- AI automates COBOL code exploration, assigns dependencies, and analyzes structural risks quickly
- Engineers can prioritize modernization based on technical risk and business value efficiently
- Automated testing verifies that migrated COBOL components produce identical results as legacy systems.
Modernizing legacy COBOL systems has long been an expensive and laborious process requiring extensive human effort, as traditionally consulting teams spent months or even years mapping workflows, documenting dependencies, and untangling decades of accumulated business logic.
Hundreds of billions of COBOL lines still run in production around the world, powering critical systems in banking, government, and airlines; However, finding developers with the knowledge to interpret these systems has become increasingly difficult.
Now, however, Anthropic is looking to supplant this, with its Claude AI platform aimed at taking much of the heavy lifting out of human workloads.
How AI helps code exploration and analysis
Historically, this shortage of expertise has slowed modernization projects and increased costs; However, Anthropic now believes that AI can automate much of the exploration phase that once consumed most of human effort.
“Modernizing a COBOL system once required armies of consultants to spend years mapping workflows…AI changes this,” the company said in a blog post.
Tools like Claude Code can map dependencies across thousands of lines of COBOL, trace data flows between modules, and document workflows that current staff no longer actively remember.
These automated processes identify risks, isolate tightly coupled components, and flag duplicate or potentially fragile code.
By analyzing these structural and functional relationships, AI can prioritize which components to modernize first based on technical risk, business value, and organizational priorities.
The best laptops for programming allow engineers to efficiently integrate AI results while maintaining oversight of the modernization plan, and once components are prioritized, AI can generate preliminary functional tests to verify that the migrated code produces identical results to the legacy system.
Human teams then decide whether these automated tests are sufficient, what scenarios require manual verification, and what performance benchmarks should be maintained.
Deployment proceeds incrementally, and each module is tested and validated before additional changes are made.
AI tools can translate COBOL logic into modern languages, create API wrappers around legacy components, and create scaffolds that allow old and new code to work side by side.
This reduces the risk of large-scale failures and allows organizations to move forward with complex modernization projects.
AI also provides detailed information on potential technical debt, siled modules, and high-risk areas, allowing teams to plan modernization strategically as engineers can review these recommendations and sequence work to align with regulatory requirements, business priorities, and operational constraints.
Automated documentation and analysis gives teams comprehensive situational awareness, but final decisions still rely on human judgment.
While this is a big win for many engineering teams, IBM, a major provider of mainframes and COBOL-based enterprise systems, will not be satisfied.
The company saw its shares fall sharply after Anthropic announced that Claude Code could automate much of the labor-intensive modernization process.
AI’s ability to replace work traditionally performed by human consultants threatens parts of IBM’s business model.
This shows that even long-established enterprise software vendors may face disruption as AI continues to reshape the modernization of legacy systems.
Follow TechRadar on Google News and add us as a preferred source to receive news, reviews and opinions from our experts in your feeds. Be sure to click the Follow button!
And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp also.
