Temporal takes on the chaos behind enterprise AI agents

AI Temporal takes on the chaos behind enterprise AI agents Devony Hof July 21, 2026 3 MIN READ link reply With more agents comes more complexity — an issue Temporal Technologies Inc. aims to address. Founded in 2019, Temporal offers an open-source durable execution platform that ensures artificial intelligence agents work as designed. Becoming available on Amazon Web Services Marketplace has given the company a wider reach, with big-name clients hoping to better manage their agentic workflows on Temporal’s platform. “Our platform basically handles all of the complexities around making the agents run reliably,” said Preeti Somal (pictured), senior vice president of engineering at Temporal. “It is built on top of technology that is battle-tested and hardened and runs at scale and really focuses on all of the error handling, retries, state management, all of this stuff we don’t want developers to think about.” Somal spoke with theCUBE’s John Furrier during an interview for the AWS Marketplace Series on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed what Temporal offers to the rapidly evolving agentic ecosystem and its partnership with AWS. (* Disclosure below.) Temporal introduces support for serverless AI Although companies have their pick of models and agents, maintaining the delicate interplay between the software components can prove tricky in the long term, according to Somal. Temporal provides the underlying intelligence and structure to solve issues as they arise over time. “The basic crux of the speed change that we deliver is not needing to worry about all the scaffolding that goes into building real applications,” Somal said. “Depending on what study you believe, more than 50% of a developer’s time is built around all of the error handling pieces. With Temporal, you don’t worry about that.” Temporal also addresses the growing speed of adoption. If a company builds an agent and it goes “viral,” the last thing that company wants is to have production failures. Temporal’s platform is built to scale with a client’s application, preventing further problems down the line and allowing successful applications to keep their momentum. “The platform we’ve built essentially has all the heavy lifting around queue management, task dispatching, flow control,” Somal said. “And so when these spikes happen, we are making sure that your system isn’t falling over, that no task is lost, and that as your workers can keep up with that load coming in, you’re still responding to your customers in the application. And we’ve been able to scale up to 150,000 actions per second.” Somal gave a demonstration of the platform, which is integrated with AWS Strands, an open-source software development kit for building and running AI agents. Temporal recently launched a new service, Serverless Workers, which enables users to run Temporal’s tools on AWS Lambda, a serverless compute service. “We are doing a lot of work around making sure that we can unlock the real power of AI with longer-running agents,” Somal said. “We have customers like Stripe, Netflix, Datadog, Snap, all of them trusting Temporal to run their agents and AI applications. That is honestly what really drives us here at Temporal, is making developers successful and enabling them to focus on their business logic versus all of the scaffolding that they’ve had to deal with over all these years.” Here’s the complete video interview, part of SiliconANGLE’s and theCUBE’s coverage of the AWS Marketplace Series: (* Disclosure: TheCUBE is a paid media partner for the AWS Marketplace Series. Neither AWS, the sponsor of theCUBE’s coverage, nor other sponsors have editorial control over content on theCUBE