
• Limited team size: Only two people involved, which may limit scalability or long-term viability.
• AI dependency: Heavy reliance on AI tools like Codex and GPT raises questions about consistency, control, and potential limitations of generative models in sensitive health contexts.

Inference: The risk of failure is high due to lack of real-world testing, no monetization strategy, and a prototype-only status. The app may not be ready for market or user feedback.

1. What specific problems with existing PCOS apps did you encounter that led to building Willa?
2. Have you tested the app with actual users (women with PCOS) beyond yourself?
3. How do you plan to ensure the AI responses are safe, accurate, and appropriate for health-related conversations?
4. What is your roadmap for moving from prototype to a full product or service?
5. Are there any plans for partnerships with healthcare providers or organizations focused on PCOS?
6. How do you intend to monetize or scale this product if it gains traction?