Natural language-driven artificial intelligence tools are currently all the rage — think ChatGPT.

But what if that same conversational AI experience is carried over to automating platform engineering and DevOps functions? That’s always been the main focus at Kubiya Inc., a DevOps virtual assistant for cloud operations.

“We’ve branded ourselves as ‘ChatGPT for DevOps,'” said Amit Eyal Govrin (pictured), chief executive officer of Kubiya. “End users can go and consume DevOps functions and platform engineer functions very easily using natural language prompting. Through Slack, [Microsoft] Teams or any type of chat interface, they can very easily attribute their natural language to automation, knowledge bases and so forth.”

Govrin spoke with theCUBE industry analyst Savannah Peterson and guest analyst Joep Piscaer, at the KubeCon + CloudNativeCon Europe event, during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed the Kubiya value proposition as it relates to abstracting complexity away from developers. (* Disclosure below.)

Fine-tuning the operator experience

Two of the main problems DevOps and platform engineering teams face are rollout and maintenance. In response, Kubiya has embedded large language models allowing end users to prompt any workflow using natural language, according to Govrin.

“It will go and generate that workflow with all of your business logic and all of the access controls baked in,” he explained. “Now you can easily fine-tune it, drag and drop it in a low-code interface, play it back, simulate it and then commit it to your organization within minutes instead of hours.”

For citizen developers and business users looking to mitigate the complexities of DevOps, Kubiya’s self-service model lets them operationalize workflows in a simple and secure way. Additionally, they can quickly validate and test those workflows using the low-code editor, Govrin added.

“There are two sides to the coin,” he said. “First, with the end-user experience, it extends things very naturally to users, so they don’t have to either flag one of the operators in the loop and get their help or otherwise low-code in order to interact with the system. Then for the operators, it’s really velocity without raising overheads.”

Here’s the complete video interview, part of SiliconANGLE’s and theCUBE’s coverage of the KubeCon + CloudNativeCon Europe event:

(* Disclosure: This is an unsponsored editorial segment. However, theCUBE is a paid media partner for KubeCon + CloudNativeCon. Neither Red Hat Inc. nor other sponsors of theCUBE’s event coverage have editorial control over content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE