Kuken Industries deploys AI search for 70 years of cooling-tower drawings
Kuken Industries and Recursive built a field app that searches Kuken’s cooling-tower drawing archive through part numbers, uploaded images, PDFs and parts lists. The tool uses OpenAI models and the OpenAI API to return possible drawing matches, while Kuken is separately prototyping AI-assisted review of partner drawings. Kuken expects the search tool to cut drawing-search time by about 90% over a year and reports that about 90% of issues flagged in prototype testing were genuine discrepancies.
The deployment shows how AI can make decades of specialized industrial records easier to search and review, while transferring some of that institutional knowledge to newer engineers.
Kuken Industries makes air conditioning and ventilation equipment for large buildings, shopping centers, and factories. It holds one of the largest shares of Japan’s cooling tower market. These towers release heat from circulating water into the air, helping cool everything from large buildings and malls to equipment in data centers.
When a cooling tower needs a replacement part, Kuken’s engineers turn to an archive of drawings that spans 70 years of installations. For a newer engineer, finding the right drawing often meant asking an experienced colleague where to look and how to read it. Kuken wanted newer engineers to be able to find those records themselves, learn from the decisions they contain, and spend more time figuring out how to make the repair.

