Red Hat integrated IBM's generative artificial intelligence (genAI) watsonx Code Assistant with its Ansible Lightspeed IT automation platform to provide a suite of tools that work together to build and test automation code for cloud, data center and on-premise environments. But this "is more than just a language model," Red Hat Chief Ansible Architect Matthew Jones told SDxCentral.

As opposed to a general purpose large language model (LLM), Lightspeed with watsonx relies on Red Hat's technical expertise in writing the tools and plugins Ansible developers use, combined with the benefits of a purpose-built language model. "We’re bringing a commercial offering that’s highly targeted at automation, specifically Ansible automation," Jones said.

Now generally available, this service aims to increase the efficiency of IT teams that are writing automation code. Instead of spending hours or days on these tasks, Lightspeed with watsonx drops that time to minutes, the vendors claim. Most enterprises can expect to immediately see the benefits of this AI tool, particularly in terms of "how fast their teams can write automation and build trust in that automation — and their own skills," he said. The service also supports best practices and organization-wide code maintenance for consistent automation.

By inputting prompts like Configure my firewall to open X ports, or Create an EC2 instance with 2 CPUs and 4 GB of memory, users receive code recommendations based on IBM's watsonx AI Code Assistant.

Prompts can also be used to create and edit Ansible Playbooks, which provide a repeatable and reusable configuration management and multi-machine deployment system that's well-suited for deploying complex applications. "If you need to execute a task with Ansible more than once, write a playbook and put it under source control. Then you can use the playbook to push out a new configuration or confirm the configuration of remote systems," Jones said.

With a "straightforward text prompt," users receive an AI-generated output translated into YAML code, which accelerates the process of creating an Ansible Playbook. For experienced users, this substantially improves productivity. For novice coders, it reduces barriers to entry and expands the definition of who can create content with Ansible.

In a move to support transparency and Red Hat's "open source values," the service includes content source matching that provides visibility into "potential sources, authors and licenses" that helped train the data used to generate code recommendations.

The vendor anticipates contributors will be able to be recognized for their efforts, which should increase IT teams' trust in AI-generated code. Those upstream contributors also have the option to have their work excluded from model fine-tuning.

The emphasis on transparency also serves to empower users and community members to find new use cases and drive innovation forward, Red Hat Head of Ansible Product Management Richard Henshall said. "Empowered users and teams no longer rely on others to make moves; they will make it happen, because they can," he wrote in a blog.

This commercial version of Red Hat Ansible Lightspeed is available as a subscription, and the IBM watsonx Code Assistant is available separately, but "all you need is VSCode with the Ansible plugin installed" to get the service running, Jones said.