Kuken Industries searches 70 years of drawings in minutes

Kuken Industries, a Japanese manufacturer of air conditioning and ventilation equipment with a leading share of Japan's cooling tower market, faced a challenge: engineers needed to find replacement part drawings from a 70-year archive to service older installations, but searches could take half a day and newer engineers often relied on experienced colleagues. Kuken partnered with Japanese AI startup Recursive, an official OpenAI partner, to build an AI-powered search system and field app. They tested several AI models, and OpenAI's models performed well on accuracy and cost, with the OpenAI API enabling search directly in the app. Engineers can search by part number or upload an image or PDF of a drawing or parts list, and the app returns possible matches, including drawings for similar designs. Kuken reports the tool is expected to cut drawing search time by about 90% over a year, reduce printing costs, and free experienced engineers to mentor newer colleagues, who can now handle a wider range of jobs independently. Kuken is also developing an AI tool to review partner drawings for discrepancies; in prototype testing, about 90% of issues flagged were genuine. According to Director and Factory Manager Takatsugu Naraki, the technology helps pass engineering skills to the next generation.

(Source：OpenAI)