A mobile client for an AI learning platform, built without waiting on the backend

The task

The platform had a web client and an AI backend but no mobile channel — and its users, school students, live on their phones. We needed a thin client on the existing API that keeps pace with the web version, while some backend routes were still in progress. Voice went to the second iteration; offline mode to the backlog.

What we built

• Built a Flutter app on Clean Architecture: each feature is a self-contained module with its own layers and DI, so new modules land without touching the core.
• Gave every module a mock mode: the whole app runs without a backend on a single build flag, so UI work ran in parallel with backend routes instead of after them.
• Three-stage micro-lessons (I do / We do / You do) with adaptive progression. The teaching method lives on the server; the client only renders state.
• Wired the platform's AI assistant with streamed replies, so text appears as it is generated. Goal-specific AI tutors keep session history and sources.
• A network layer that survives flaky connections without dropping the session. Later added a parent dashboard, voice, payments and a local cache on the same architecture.

Outcome

13 weeks

from first commit to a working app with auth, goals, lessons and AI chat

41 → 81 endpoints

API coverage doubled from MVP to the extended version — 14 → 31 modules on the same architecture

+17 modules in 2.5 months

31.5k lines on top of the MVP across 10 documented sync phases with the web version — no change to stack or module structure

20 mock repositories

every module runs without a backend, so UI was built in parallel with server routes (8 in the MVP, 20 in the extended version)

More cases