Meeting Modern Design Challenges
To address pressing industry changes such as labour shortages and the advancement of digitalisation, Takenaka has been promoting internal initiatives like “work style reform” and improvements in its architectural production processes. A key challenge identified was to create an environment where designers can focus on more creative tasks by effectively utilising past design assets to reduce their workload.
Although past project drawings were mostly stored in digital form, designers often struggled to quickly access the information they needed. In practice, teams frequently had to manually sift through hundreds of thousands of pages of drawings or consult colleagues to track down reference details. This time-consuming process made it difficult to fully leverage the company’s accumulated knowledge in ongoing design work.
AI-Powered Solution: Tektome KnowledgeBuilder
To overcome these challenges, Takenaka adopted Tektome KnowledgeBuilder, an AI-driven solution that automatically organises large volumes of design documents – a task that would be impractical to do manually. Tektome KnowledgeBuilder structures information from various formats, such as drawings and meeting notes, simply by allowing architects or designers to give instructions in natural language. It analyses, organises, and converts key content into a searchable database. This allows even non-engineers to easily structure and store information, transforming past data into actionable knowledge within the firm.
The system helps to prevent design errors from recurring, reduces unnecessary redesign work, and supports the creation of new designs by making relevant historical data readily accessible. Learn more about KnowledgeBuilder on our website: KnowledgeBuilder product page.
Pilot Implementation and Results at Takenaka
For this implementation, multiple working groups were established within Takenaka. On-site team members took the lead in verifying how as-built drawing data could be structured using the new tool. After a three-month pilot programme, those members were able to set up their own custom extraction criteria tailored to their needs. This empowered them to quickly retrieve practical information such as:
-
Past as-built drawings that matched specific project requirements
-
Reference examples from similar projects
-
Summaries of relevant numerical data from previous designs
Building on the pilot’s success, Takenaka is now expanding the system by importing a larger volume of past as-built drawings and further enhancing search options and usability. By applying this accumulated design knowledge to current projects, the company is already reducing needless redesigns and improving overall quality.
Comment from Takenaka Corporation
Mr. Takaoka of the Structural Department, Design Division at Takenaka’s Tokyo headquarters, commented on the collaboration (translated from Japanese):
“Over two years of collaboration between Tektome, which possesses cutting-edge generative AI technology, and Takenaka Corporation, a leader in the construction industry, we have realised a powerful partner for designers. The shift from manually searching hundreds of thousands of pages of drawings to instant access through natural language has revived veteran design expertise as actionable knowledge, allowing designers to focus on more creative tasks. We are confident that this innovative partnership, which balances increasingly complex design requirements with work style reform, will drive transformation across the architecture industry.”
Looking Ahead
Going forward, Tektome will continue to support Takenaka by providing services that enable the automatic organisation and checking of design requirements. By further boosting productivity in AI-driven design workflows, we aim to contribute to ongoing reforms in both designers’ work styles and architectural production processes, helping to drive positive change across the industry.
