New AI tool from Fujitsu turns decades of COBOL code into readable design documents without expert knowledge
- Fujitsu automates COBOL documentation, reducing analysis time by 97%
- The system generates design documents without requiring extensive programming expertise
- Knowledge Graph recovery reduces hallucinations and improves documentation completeness
Fujitsu has introduced a new generative AI service that analyzes existing COBOL and other source code, automatically producing design documents in minutes rather than hours.
The system can operate and automatically produce design documents without specialist knowledge, reducing the need for specialist human programmers.
The company claims that Fujitsu Application Transform, powered by Fujitsu Kozuchi, eliminates the need for extensive manual review, reducing the time needed to understand complex source code by approximately 97%.
Article continues below
Accuracy and readability improvements
The service aims to provide a clear understanding of existing system specifications, providing organizations with a practical tool to effectively support modernization strategies.
Compared to analysis performed only by general generative AI tools, Fujitsu’s proprietary solution improves the quality of the generated documentation.
This system links large volumes of source code through a Knowledge Graph — Enhanced retrieval system.
Thus, it avoids omissions and hallucinations, ensuring that the generated design documents reflect all relevant details of the system.
This approach improves completeness by 95% and increases readability by 60%, producing documentation that is easier for teams to interpret and use.
These improvements are especially crucial when it comes to COBOL, a programming language designed by Dr. Grace Hopper in 1959 that has approximately 850 billion lines of code.
Despite being over 65 years old, COBOL remains widely used and businesses remain heavily dependent on this venerable programming system.
It often powers the main transaction systems of banks, insurers and government agencies without public visibility.
During the pandemic, the United States has raised the prospect of a shortage of COBOL programmers to help manage critical systems, demonstrating its importance.
Before the Fujitsu system, Anthropic highlighted that AI could help keep COBOL running for a long time.
Fujitsu plans to provide support services to guide organizations in effectively deploying the system. This year, the company intends to introduce features to reconstruct existing source code for future use.
The system will automatically rewrite the code and support ongoing operation and maintenance.
This sequential development ensures that businesses can not only understand existing systems, but also adapt and maintain them with minimal manual intervention.
“We view this announcement as an initiative that realistically advances the modernization of our existing systems…we have come to recognize the potential of this technology,” said Toshihiro Horiuchi, managing director of SMBC Nikko Securities Inc.
For many engineering teams, this announcement represents a clear benefit, but IBM, a major provider of COBOL-based mainframes and enterprise systems, must rethink its strategy or risk being left behind in the automated modernization of existing systems.
Follow TechRadar on Google News And add us as your favorite source to get our news, reviews and expert opinions in your feeds. Make sure to click the Follow button!
And of course you can too follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp Also.
