# Google targets AI agents' idle-time costs with new compute service

DevFeed: [Google targets AI agents' idle-time costs with new compute service](<https://devfeed.tech/articles/google-targets-ai-agents-idle-time-costs-with-new-compute-service-97666.md>)

Original publisher: [Read original article](<https://www.infoworld.com/article/4239685/google-targets-ai-agents-idle-time-costs-with-new-compute-service.html>)

Author: Anirban Ghoshal

Published: 2026-10-23T12:42:19Z

Content type: news

Language: en

Sources: [InfoWorld](<https://devfeed.tech/sources/infoworld.md>)

Topics: [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [virtual machines](<https://devfeed.tech/topics/virtual-machines.md>), [long-running](<https://devfeed.tech/topics/long-running.md>), [virtualization](<https://devfeed.tech/topics/virtualization.md>), [cost-optimization](<https://devfeed.tech/topics/cost-optimization.md>), [Infrastructure as a Service (IaaS)](<https://devfeed.tech/topics/infrastructure-as-a-service-iaas.md>)

Tags: [agent-compute-engine](<https://devfeed.tech/tags/agent-compute-engine.md>), [agent-state](<https://devfeed.tech/tags/agent-state.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-development-tools-software-development](<https://devfeed.tech/tags/artificial-intelligence-development-tools-software-development.md>), [cios](<https://devfeed.tech/tags/cios.md>), [cloud-compute](<https://devfeed.tech/tags/cloud-compute.md>), [compute](<https://devfeed.tech/tags/compute.md>), [compute-resources](<https://devfeed.tech/tags/compute-resources.md>), [containers](<https://devfeed.tech/tags/containers.md>), [context](<https://devfeed.tech/tags/context.md>), [costs](<https://devfeed.tech/tags/costs.md>), [development-tools](<https://devfeed.tech/tags/development-tools.md>), [environment](<https://devfeed.tech/tags/environment.md>), [execution](<https://devfeed.tech/tags/execution.md>), [google](<https://devfeed.tech/tags/google.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [isolation](<https://devfeed.tech/tags/isolation.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [long-running](<https://devfeed.tech/tags/long-running.md>), [long-running-agents](<https://devfeed.tech/tags/long-running-agents.md>), [service](<https://devfeed.tech/tags/service.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [storytype-news](<https://devfeed.tech/tags/storytype-news.md>)

## AI overview

Google's Agent Compute Engine (ACE) suspends inactive agents in hardware-isolated microVMs and restores their execution state on demand, aiming to cut idle compute costs without rebuilding the environment and context. MicroVMs have their own kernels, offering stronger isolation than containers, and are intended to initialize with less overhead than conventional VMs. Potential savings depend on agents spending meaningful time idle; continuously active workloads may benefit less, while persistent microVM storage can add costs. The excerpt says ACE is closely integrated with Google Cloud and was not yet in preview, so portability, operational complexity, and production performance remain concerns. It contrasts ACE's checkpointing of memory and execution state with AWS AgentCore's per-session microVMs and Microsoft Foundry's suspension between turns. Checkpointing can leave external actions in an uncertain state if interrupted mid-operation; developers may need repeat-safe actions, expiry policies, fresh workspace rebuilds, and tools for debugging suspended environments.

## Source excerpt

As enterprises scale AI agents, Google is betting that idle infrastructure costs could become a major barrier to adoption. To address that challenge, the company on Thursday launched Agent Compute Engine, a service that suspends inactive agents and restores them on demand while preserving their execution state. AI agents often spend long periods waiting for instructions, tool responses, or human approvals. While enterprises can reduce costs by shutting down the underlying compute resources, restarting agents typically requires rebuilding the execution environment and restoring context, adding latency. Google says its new Agent Compute Engine addresses that trade-off by preserving agent state in hardware-isolated microVMs that can be suspended and resumed on demand. That choice of microVMs is intended to reduce the overhead associated with conventional virtual machines, which typically take longer to boot and require more resources to initialize, the company wrote in a blog post. Additionally, microVMs offer stronger isolation than containers, which are commonly used by enterprises for running AI agents on shared infrastructure. Unlike containers, which share the host operating system's kernel, microVMs run their own kernels, providing a stronger isolation boundary for agents executing AI-generated code or handling untrusted inputs, limiting the potential impact of compromised agents, the company added. Lower costs for long-running agents The ability to suspend and resume an agent's computing environment swiftly will help CIOs save costs, at least for long-running coding and research agents that hold state for hours or days, said Amit Kumar Jena, AI development head at IT consulting firm Kanerika. More so because traditional cloud compute was not built for long-running agents that activate thousands of times and otherwise sit idle, echoed Manoj Chandra Jha, principal analyst at Nord-IQ Research. As agents move from pilots to fleets of thousands, idle compute cost whe