Google LLC wants to put an end to the notion that serverless computing can’t scale — and it’s doing it with Cloud Run, a platform built for the agentic age of artificial intelligence.

Cloud Run lets developers run containerized workloads directly on Google’s global infrastructure, combining serverless simplicity with on-demand scalability, according to Belinda Runkle (pictured, center), senior director of engineering, serverless, Google Cloud, at Google.

Google Cloud’s Belinda Runkle and Lisa Shen talk with theCUBE about serverless.

“We run functions. We run containers. We can run from source code, and it’s very lightweight — no management, fast scale up, scales to zero, pay as you go … and really has been kind of the evolution of how to get sort of ready-made compute in a very low-toil sort of way for developers,” Runkle said.

Runkle and Lisa Shen (right), product manager at Google Cloud, spoke with theCUBE’s Savannah Peterson for the “Google Cloud: Passport to Containers” interview series, during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed the rise of agentic AI and the magic of a serverless platform such as Cloud Run. (* Disclosure below.)

Building systems around AI agents

To say there is a lot of buzz around agentic AI in the enterprise world would be an understatement. Shen describes it as “giving code a brain” and suggests that the increase in agentic offerings will lead to a higher proportion of business processes being fully automated.

“Large language models are the brain of an agent, and then the tools are really like the agent’s hands reaching out to the digital world,” she said. “You have agent plus tools, and then the large language models plus tools, then an AI agent to help you accomplish a specific task.”

Google Cloud foresees the development of multi-agent systems, with individual agents that can reason independently based on tailored data sets. Retail and customer service have seen several applications for generative AI, and now agentic AI, but the potential use cases are wide-ranging. Shen offers the example of a financial advisor agent comprised of multiple sub-agents.

“Let’s say you have a stock symbol that you’re interested in buying,” she said. “[The advisor agent] has this data analysis sub-agent that actually takes the stock symbol, and it’s going to pull out the [U.S. Security and Exchange Commission] data and go to Google or some other website to get all the information, recent publications, recent news related to this stock and … come up with a data analysis report.”

How does Cloud Run support agentic AI? The answer is scalability, according to Runkle. The platform offers an on-demand model so that users can access the amount of compute power they need for their applications at a given time. This capability offsets costs and fosters growth for Google Cloud’s customers.

“Where you have multiple agents, typically what’s happening is something needs to be spun off,” Runkle explained. “I’m going to assign a task, a thinking task, a context task … and each of those is going to basically spin up a little unit of work that needs to get done. That ability to do fast fan out, fast scale up, scale to zero when it’s done … those things are already built into Cloud Run.”

Proving serverless can scale

Cloud Run has remained a cost-effective option by offering serverless graphics processing units on a pay-as-you-go model. While agents don’t necessarily require GPUs, that kind of compute power is necessary for any kind of inference. Cloud Run has capabilities that not only support developers, but also a variety of enterprise customers, according to Runkle.

“When they think Cloud Run, they assume it’s a functions offering,” she said. “While it’s serverless in nature, it is not at all defined to functions. Actually, most of what customers bring to us are containers. So, it’s really more of a container orchestration that has a lot of the same simplicity and magic of what you would think of when you think of serverless.”

When it comes to the future of Cloud Run, Shen is most excited about “wipe coding” — or AI-generated code. She sees the potential for it to democratize AI by allowing non-developers to realize their ideas.

“Wipe coding is all about how you turn the ideas into code with minimum friction,” Shen said. “Cloud Run [is] a natural fit, and the next step, where then you turn your source code into a live, functional app, with no time, and with minimum infrastructure to manage. Then wipe coding is also all about this instantaneous feedback loop, and Cloud Run basically gives you all these faster iterations.”

Here’s the complete video interview, part of SiliconANGLE’s and theCUBE Research’s coverage of the “Google Cloud: Passport to Containers” interview series:

(* Disclosure: TheCUBE is a paid media partner for the “Google Cloud: Passport to Containers” series. Neither Google Cloud, the sponsor of theCUBE’s event coverage, nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE