AI PM Ready
Back to the Digest

Kuken Industries Reduces Drawing Search Time by 95% with OpenAI API

OpenAI BlogVendor storyProduct Strategy3 min readImportantOriginal source ↗

Kuken Industries significantly reduced the time engineers spend searching for cooling tower drawings from nearly an hour to 4.5 minutes by implementing a solution using the OpenAI API. This demonstrates the power of LLMs in rapidly processing and retrieving information from vast unstructured data sets. AI PMs should explore how similar applications can unlock efficiency gains in their organizations. This week, identify a knowledge-intensive process in your company that involves searching through large volumes of documents.

What happened

Kuken Industries has implemented a solution using the OpenAI API to enable engineers to search through 70 years of cooling tower drawings. This application has dramatically reduced the time required to find a specific drawing from nearly an hour to just 4.5 minutes, representing a nearly 95% efficiency improvement in information retrieval.

A scenario you might face

A manufacturing company has a large archive of historical product design documents, specifications, and maintenance logs that are difficult to search and access. Engineers spend a significant amount of time manually sifting through these documents. Kuken Industries' success with the OpenAI API offers a compelling solution. The PM must now evaluate the feasibility and ROI of building a similar AI-powered search capability for their company's internal knowledge base, balancing development costs against potential productivity gains.

What changes in your practice

This week, identify a critical internal process that involves searching through a large volume of documents or data. Scope out a potential AI-powered solution, similar to Kuken Industries', and estimate the potential time savings and efficiency gains.

Questions for your team

  1. 01What specific techniques were used to index and enable semantic search across Kuken Industries' 70 years of drawings?
  2. 02How does Kuken Industries ensure the accuracy and relevance of the search results provided by the OpenAI API?
  3. 03What was the total cost of implementing and running this solution, and how does it compare to the previous time-based cost of manual searching?
  4. 04Are there plans to expand this AI-powered search capability to other types of documents or data within Kuken Industries?

Practise this

Interviewers ask about stories like this one. Rehearse your answer in a timed mock interview.

Start a mock interview →
All stories
Was this page useful?