Practice · B2B-distribution case study published · sovereign local AI
Published the second showable case study: custom quoting and procurement software for a CEE B2B distribution operator, with a sovereign local AI on top. A deterministic engine runs the transactional work — best price across vendors, adjustable margins, stock ETAs, demand-based ordering — while a local model grounded in the company's own data via retrieval, on their own hardware, surfaces trends, retunes the system in plain language, reports daily, and answers the team's questions. A frontier model touches only the non-sensitive drafting at the edge. The home page's selected-work card was corrected to the delivered scope and now links straight to the write-up. Client name withheld; figures qualitative under confidentiality.