Apprentice Atlas

The description states that Apprentice Atlas is a bilingual, map-first mobile app designed to help students and post-secondary individuals in Germany and the UK discover apprenticeships and early-career opportunities. It allows users to:

• Explore official opportunities via map or list.
• Search by role, company, interest, location, and opportunity type.
• Read AI-generated plain-language explanations (GPT-5.6).
• Receive fit guidance ("Good if you...", "Not so good if you...").
• Ask practical questions about roles.
• Save and track applications through calendar integration.
• Export application progress and account data.
• Use the app in English or German.

It is built with Expo SDK 57, React Native, TypeScript, and integrates with:

• Apple Maps (iOS)
• Supabase Auth, Postgres, Storage, Row Level Security, RPCs, Edge Functions
• OpenAI API with GPT-5.6
• Official data sources from Bundesagentur für Arbeit (Germany) and Find an apprenticeship Display Advert API v2 (UK)

The app is described as a native mobile experience, not a web application.

The description states that Apprentice Atlas aims to address a real problem: students and post-secondary individuals are expected to make career decisions before knowing what opportunities exist. It positions itself as an alternative to traditional job boards, which assume users already know what to search for.

Key claims include:

• The app helps users move from uncertainty to one concrete next step.
• It provides plain-language explanations, fit guidance, and practical question answering.
• AI is used not as a chatbot but to ground answers in the actual job listing.
• It supports anonymous browsing, with saved jobs and tracking requiring sign-in.

The positioning evolves from a tool for discovery to one that supports a full application journey—from exploration to planning to execution.

The description states that the app targets:

• Students and people leaving university without a degree
• Specifically in Germany and the UK
• Users who are uncertain about their next career step
• Individuals seeking to understand roles in plain language before applying

It is described as a bilingual experience for these two countries.

The description does not provide any information about:

• Revenue model
• Pricing structure
• Monetization strategy
• Customer acquisition costs
• Sales process or go-to-market plan

It is unclear whether the app will be monetized through subscriptions, partnerships, grants, or other means.

The product is built using:

• Expo SDK 57
• React Native and TypeScript
• Expo Router
• Apple Maps (iOS)
• Supabase Auth, Postgres, Storage, Row Level Security, RPCs, Edge Functions
• OpenAI API with GPT-5.6

Key technical features include:

• Server-side data normalization from official APIs
• AI outputs grounded in canonical job records
• Structured schemas and prompts to prevent invented content
• Native mobile experience (iOS)
• Anonymous browsing with account-based tracking
• EAS Build and TestFlight for distribution

The team used Codex as a persistent engineering partner throughout the build process, helping with implementation, testing, and iteration.

There is no evidence of:

• Revenue
• Customers
• User adoption
• Product-market fit
• Commercial traction beyond the hackathon prototype
• Any form of live deployment or user feedback

The app was built during a Build Week hackathon, and the team plans to continue development beyond that time.

The description does not provide any information about:

• Competitors
• Market size or dynamics
• Competitive advantages
• Differentiation from existing platforms

It only states that the app is different from traditional job boards, which assume users already know what to search for.

Several risks and red flags are implied by the self-reported nature of the project:

1. No commercial traction or revenue: The app is described as a hackathon prototype with no evidence of adoption or monetization.
2. Unverified AI outputs: While the system uses structured prompts, there is no independent verification that AI outputs are accurate or consistent.
3. Limited data sources: Only official APIs from Germany and the UK are used; no evidence of broader coverage or scalability.
4. Dependency on external tools: Heavy reliance on Expo, Supabase, and OpenAI may pose risks if those services change or become unavailable.
5. Unproven UX maturity: The team acknowledges early versions felt like web apps, suggesting that the final product may not yet be fully polished.

1. What is your plan for scaling beyond Germany and the UK?
2. Have you validated the app with real users, especially students or post-secondary individuals?
3. How do you intend to monetize this product?
4. What are the key challenges in integrating official data sources from multiple countries?
5. Can you provide evidence of user engagement or retention beyond the prototype phase?
6. How do you ensure that AI-generated content remains accurate and unbiased over time?
7. Are there any legal or compliance considerations around using official APIs and user data?