IBM Launches watsonx GenAI Powered Code Assistant

IBM launches watsonx Code Assistant, putting AI-assisted code development and app modernization tools into the hands of developers.

IBM made another big bet on generative AI for developers with the release last week of watsonx Code Assistant, a generative AI-powered assistant designed to help enterprise developers and IT operators code more quickly and accurately using natural language prompts.

The new code assistant leverages generative AI based on IBM's Granite foundation models for code running on IBM's watsonx platform, explained Dinesh Nirmal, senior vice president in IBM's Software group, in a blog post. This family of flexible, reusable AI models uses the "Decoder" architecture, which underpins large language model capabilities to predict what is next in a sequence to support natural language processing tasks. At 13 billion parameter models, the Granite models are more efficient than larger models, the company says, fitting onto a single V100-32GB GPU. IBM says it is "exploring opportunities" to tune watsonx Code Assistant with additional domain-specific generative AI capabilities to assist in code generation, code explanation, and the full end-to-end software development lifecycle to continue to drive enterprise application modernization.

"With this launch, watsonx Code Assistant joins watsonx Orchestrate and watsonx Assistant in IBM's growing line of watsonx assistants that provide enterprises with tangible ways to implement generative AI," said Kareem Yusuf, senior vice president in IBM's Product Management and Growth group, in a statement. "Watsonx Code Assistant puts AI-assisted code development and application modernization tools directly into the hands of developers – in a naturally integrated way that is designed to be non-disruptive – to help address skills gaps and increase productivity."

The Code Assistant currently delivers on two specific enterprise use cases, the company says: IT Automation with watsonx Code Assistant for Red Hat Ansible Lightspeed, for tasks such as network configuration and code deployment; mainframe application modernization with watsonx Code Assistant for Z, for translation of COBOL to Java.

Code Assistant for Red Hat Ansible Lightspeed is a generative AI service designed by and for Ansible automators, operators, and developers. With IBM watsonx, platform users can input plain English prompts to automatically generate task recommendations for Ansible Playbooks that adhere to best practices in task creation and maintenance, the company says. This way, a greater number of team members can create Ansible Playbooks more efficiently and implement automation engineered to be more resilient and easier to support without in-depth training.

"Red Hat has already shown what domain-specific AI can do for IT automation at the community level," said Ashesh Badani, senior vice president and chief product officer at Red Hat. "The release of watsonx Code Assistant for Red Hat Ansible Lightspeed has the potential to close skills gaps, create greater organizational efficiencies and free enterprise IT to deliver even more business value."

IBM watsonx Code Assistant for IBM Z lets developers selectively translate COBOL applications to high-quality Java code optimized for IBM Z and the hybrid cloud. It enables faster translation of COBOL to Java and enhances developer productivity on the platform, the company says. It was designed to assist businesses in leveraging generative AI and automated tooling to accelerate their mainframe application modernization, while allowing clients to take advantage of the performance, security, and resiliency capabilities of IBM Z. The company expects future releases to include support for automated test-case generation to validate the new COBOL or Java services.

About the Author

John K. Waters is the editor in chief of a number of sites, with a focus on high-end development, AI and future tech. He's been writing about cutting-edge technologies and culture of Silicon Valley for more than two decades, and he's written more than a dozen books. He also co-scripted the documentary film Silicon Valley: A 100 Year Renaissance, which aired on PBS.  He can be reached at