Photo-to-explanation flow
A student photographs a homework question and gets a step-by-step explanation in Arabic or English, powered by Gemini 2.5 Flash.
- AI Product Engineering
- In-house Product
Smart Teacher
An Arabic AI tutor that explains homework from a photo. Students snap a question and get a step-by-step explanation in Arabic or English, then ask follow-up questions in an AI teacher chat.
Live — App Store & Google PlayView on Google Play →
Mobile app interface
Snapshot
Production status & delivery details.
Verified production status, stack, and maintenance model.
- Client / Context
- Smart Teacher (معلم بالذكاء الإصطناعي) — Arabic AI tutor app for iOS and Android, built and published by GenAILabs
- Engagement
- In-house GenAILabs product — no client engagement. App, AI prompts, analytics dashboard and store listings all built in-house
- Status
- Live on the App Store and Google Play, at an early stage
- Technology
- Flutter/Dart, GetX, Bloc/Cubit, Hive · Firebase (Firestore, Analytics, Remote Config) · Google Gemini 2.5 Flash · Codemagic, TestFlight · Microsoft Clarity
The challenge
What problem had to be solved?
The context, constraints, and risk surface that shaped every decision.
Arabic-speaking students often get stuck on homework with nobody to explain it. Most tools are English-first and give only the answer, not the reasoning.
Smart Teacher had to work from a photo of a question, explain the reasoning step by step in Arabic or English, and let the student keep asking until it made sense. It also had to be honest about its limits: AI answers can be wrong, so the product points students back to their teacher, and it keeps data collection to an anonymous device ID.
Contributions
What GenAILabs built.
Everything in-house except the Gemini API and Firebase.
AI teacher chat
Follow-up questions in a chat with the AI teacher, with solution history so past answers can be revisited.
Lessons & Challenges
Grade-based lessons and a Challenges quiz mode with points and answer streaks.
Flutter app
One Flutter codebase for iOS and Android, using GetX and Bloc/Cubit for state and Hive for local storage.
Firebase backend & config
Firestore, Analytics and Remote Config for data, usage tracking and runtime configuration, on Firebase's free plan.
Dashboard, delivery & listings
An internal usage dashboard, Codemagic and TestFlight delivery, and optimized App Store and Google Play listings.
System / solution
How the product works.
A Flutter client talking directly to Gemini and Firebase, shipped through Codemagic.
System architecture
Flutter app (GetX, Bloc/Cubit, Hive) on iOS and Android → photo sent to Google Gemini 2.5 Flash for a step-by-step explanation in Arabic or English → follow-ups in the AI teacher chat. Firestore, Analytics and Remote Config on Firebase; Microsoft Clarity for session recordings; Codemagic and TestFlight for delivery.
Flywheel impulse
Deployment, integration, and real-world use.
How the product is run today, and what changes before it scales.
Smart Teacher is live on the App Store and Google Play at an early stage. It is an in-house GenAILabs product, so there is no client engagement: the same team builds, ships and watches it through its own admin dashboard and the two store consoles.
- Integration pattern
- Photos sent to the Google Gemini 2.5 Flash API; usage events to Firebase Analytics; Remote Config for runtime settings; Microsoft Clarity for session insight
- Scale protocol
- Early stage. The Gemini key currently sits inside the app, so it moves behind a backend before scaling
- Maintenance mode
- Maintained in-house on Firebase's free plan, watched through the internal admin dashboard, Google Play Console and App Store Connect
Outcomes / evidence
Early signals from the live product.
Early-stage figures from the admin dashboard and store consoles, taken at the dates shown.
Play Console · 28 days to Sep 13
~4,590 impressions, 60 installs
From Google Play Console. Refresh before relying on it
App Store Connect · August
1,968 impressions
From App Store Connect. Refresh before relying on it
Key outcome
~45% opened the app more than once
Repeat opens from the admin dashboard, counting same-day reopens, so not a retention figure. Users mostly in Saudi Arabia, Jordan, Egypt, Yemen and Syria
Capabilities involved
How core competencies were applied.
Built and shipped end to end by the GenAILabs team.
AI Product Engineering
The whole product: Flutter app, Gemini-powered photo explanations in Arabic and English, an AI teacher chat, lessons, a quiz mode, analytics, and optimized store listings.
In-house delivery
Shipped to both app stores through Codemagic and TestFlight, and run by the same team with its own usage dashboard.
Related work
Other production builds.
Two more engagements from the same team.
AI Product EngineeringProduction
Kaya Health Coach
AI functional medicine coach live on both app stores — Flutter app, FastAPI backend, real-time LLM streaming, structured health journeys.
AI Product EngineeringProduction
Ask Dahab
Multilingual travel and booking platform for Dahab, Egypt — 6 languages, ~915 pages, admin panel, and the Ask Sinai mobile app.
Let's talk
Have a similar challenge?
Let's discuss the problem you're trying to solve.
Talk to our team
