I’m thrilled to announce that IBM’s generative AI-assisted application modernization product, watsonx Code Assistant for Z, is now available. I’ve been talking to many clients about watsonx Code Assistant for Z over the past couple months. We’ve been hard at work aiming to bring the power of generative AI to accelerate COBOL code modernization and help developers become much more productive.
Can AI and automation assist modernization efforts?
If organizations can leverage generative AI and automation during application modernization projects, there’s potential to drive business agility amidst an increasingly competitive market. From automated discovery, code refactoring and conversion, testing, and fit for purpose deployment, generative AI can play an important role.
IBM watsonx Code Assistant for Z leverages IBM’s Granite foundation models for code, running on IBM’s watsonx platform. Using generative AI, it is designed to make it easier for developers to selectively modernize COBOL business services and translate COBOL into Java. Our goal is for clients to easily integrate refactored COBOL or Java code into existing COBOL applications running on IBM Z with full interoperability, while maintaining mainframe capabilities.
View the demo here: https://www.youtube.com/watch?v=bLOcdyFZN0k
Could generative AI simplify developers’ day to day tasks?
The IBM watsonx Code Assistant for Z application lifecycle is aligned with DevOps practices and leverages existing IBM Z DevOps investments. IBM initial innovation areas include application discovery, refactoring of business services, code transformation. The next step in the lifecycle is validation testing. Anticipated in a future release, the product will support automated test case generation to validate the new COBOL or Java services.
We start with application discovery and refactoring of COBOL business services by capturing and leveraging metadata about clients’ COBOL applications. What we think is really unique about our approach is that clients can continue in COBOL or decide to transform the refactored code into Java, leveraging a generative AI-assistant powered by a COBOL to Java foundation model provided by IBM. This product is targeted and tuned for this specific objective.
Why is COBOL code targeted?
Let’s be clear, it is not our intent or recommendation to convert an entire set of COBOL applications to Java. Instead, IBM is creating an experience that allows for optimal use of COBOL and Java together. Why? Simply put, each language brings their own unique strengths and clients should have full control over which language they want to use for their business needs. Independent of client choice, IBM supports interoperability and optimization for IBM Z capabilities, and you also can leverage your existing application investments.
And the best news is that this is just the beginning. IBM is exploring additional opportunities to extend the watsonx Code Assistant product portfolio over time to address other programming languages – designed to improve time to value for modernization and address growing skills challenges for developers. Much more to come on that front so stay tuned! At IBM, we’re constantly listening and looking for new ideas. If there are languages that you would like to see supported in the future, please let us know in the comments.
To get started with watsonx Code Assistant for Z, visit the product webpage and sign up for a live demo here.