Real problems, shipped in production.
Deep-dives into the ML and AI systems we've designed, trained, and deployed end to end — the constraints, the architecture, and the results.
Enterprise Search Software for a Regulated Firm: Permission-Aware Answers Across SharePoint and File Shares
Enterprise search deployed inside a regulated mid-market firm's own infrastructure — indexing SharePoint, shared drives and internal systems, and answering questions without ever showing anyone a document they are not cleared to…
Read the case study →
Next Item Recommender Using BERT4Rec
Replacing collaborative filtering with a bidirectional Transformer sequence model for a 10M-user e-commerce catalogue — and serving it under 70ms in production.
Read the case study →Have a Problem Worth Solving?
Bring your data, your constraints, and your current baseline. In 30 minutes we'll tell you whether it's worth building — and roughly what it takes to ship.