IBM has announced IBM Watsonx Code Assistant for Z, an AI-assisted solution designed to make it faster and less risky to modernize COBOL applications.

The tool is based on IBM's watsonx.ai generative foundation model for code automation.

IBM Watsonx is an AI and data platform that until now had three products: the watsonx.ai studio for new foundation models, generative AI and machine learning; the watsonx.data store built on an open lakehouse architecture and the watsonx.governance toolkit.

The new tool is designed to help users modernize COBOL applications by converting them to Java faster, for a lower total cost and complexity. The developers say it results in code that is easy to maintain through model customization.

Here's a demo of Code Assistant for Z:

IBM says the code automation foundation model is now one of the largest generative code models compared to the previous largest, community model StarCoder. The model has been trained on 80 code languages and 1.5 trillion tokens of data, and when IBM tested its COBOL to Java translation against ChatGPT, it outperformed ChatGPT 88% to 32%.

The model will also be used to power Ansible Lightspeed with IBM watsonx Code Assistant and IBM plans to extend it over time to other languages.

The new tool is part of a larger set of IBM products, including  IBM's Application Discovery and Delivery Intelligence (ADDI) inventory and analysis tool. IBM says that having used ADDI, organizations can use their products to refactor business services in COBOL, transform COBOL code to Java code with an optimized design, and validate the resulting outcome, including using automated testing capabilities.

Kareem Yusuf, PhD, Senior Vice President, Product Management and Growth, IBM Software, said:

"Code Assistant for Z is built to mitigate the risk of modernization while converting code optimized for IBM Z."

The resulting Java code from this solution will be object-oriented, and IBM says the solution is optimized to interoperate with the rest of the COBOL application, with CICS, IMS, DB2, and other z/OS runtimes. Java on Z is designed to be performance-optimized versus a compared x86 platform.

This solution is expected to be generally available in Q4.

More Information

Watsonx Website

Related Articles

Pyro Now On Watson Machine Learning

IBM Watson and Project Intu for Embodied Cognition

IBM, Slack, Watson and the Era of Cognitive Computing

$200 Million Investment In IBM Watson

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

Comments

Make a Comment or View Existing Comments Using Disqus

or email your comment to: comments@i-programmer.info