Kuken Industries searches 70 years of drawings in minutes

Kuken Industries, a Japanese manufacturer of air conditioning and ventilation equipment, holds a large share of Japan's cooling tower market. When a cooling tower needs a replacement part, engineers must consult an archive of drawings spanning 70 years of installations. Searching that archive could take half a day, and newer engineers often relied on experienced colleagues to find and interpret the right drawings. Kuken worked with Recursive, a Japanese AI startup and official OpenAI partner, to build a search system and field app using OpenAI models, which performed well on accuracy and cost. Engineers can enter a drawing or part number or upload an image or PDF, and the app returns possible matches, including drawings for similar designs. Kuken expects the tool to cut drawing-search time by about 90% over a year, reduce printing costs, and let newer engineers work more independently while experienced engineers mentor colleagues and take on their own engineering work. Kuken is also developing a tool to check partner drawings against specifications; in prototype testing, about 90% of the issues the AI flagged were genuine discrepancies. The company aims to use AI to pass engineering experience on to the next generation.

(Source：OpenAI)