EdTech · Mobile app
A mobile client for an AI learning platform, built without waiting on the backend
Flutter client for an exam-prep platform: adaptive micro-lessons, a streaming AI assistant, a knowledge map. The UI was built alongside the backend via a mock layer.
- Status
- In-house product
- Timeline
- about 3 months MVP + 2.5 months extension
- Stack
- Flutter / Dart
- flutter_bloc
- go_router
- get_it
- dio
- drift / SQLite
The task
The platform had a web client and an AI backend but no mobile app, 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 and 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 we added a parent dashboard, voice, payments and a local cache on the same architecture. The client has not been published in app stores.
Outcome
- 13 weeks
- from first commit to a working app with sign-in, goals, lessons and AI chat
- 41 → 81 endpoints
- API coverage doubled from MVP to the extended version, with 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, with 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)
Services
More cases
IT consulting · Lead qualification
In-house productA pilot plan for the visitor, a qualified lead for sales
We replaced the contact form with an AI consultant: it interviews the visitor, returns a pilot plan with KPIs and risks, and sales gets a lead with budget and timeline.
- 1 day
- to build a working MVP: frontend, backend and deploy configs
- 16 days
- from first commit to production with HTTPS and an issued certificate on its own domain
Aviation · aircraft components trading and MRO
PilotAircraft parts procurement: from email to a managed pipeline
An AI agent reads incoming RFQs, compares supplier quotes and checks trace documents. A separate deal-tracking system moves each deal through mandatory stages.
- Full loop
- the AI loop ran end to end on a live procurement process, from an incoming RFQ to a team notification. This was a pilot and the figures are our own so far: the client has not confirmed them yet
- 3
- types of trace documents checked by the agent: FAA 8130-3, EASA Form 1 and COC. Like the figure above, it still awaits the client’s confirmation
Distribution · Partner networks
In productionA sales and support platform for a distributed partner network
Partners ask who on their team is inactive and what blocks the next level, and get numbers for their own part of the network only. Access is enforced at the SQL level.
- Their own slice
- a partner gets figures for their own team only: a filter on the current user is added to every SQL query
- 6 layers
- of data protection between the language model and the database, from blocked personal-data columns in SQL to rate limits; counted in the code
Estimate the payback of a similar process
AVA lets you work out the economics of your process on your own figures, with no form and no price from us. It shows what the manual work costs, what cash effect automation would give and what budget would pay back. If the effect does not even cover running costs, it says so.
Estimate the paybackDiscuss a similar problem
Describe the process and the data you have. Before any work starts we will tell you what can be measured in money, what cannot, and whether it is worth doing.