3.0
SLMs
Specialized small models trained on domain-specific data from our collection work. Built to run on constrained hardware, close to the data source, with no cloud dependency.
Shelf-1
Computer vision for retail shelf analytics. Detects every product facing, price tag, and empty slot from a standard smartphone photo in under 90 seconds. On-premises. No cloud. Client owns the deployed model.
Commerce-1
A small model trained on Machine Commerce behavioral traces, built to predict and classify agent decision quality in e-commerce flows. Designed to run as a lightweight evaluator inside agent pipelines, flagging likely failures before they surface in production.