Kuken Industries searches 70 years of drawings in minutes

OpenAI
Kuken Industries uses OpenAI-powered AI search to find replacement part drawings across 70 years of archives in minutes, cutting search time by 90%.

Summary

Kuken Industries, a major Japanese manufacturer of cooling towers and ventilation equipment, has digitized 70 years of engineering drawings but struggled with searchability, especially for newer engineers who often relied on experienced colleagues. Partnering with Japanese AI startup Recursive and using OpenAI models via API, Kuken built a search system and field app that allows engineers to search by part number, upload images or PDFs, or paste screenshots of parts lists. The app returns possible matches, including similar designs. Kuken reports that the tool is expected to cut drawing search time by about 90% over a year, saving printing costs and freeing experienced engineers to mentor others while newer engineers take on more independent work. Kuken is also prototyping an AI tool to check partner-prepared drawings against specifications; in testing, about 90% of flagged issues were genuine discrepancies. The company aims to use AI to preserve and pass on engineering expertise to the next generation.

(Source:OpenAI)