// case studies

Real projects, real numbers.

Some client names are under NDA. The metrics aren't.

AI · iGaming · 2024–2025

Audit AI for an online betting company

Duration: 12 months Team: 3 data engineers · 1 PM · 1 data scientist Stack: Golang · PostgreSQL · Python

Challenge

The client relied on five full-time analysts manually cross-checking data from multiple betting platforms to validate deals. Slow, error-prone, expensive — and human fatigue was directly costing money.

What we built

  • Data infrastructure: a warehouse plus scrapers that extract and normalize data from sources the client considered "unparsable".
  • AI engine: a model that replicates expert decision logic — accurate even when only 20% of data per deal is available.
  • Automation layer: Golang + PostgreSQL + Python pipelines with continuous monitoring, so accuracy doesn't decay in production.

Results

90%+
match with human expert decisions (KPI was 85%)
5 FTE
freed from manual verification
20%
data coverage was enough for accurate decisions
Data engineering · NDA holding · 2 years

Full analytical ecosystem for a US multi-brand holding

Duration: 2 years Team: 5–6 specialists Stack: Hadoop · Hive · Presto · Python · Tableau

Challenge

A holding with 15 years of history and 200+ brands ran its analytics on manual Excel reports. Data was scattered across dozens of databases, APIs and spreadsheets accumulated over a decade. Decisions took weeks.

What we built

  • Data warehouse: 38 sources unified — 23 databases, 8 APIs, 7 Google Docs — with automated hourly and daily pipelines.
  • BI system: 300+ Tableau dashboards, fully automated company-wide P&L, ad-hoc analysis for every business unit.
  • Real-time monitoring: 5-minute health checks on critical metrics with instant Slack alerts.
  • Data science: LTV prediction, churn & chargeback models, active-user forecasting, traffic segmentation.

Results

38 → 1
data sources in one warehouse
300+
dashboards, incl. automated P&L
100s hrs
of manual reporting eliminated monthly
Full-cycle product · Restaurant tech · 2023–present

Justy — CRM ecosystem for the restaurant business

Duration: ongoing since 2023 Team: 8 specialists Stack: Go · PostgreSQL · Angular · Swift · Kotlin

Challenge

Build a next-generation restaurant management and customer engagement platform entirely from scratch: CRM, web menu, native mobile apps, and a Telegram chatbot — all working as one system. This is what "built right from day one" looks like.

What we built

  • Backend: scalable Go + PostgreSQL architecture with a secure API layer and fallback logic for unstable third-party APIs.
  • Mobile: native iOS (Swift, SwiftUI) and Android (Kotlin, Jetpack Compose) apps with full test coverage.
  • Web & CRM: Angular-based CRM dashboard for restaurant partners — menus, orders, clients.
  • Chatbot: custom Telegram bot for customer interactions and orders.

Results

0 → MVP
complete platform from scratch
5
restaurant partners onboarded at launch
4
products in one ecosystem: CRM, web, mobile, bot

Want results like these?

Tell us about your project — we'll tell you what's realistic.

Book a free call