In development2026Macsug
Live scores, AI predictions and an accountable tipster platform.
- Project
- Our own product
- Our role
- Product · Mobile development · Backend · AI layer
- Duration
- In development
01 / Behind the product
A real need. A considered solution.
Challenge
There are plenty of live-score apps; prediction and "tipster" sharing usually amounts to unverifiable claims. The product’s strength lies in every prediction being accountable afterwards and coupons settling automatically.
Approach
On Supabase, 21 migrations and 19 Edge Functions: score ingestion and catalogue sync, a predictions ledger, coupon creation and settlement, tipster stat refresh, value-bet scanning, push fan-out, data export and deletion, KVKK consents, moderation. AI analysis uses Claude models with web search for news awareness; mascot characters produce daily picks and per-match commentary. The mobile side is Expo + Tamagui with TanStack Query and MMKV; sports data comes from Sportmonks, API-Football and OddsPapi, subscriptions through RevenueCat.
Result
Designed for six languages (TR, EN, IT, FR, DE, ES), the product is in development; the data model, server functions and main screens are in place, and live data comes online as provider keys are connected.
02 / Inside the product
The experience, on screen.
Open a screen to explore the details.02 images
03 / Scope & details
The details make the experience.
- 01
A predictions ledger with automatic coupon settlement
- 02
News-aware AI match analysis and mascot picks
- 03
Value-bet scanning and tipster statistics
- 04
19 Edge Functions, 21 migrations, KVKK consents
- 05
Six languages
Technology
INSIDE THE PRODUCT
The engineering behind the interface.
Systems we built and concrete problems we addressed in this project.
A predictions ledger and coupon settlement
006_predictions_ledger records every prediction permanently; the coupon-settle function closes coupons on match results and tipster-stats-refresh recomputes statistics. Accountability lives in the data model.
Mascots and news-aware analysis
mascot-daily-picks, mascot-per-match, mascot-conversation and mascot-user-reply produce the mascots’ picks and conversations; news-scanner and ai-match-analysis fold news into analysis through Claude calls with web search.
Compliance and quotas
The kota_tracker, moderation and kvkk_consents migrations carry usage quotas, moderation and consent records; the data-export and data-deletion functions serve user rights. Every table sits under RLS policies.
Your idea could be next.
What could we build for you?
From a first release to a growing platform. Let’s plan the design, development and launch together.
From Türkiye to the US, UK, Australia and everywhere in between.