Case studies
Results, not promises
Every case follows the same format: context, problem, what we built, and the numbers before and after.
Erudil (in-house product)
25k+
matches analysed
Erudil: an AI engine that prices every match outcome
Our own product. A probability engine turns match data into outcome probability matrices, compares them with bookmaker odds, and publishes a tamper-proof track record of every pick — wins and losses alike.
Grocery retail chain, EU & US (under NDA)
−55%
time spent searching regulations
AI knowledge assistants for a 30 000-employee grocery chain
Three RAG assistants on one platform — for commercial staff, store directors (by voice, from the shop floor) and HR — answer questions from corporate regulations with a citation to the exact clause, or say honestly that they do not know — so staff stop phoning head office for routine questions.
Grocery retail chain, EU & US (under NDA)
88%
straight-through, no human touch
Document AI that reads 1 300 supplier invoices a day
Scans and photos of invoices, delivery notes and acts go through a multimodal model that extracts typed fields with a confidence score per field, reconciles them with the supplier and contract master data, and posts to the ERP. Only low-confidence documents reach a human — roughly one in nine.
Grocery retail chain, EU & US (under NDA)
−78%
time to classify a new SKU
Catalogue AI: classifying new SKUs and cleaning 182 000 product cards
Two models on the product catalogue of a grocery chain: one suggests the classification code and category for every new item with top-3 probabilities, the other finds duplicate product cards semantically. Category managers confirm with one click instead of searching the classifier by hand; every confirmation feeds back into training.
Grocery retail chain, EU & US (under NDA)
2.4 h
median reaction to a critical review, from 52 h
Voice of customer: 12 review sources, one AI-classified stream
Reviews from maps, app stores, social networks, the hotline and the in-store complaint book flow into one system that classifies each by topic, sentiment, store and severity, escalates critical ones to the responsible manager within minutes, and gives management a live, per-store picture instead of a monthly digest.
KLR.gg (in-house product)
100%
of match days ingested with no manual upload
KLR.gg: automated CS2 match analytics for private lobbies
A platform that pulls server logs, match stats and demo recordings from Counter-Strike 2 community servers automatically, scores every duel and round, and turns them into player ratings, trends and balanced teams — no uploads, no spreadsheets.
Medical imaging research group (under NDA)
0.93
SSIM at 4× acceleration, from 0.71
Deep-learning MRI reconstruction: sharper images from 4× faster scans
A research-use system that reconstructs and denoises MRI series with neural networks — recovering image quality from undersampled and low-SNR acquisitions — deployed as a DICOM node between the scanner and PACS, with automatic quality gates so that no unreliable image reaches a reader.