Home

Blog

CONTACT US

AI

EdTech

Test Test

Mobile App Development Case for Loxie

ABOUT PROJECT

Loxie is a mobile-first learning application designed to help users retain and apply insights from nonfiction books.

CLIENT REQUIREMENT

“The task was to develop an application that extends the functionality of the knowledge retention through active recall, spaced repetition, and gamified reinforcement. The application needed to deliver adaptive learning sessions based on demonstrated knowledge and confidence, and build habit-forming daily routines via gamification and streak systems. It also aimed to support monetization through a subscription mode and affiliate links.“

Henrik Cader

Chief Digital Officer, Tumbli

Flutter (iOS-first, scalable to Android/Web)

FastAPI (Python) on Firebase Functions/AWS Lambda as backend

Supabase (PostgreSQL + Auth) as database layer

RevenueCat for subscriptions

Google AdMob for ads

Firebase Cloud Messaging for push

OpenAI API for AI features

Firebase Analytics (+ RevenueCat, optional Mixpanel) for analytics

Flutter (iOS-first, scalable to Android/Web)

FastAPI (Python) on Firebase Functions/AWS Lambda as backend

Supabase (PostgreSQL + Auth) as database layer

RevenueCat for subscriptions

Google AdMob for ads

Firebase Cloud Messaging for push

OpenAI API for AI features

Firebase Analytics (+ RevenueCat, optional Mixpanel) for analytics

Outcomes

Adaptive Learning Sessions

The app delivers daily learning sessions that adapt to user performance through a sophisticated Session Algorithm. This algorithm prioritizes questions based on a queue of books that the user can modify, correctness and confidence, session-based resurfacing (spaced repetition), and complex coefficients.

Gamification and Progression System

 Loxie incorporates a robust progression system featuring XP and streaks to motivate users. Progress is tracked via a Knowledge Meter, and cumulative points after each daily session. The app incentivizes consistent engagement with push notifications for new daily drills and a clear upgrade path for Free users to access more daily drills and questions (Pro users get 5 questions per daily drill and more daily drills, while Free users get 5 questions per day).

Monetization Strategy

The application implements a Freemium model with a Free tier (limited access) and a Pro subscription (full feature access, multiple sessions, advanced questions). A Founders Club lifetime offer was also planned for early adopters. But new model is in progress.

Book and Content Management

Users can select books from a curated catalog. Free users are limited to one active book, while Pro users can have up to 5 books on their “shelf” with all simultaneously accessible.
If user like any book, but has more prior books on the shelf-he can add it to a favorite and this book will appear at favorites shelf, so user can add it to gis main shelf and get daily drills a bit later.

Challenges

Complex Adaptive Learning Algorithm Implementation

A core challenge was the development and precise implementation of Loxie’s hybrid session algorithm. This algorithm dynamically determines the optimal order of learning questions by balancing multiple factors: book weight, question level, answer history, time since last seen (spaced repetition), a boost for unseen content and randomize coefficient to provide more interesting daily drills and provide more diversity. Ensuring accurate calculation of each card’s priority score and managing the conditional unlocking and locking of Level 1, 2, and 3 questions based on mastery criteria (correctness, confidence, and temporal intervals) presented significant complexity. The system had to flawlessly transition questions between active and locked states to maintain effective long-term retention.

Dynamic Deck Size Management and Mid-Day Content Changes

Another major challenge involved efficiently managing the dynamic size of the user’s daily question deck and integrating mid-day content changes that a should affect only next daily deck generation. Crucially, the daily deck had to be generated and locked at midnight to maintain the integrity of spaced repetition and confidence tracking. This required careful logic to ensure that user changes to their book shelf (for Pro users) or book replacements (for Free users) either didn’t affect the current day’s session or were queued for the next day, preventing “reshuffling exploitation” and reinforcing a consistent daily learning experience.

CONTACT US

Request a free consultation
with our experts & estimate
your project

SEND REQUEST

case img case img case img case img case img