AI agents are no longer limited to isolated, one-off prompts; they now carry out multi-step workloads that can run for hours. Citing METR, the length of task that frontier agents can finish on their own doubles roughly every four months, and according to McKinsey, 40 percent of large enterprises are now scaling AI agents, up from 27 percent a year earlier. As agents gain autonomy and run longer, attention is shifting from what they can do to how securely, reliably and economically they operate at scale. Because agents execute code, drive browsers, reach sensitive data and act on behalf of users, they create security and infrastructure demands that make strong isolation a prerequisite for production use.
Every agent session needs a secure, isolated environment, but providing that isolation at scale forces a trade-off among performance, cost and efficiency. Pre-provisioned environments consume resources even while idle, while on-demand environments save capacity at the price of cold-start latency. As organizations move from a handful of agents to thousands of concurrent sessions, custom-built sandboxes become more complex, expensive and unpredictable to operate. Figures from Deloitte underline the difficulty: only 15 percent of organizations have scaled orchestrated multi-agent systems, and 70 percent say they cannot yet trust and govern their agents.
The next generation AgentCore runtime
Amazon built Bedrock AgentCore to let developers build, connect and optimize agents securely at scale. AgentCore runtime, one of its capabilities, is the managed compute layer that gives developers a fully managed environment for deploying and running agents without building or maintaining infrastructure. AWS says customer workloads have grown more complex since launch, increasing demand for more compute, more flexible billing and trust boundaries that extend to data rather than compute alone.
The announced updates keep the core guarantee in place: every session still runs inside its own hardware-isolated Firecracker micro virtual machine (MicroVM), with its own identity, policy and audit trail. Within that boundary, sessions now start up to 15 times faster, scale to four times more compute and run up to 68 percent more efficiently.
Bigger workloads without longer waits
Sessions now scale to four times the previous limits, reaching up to 8 vCPUs and 32 GB of memory, and support container images of up to 10 GB, covering workloads from large codebase compilations to browser-driven flows and local model inference. Startup takes under two seconds regardless of image size or concurrency, so warm pools and pre-provisioned clusters are no longer needed to mask cold starts.
Customer reactions included in the announcement:
"Migrating to the next generation of AgentCore runtime reduced our agent session cold starts from nearly a minute to under five seconds, even during peak traffic. It also eliminated startup delays longer than 30 seconds, all while our weekly agent volume more than doubled." — Siwei Shen, VP of Engineering, Coinbase
"Mission is using Amazon Bedrock AgentCore runtime to power a natural-language query agent that helps users retrieve property and sales insights without navigating complex data systems. In our initial comparison of both runtime versions, the same workload delivered 35% faster cold starts for inference requests and 77% faster starts for health checks, while reducing measured runtime cost per call by 17%. The new AgentCore runtime gives us a compelling combination of faster agent experiences and more efficient resource utilization as we bring enterprise agents into production." — Dr. Ryan Ries, Chief AI & Data Scientist, Mission Cloud
"Our approach is to run Zuora's cloud with automation and AI agents wherever we can, and that only works if the runtime is efficient and reliable. The next generation AgentCore runtime cut our memory footprint per invocation by around 60% in many use cases while handling more traffic at steady latency. That gives us a stronger cost profile as we expand agentic workloads across our platform." — Brad Ruppert, VP of Cloud and Security, Zuora
"The Rescale platform helps R&D and engineering teams accelerate product development with agentic digital engineering. Our engineering-specific agents validate simulation inputs, troubleshoot jobs, select hardware, and generate reports, while engineers stay in control. Amazon Bedrock AgentCore runtime allows us to deploy and scale those agents in production without building or operating the underlying agent infrastructure, so we can deliver new agents to customers faster." — Mark Whitney, VP Engineering, Rescale
Stop paying for idle agents
Agents spend much of their runtime waiting on a model response, a tool call or a human decision, and AWS argues that billing should reflect the work performed rather than the time spent waiting. The runtime now reclaims memory within minutes of the agent releasing it, and an idle agent scales to zero. For multi-turn agents with natural pauses between interactions, AWS says this means up to 68 percent less memory consumed per session. Always-on agents can use committed baseline pricing, which sets a per-session memory baseline billed as a minimum while allowing bursts of up to four times that baseline on demand, at AWS Lambda MicroVM rates.
"The next generation Amazon Bedrock AgentCore runtime helps us deliver more responsive AI experiences by starting agents faster and using memory more efficiently. Aligning consumption with actual usage gives our clients great confidence to scale agentic solutions while keeping costs connected to real demand." — Ashwin Patil, Principal, AI and Data Leader, Deloitte Consulting LLP
"AgentCore runtime gives us a managed foundation for building agentic products and platforms around our customers' data, tools, and business processes. The next generation Agentcore runtime makes that foundation more responsive and resource-efficient by restoring initialized environments and reclaiming unused memory. We're beginning to build on the latest version because the cost and latency reductions make a significant difference in how our customers' businesses operate." — Randall Hunt, CTO, Caylent
Isolation extends to the data
A persistent gap remains in many enterprise agent security models: the agent runs inside an isolated session, but the data it needs, such as files, credentials and tool outputs accumulated during a long run, sits outside that boundary. Teams end up writing their own rules for moving data in and out, which adds complexity and risk with every new agent. The updated runtime lets agents dynamically mount and save work to a filesystem, for example an Amazon Simple Storage Service (Amazon S3) bucket with FUSE support, so data stays inside the trust boundary for the entire job under a single set of controls defined once.
"At Okta, the combination of AgentCore runtime and Lambda MicroVMs provide the isolated execution environment and contextual memory our agents need to inspect code, run test suites, and open pull requests within ephemeral sandboxes. Paired with our identity-governed policy controls, AgentCore Runtime and Lambda MicroVMs demonstrate how we can safely scale autonomous engineering agents without risking workspace leakage or privilege escalation." — Monica Bajaj, SVP Engineering, Okta
"From helping car shoppers value a trade-in to helping dealers book service appointments and structure deals, Amazon Bedrock AgentCore powers dozens of agentic solutions across Cox Automotive's brands. Having a single, governed agent platform lets our teams across our business move from pilot to production with confidence." — Chris Dillon, VP, Product and Engineering, Cox Automotive
Commitment and availability
AWS says the agents that reach production are the ones trusted to act on a user's behalf with real data, real stakes and real accountability, and frames this release as a step toward bigger sessions, efficient resource use and storage inside the trust boundary without loosening isolation. The company states that by re:Invent, per-session scoping will bind each session to its own storage folder through session-labeled credentials.
The next-generation AgentCore runtime is available in AWS Regions across North America, South America, Europe and Asia Pacific.