- Fujitsu automates COBOL documentation and reduces analysis time by 97%
- The system generates design documents without requiring deep programming expertise
- Knowledge Graph retrieval reduces hallucinations and improves documentation completeness
Fujitsu has introduced a new generative AI service that analyzes COBOL and other legacy source code and automatically produces design documents in minutes instead of hours.
The system can operate and automatically produce design documents without expert knowledge, reducing the reliance on specialized human programmers.
The company says Fujitsu Application Transform powered by Fujitsu Kozuchi eliminates the need for extensive manual review, reducing the time required to understand complex source code by approximately 97%.
The article continues below
Accuracy and readability improvements
The service aims to provide a clear understanding of existing system specifications and offer organizations a practical tool to effectively support modernization strategies.
Compared to analyzes performed solely by general generative AI tools, Fujitsu’s proprietary solution improves the quality of generated documentation.
This system connects large amounts of source code through a knowledge graph — improved retrieval system.
With this, it prevents omissions and hallucinations, ensuring that the generated design documents reflect all relevant system details.
This approach improves scope by 95% and increases readability by 60%, producing documentation that is easier for teams to interpret and act on.
These improvements are particularly critical when dealing with COBOL, a programming language designed by Dr. Grace Hopper in 1959, which has an estimated 850 billion lines of code.
Although COBOL is over 65 years old, it is still widely used and companies continue to rely heavily on this venerable programming system.
It often runs the core transactional systems of banks, insurance companies and government agencies without public visibility.
During the pandemic, the US raised the prospect of a shortage of COBOL programmers to help manage critical systems, showing its importance.
Before the Fujitsu system, Anthropic noted that AI could help keep COBOL running for a long time.
Fujitsu plans to provide support services to guide organizations in implementing the system effectively – this year the company intends to introduce features for rebuilding existing source code for future use.
The system will automatically rewrite code and support ongoing operation and maintenance.
This sequential development ensures that companies can not only understand legacy systems, but also adapt and maintain them with minimal manual intervention.
“We see this announcement as an initiative that realistically advances the modernization of our legacy systems … we have come to recognize the potential of this technology,” said Toshihiro Horiuchi, CEO, SMBC Nikko Securities Inc.
For many engineering teams, this announcement represents a clear advantage, but IBM, a major supplier of COBOL-powered mainframes and enterprise systems, needs to revise its strategy or risk being overtaken in automated legacy system modernization.
Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews and opinions in your feeds. Be sure to click the Follow button!
And of course you can too follow TechRadar on TikTok for news, reviews, video unboxings, and get regular updates from us on WhatsApp also.
