Red Hat’s Mark Swinson breaks down one of the company’s latest additions to its automation capabilities for developers.
Automation can be especially helpful in the area of enterprise software, where businesses are striving for efficiency, scalability and streamlined operations.
From automating repetitive tasks to orchestrating complex workflows, organisations are increasingly turning to automation tools to drive productivity, reduce human error and unlock new possibilities.
With the ever-growing demand for seamless integration, heightened security and rapid deployment, companies are working hard to bring automation into their enterprise software offerings.
One such example is Ansible Lightspeed, the latest addition to Red Hat’s Project Wisdom, a capability that automatically generates code for developers on Red Hat Ansible through a natural-language interface.
Mark Swinson is an experienced enterprise IT automation specialist with Red Hat, where he is responsible for helping customers solve their business challenges with hybrid cloud tools.
“I’ve spent my entire career working in enterprise software and it’s been a fascinating journey because it is a field constantly changing and innovating,” he told SiliconRepublic.com.
“One thing that has been a common thread throughout is automation – whether that was workflow systems to help streamline business processes or IT service management tools and ITIL (Information Technology Infrastructure Library) standards to help improve IT service efficiency and quality.”
He said Ansible Lightspeed, which will be available as a beta for evaluation and feedback in 2023, is like “having an expert sitting next to you” as you work on content for the Red Hat Ansible Automation Platform (AAP).
AAP is a tool used for automating the kind of repetitive tasks that system administrators have to perform every day. “Its power is its ability to automate practically every type of IT resource, whether that’s servers, storage, networks or cloud infrastructure. That comes from a wealth of content that’s been developed by users of the tool and vendors of IT products,” said Swinson.
“Ansible Lightspeed helps you to tap into that collective ‘expertise’ in a very easy way. It is able to write, review and correct Ansible configuration, helping you to write better automation, prevent mistakes and deliver a more consistent approach to automating your systems.”
Bringing generative AI to automation
Ansible Lightspeed is based on a generative AI model, IBM’s Watsonx.ai, which is a foundation model, like that at the heart of ChatGPT.
Watsonx.ai has been trained exclusively on verified Ansible content. According to Swinson, additional pre- and post-processing means the code it produces in response to natural language requests is much more reliable and accurate than what a general-purpose model would produce.
“It is also able to give the user information about where its answer comes from, so it’s possible to verify the validity and authenticity of the code it generates. Contributors to the Ansible content, known as Ansible Galaxy, will be able to choose whether their contributions are included in the Ansible Lightspeed model,” he said.
“In addition, the model can be refined with content specific to a user’s situation. This means an organisation can ‘tune’ the results – for example, to include standards and policies that they wish to enforce.”
The challenges of automation
As an automation specialist, Swinson is naturally a big fan of bringing more automation into areas of work that can make sure users are more productive.
He said the biggest challenge when it comes to automation projects such as these is around skills.
“Although Ansible’s definitions are expressed in human-readable YAML, and as mentioned before, a wealth of content is already available, there is still a learning curve,” he said.
“By reducing the barrier to entry for new teams getting up-to-speed with AAP, Ansible Lightspeed should accelerate adoption and help organisations to standardise on AAP and ultimately be more productive faster.”
And while the learning curve can be a challenge across all automation technologies, Swinson said they still come with benefits such as better security, fewer faults and outages and more responsive IT departments as changes can be actioned faster.
“Helping people to do less repetitive manual tasks is a good start, but when we connect the power of AAP to fix things with the always-on monitoring that other tools bring, then we begin to see how systems can address common failures without needing human intervention.”
10 things you need to know direct to your inbox every weekday. Sign up for the Daily Brief, Silicon Republic’s digest of essential sci-tech news.