CareCompass Kids

What the company appears to be: CareCompass Kids is a self-reported mobile prototype for iOS and Android, built by one developer (Wonah Choi), that aggregates and displays pediatric urgent-care wait times in the San Francisco Bay Area. It presents provider-published wait information with clear labeling of missing, stale, or unavailable data. The app uses Google Maps for discovery, GPT-5.6 for a navigator feature, and a React Native/Express.js architecture.

What changed: The project is described as a hackathon submission (Devpost entry) that evolved from an initial idea to a working prototype. It was built using Expo SDK 54, TypeScript, and includes a monorepo with mobile app, Express API, and shared packages. Key changes included moving from Expo SDK 52 to 54, replacing WebView-based maps with native react-native-maps, and implementing structured validation for data sources.

Single most important open question: Is there any evidence of traction, revenue, or customer adoption beyond the author's own development and testing?

Note: This analysis is based entirely on the self-reported description provided by the author. No third-party verification, archived data, or independent sources are available. All claims in this report are labeled as "the description states" unless otherwise noted.

The description states that CareCompass Kids is an Expo iOS and Android prototype for the San Francisco Bay Area. It allows users to:

• Use approximate device location or enter a ZIP code
• Choose a 10-, 20-, or 30-mile radius
• Explore nearby urgent care on a native map and proximity-ordered directory

Each result displays one of four clear states:

• A current provider-published wait
• A stale previous wait
• A temporarily unavailable source
• A prominent “Wait time not available” message

The app also shows:

• Provider update times, Google-listed hours, and CareCompass check times (separately labeled)
• Emergency departments are clearly excluded from urgent-care ranking and GPT comparisons
• A Guidelines tab with general information about when to seek urgent vs. emergency care

Inference: The product is a mobile app focused on source-transparent wait-time comparison for pediatric urgent care, built as a prototype using React Native and Expo.

The description states that the project was inspired by personal experience with long waits at urgent care facilities when caring for children. It aims to reduce the search cost of finding nearby urgent care by consolidating provider-published wait information into one view, while clearly labeling missing or stale data.

Inference: The positioning is centered on transparency and honesty in healthcare data, rather than completeness or estimation. The author emphasizes that the app does not generate estimates but instead flags when wait times are unavailable or outdated.

The description states that CareCompass Kids targets families with children who need urgent care, especially those:

• Searching for nearby clinics
• Traveling and unfamiliar with local healthcare systems
• Wanting to avoid long, uncertain waits

It is explicitly designed for pediatric urgent care, not adult or emergency services.

Inference: The target customer is a parent or guardian seeking timely pediatric care in the San Francisco Bay Area, with a focus on transparency over convenience or booking features.

Not evidenced. The description does not mention any pricing model, monetization strategy, or business model. It is described as a prototype built for a hackathon.

The description states that the app was built using:

• Expo SDK 54
• React Native
• TypeScript
• Express.js API
• Google Maps Platform
• GPT-5.6 (server-side Responses API)
• Codex and ChatGPT-5.6 for development assistance

Key technical features include:

• Native map implementation
• Provider-specific adapters that retrieve only public, non-identifying information
• Structured output constraints on GPT-5.6 to prevent clinical advice or diagnosis
• Runtime validation and schema versioning to avoid crashes
• A fallback mechanism when GPT is unavailable

Inference: The technical stack suggests a lightweight, mobile-first prototype with strong emphasis on safety, data integrity, and source transparency.

Not evidenced. There is no mention of:

• Revenue
• Customers
• Usage metrics
• Product adoption
• Any form of traction beyond the author’s own development and testing

The project is described as a prototype built for a hackathon, with no indication of production deployment or market validation.

Not evidenced. The description does not mention:

• Competitors
• Market size
• Existing solutions in the pediatric urgent-care wait-time space

It only states that the app aims to reduce search cost and improve transparency, without comparing itself to other tools or platforms.

1. No traction or revenue: The project is described as a prototype with no evidence of adoption or monetization.
2. Single-person team: Only one developer (Wonah Choi) is listed, which may limit scalability and product development speed.
3. Limited geographic scope: Currently only covers the San Francisco Bay Area.
4. Dependency on external data sources: Relies heavily on Google Maps and provider-published data, which may be inconsistent or incomplete.
5. AI dependency with fallbacks: While GPT-5.6 is used for navigation, it has a deterministic fallback — but this raises questions about the reliability of AI in healthcare contexts.
6. No clinical review: The author notes that licensed pediatric clinician review is a priority before public release, suggesting potential safety or regulatory concerns.

1. What is the current status of the prototype? Is it being tested with real users?
2. Are there any plans to expand beyond the San Francisco Bay Area?
3. How are you planning to validate and maintain accuracy of provider data over time?
4. Has there been any feedback from pediatric clinicians or healthcare professionals?
5. What is your roadmap for monetization or product evolution?
6. How do you plan to handle changes in Google Maps API or provider data availability?
7. Are there any legal or compliance considerations around healthcare data handling?