Kuken Industries searches 70 years of drawings in minutes

OpenAI
Kuken Industries uses OpenAI-powered search to find replacement part drawings from 70 years of archives in minutes, cutting search time by 90% and helping newer engineers work independently.

Summary

Kuken Industries, a leading Japanese manufacturer of air conditioning and ventilation equipment, holds a 70-year archive of engineering drawings for its cooling towers. Previously, finding the right replacement part drawing required asking experienced colleagues and could take half a day. Kuken partnered with Japanese AI startup Recursive and used OpenAI models to build a search system and field app that lets engineers find drawings by part number, image, or PDF screenshot. The tool returns possible matches, including similar designs, so engineers can identify the correct drawing. 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. Newer engineers can now handle a wider range of jobs independently. Kuken is also developing an AI tool to check partner-prepared drawings against specifications; in prototype testing, about 90% of flagged issues were genuine discrepancies. The company aims to use AI to pass engineering skills and decision-making experience to the next generation.

(Source:OpenAI)