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, boosting efficiency and mentoring.

Summary

Kuken Industries, a major Japanese manufacturer of cooling towers and ventilation equipment, faced a challenge: finding the right replacement part drawing from 70 years of archived installations could take half a day, especially for newer engineers. Partnering with Japanese AI startup Recursive and using OpenAI models, Kuken built a search system and field app that lets engineers search by part number, drawing number, or even a screenshot of a parts list. The app returns possible matches, including similar designs, and allows review of drawings on-screen. Kuken expects the tool to cut drawing search time by about 90%, freeing experienced engineers to mentor and newer engineers to work more independently. The company is also developing an AI tool to check partner drawings, with prototype testing showing about 90% of flagged issues were genuine discrepancies. Kuken aims to use AI to pass engineering expertise to the next generation.

(Source:OpenAI)