Learning and careers decision
Francopass
A capable developer can build a useful subset (quizzes, SRS, and a basic AI mock-interview) in a few weeks, but replicating the polished mobile UX, curated content, and an operational, high-quality conversational AI product is non-trivial and better suited to continuing to pay the existing service.
Visit website↗Not priced
No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.
$100one-off66 h to build
$40/mo6 h/mo upkeep
No published price to break even against.
Open-source builds that already do this
Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All Francopass alternatives, with the arithmetic →
What a replacement has to do
- A learner opens the app, follows a personalized study plan, completes quizzes and spaced-repetition flashcards, and practices oral interviews with an AI interviewer that scores and gives feedback.
What it still won’t have
- Polish and UX of the mobile apps (iOS/Android)
- Large existing user base and reviews
- Continuously curated and legally vetted question bank
- Proprietary conversational model tuning and evaluation pipelines
- Integrated App Store/Play Store presence and push-notifications
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
Francopass does not publish a price we could read, so there is nothing to compare against. What building costs is below.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a responsive web app using Next.js (React) for the frontend, Postgres (hosted via Supabase) for user and content storage, and Vercel for hosting. Implement: 1) user auth and profile with a study-deadline-based personalized schedule; 2) quiz engine supporting multiple-choice and scored exams, progress tracking and a spaced-repetition flashcard scheduler; 3) admin CMS to create/update question bank, lessons and audio files; 4) AI oral interview feature using WebRTC/MediaRecorder for browser audio capture, a speech-to-text API (e.g., Whisper-compatible), OpenAI or equivalent LLM to run a dialog flow and generate feedback, and a TTS API for interviewer voice; 5) scoring/report page for each mock interview and per-user study progress. Out of scope: native iOS/Android apps (build only a responsive web app), offline-first functionality, and App Store deployment. Require: authentication error handling, retries for external API calls, input validation, role-based access for CMS, unit and end-to-end tests for core flows, and infrastructure IaC (Terraform or Vercel configuration) to deploy.
How we checked
How the score was reached
- Partly verdict base52
- An open-source build was found+5
- 2 cited sources+1
- 3/3 assessment runs agreed+4
- Evidence score62
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 2
Every page the run actually retrieved.
- official productFrancopass - Réussissez l'examen civique et l'entretien de naturalisation
- open sourcestudyield/studyield
Integrity checks
What held up, and what did not.
