Amazon Bedrock AgentCore
Agentic platform to build, deploy and operate agents securely at scale - using any framework and model
What is Amazon Bedrock AgentCore?
Amazon Bedrock AgentCore is an agentic platform to build, deploy, and operate highly capable agents securely at scale. With AgentCore you can easily enable agents to take actions across tools and data, run agents securely with low-latency and extended runtimes, and monitor agents in production - all without any infrastructure management. AgentCore is comprised of fully-managed services that can be used together or independently and work with any framework (including CrewAI, LangGraph, LlamaIndex, Google ADK, OpenAI Agents SDK, and Strands Agents), as well as any foundation model - eliminating the choice between open-source flexibility and enterprise-grade security and reliability.
Bedrock AgentCore Capabilities
Deploy agents securely at scale
Deploy and scale highly-capable agents securely using any framework, protocol, or model in or outside of Amazon Bedrock. Benefit from complete session isolation and industry leading support for long-running workloads up to 8 hours, enabling complex, multi-step agent tasks. Manage agent identity and access seamlessly across your services with native integration to your existing identity providers for automated authentication and permission delegation.
Enhance agents with tools and memory
Enable intelligent, personalized experiences with persistent memory that maintains agent knowledge across interactions. Easily connect agents to your existing tools and services with a gateway that transforms them into agent-ready capabilities with minimal code. Enhance your agents with powerful built-in tools including a secure browser runtime to help agents execute complex web-based workflows and a code interpreter to securely execute code for tasks such as generating visualizations.
Comprehensive observability to boost performance
Gain deep operational insights with real-time visibility into your agents' performance through comprehensive monitoring dashboards powered by Amazon CloudWatch. Track key metrics such as token usage, latency, session duration, and error rates to support optimal operations. Trace, debug issues, audit agent decisions, and support compliance with visibility into the entire agent workflow. Integrates seamlessly with your existing observability systems via OpenTelemetry.
Bedrock AgentCore Benefits
Faster time to value
Accelerate from prototype to production with fully-managed services that eliminate infrastructure complexity, so you can bring groundbreaking agentic solutions to market faster.
Flexibility and interoperability
Build agents your way using any framework, model, or tool—while maintaining complete control over how your agents operate and integrate with existing systems.
Security and trust
Deploy with confidence using enterprise-grade security features, including complete session isolation, Amazon VPC connectivity, AWS PrivateLink support, and comprehensive controls—all designed to ensure your agents operate reliably and securely at scale.
Bedrock AgentCore Services
Bedrock AgentCore in Action
Transforming AI agents with AgentCore
Join Swami Sivasubramanian, VP of Agentic AI at AWS, as he shares the vision behind Amazon Bedrock AgentCore and how it transforms the enterprise AI landscape. Learn how AgentCore's comprehensive suite of services addresses critical business challenges in deploying production-ready agents, from security and scalability to operational excellence. Discover how leading organizations are leveraging AgentCore to accelerate their AI initiatives while maintaining enterprise-grade security and reliability.
Getting hands-on with AgentCore
Watch AWS Developer Advocate Mike Chambers demonstrate AgentCore services in this hands-on technical walkthrough. Follow along step-by-step as Mike deploys an agent, implements secure tool integrations, and sets up monitoring. This practical demonstration covers AgentCore services including Runtime, Gateway, Memory, and how to leverage AgentCore Observability capabilities to monitor and debug agent behavior in production.
Marketing campaign automation with AgentCore
Watch Prashanth Athota, SVP of Product Engineering at Epsilon, as he shares how they revolutionized campaign automation using Amazon Bedrock AgentCore. Learn how Epsilon reduced campaign setup time by 30%, increased personalization by 20%, and saved teams 8 hours weekly. Discover how AgentCore enabled them to scale AI-powered marketing while maintaining enterprise security and reliability.
Customers
Epsilon
"At Epsilon, we manage thousands of personalized marketing campaigns daily for the world's leading brands. We saw an opportunity to revolutionize our campaign execution through AI-driven automation. Using AgentCore, we rapidly prototyped and deployed an AI-powered campaign orchestration system within days instead of weeks. AgentCore Runtime enabled us to deploy and scale agents effortlessly, while AgentCore Observability gave us a clear view of our agents in action. The impact has been remarkable: we've reduced campaign setup time by 30%, increased personalization capacity by 20%. Most significantly, we've scaled campaign creation by 20% while saving our teams 8 hours per week. This isn't just about efficiency - it's about reimagining what's possible in modern marketing. With AgentCore, we've built a next-generation platform that's setting new standards for AI-driven customer engagement.“
— Prashanth Athota, SVP, Product Engineering/Architecture, Epsilon Data Management
Thomson Reuters
"At Thomson Reuters, we're reimagining content workflows that we've built over decades. We see a significant opportunity with agentic systems - not just for automation, but for process simplification, improving content currency and quality, and modernizing our technology stack. We're exploring Amazon Bedrock AgentCore because of its potential to accelerate how we build and deploy agentic workflows, compressing timelines from months to weeks. What's compelling is how AgentCore reduces our engineers' cognitive load by abstracting away infrastructure complexity - agent runtimes, observability, lifecycle management - so they can focus on solving the business problems that matter.“
— Emre Caglar, Head of Product Engineering, Content and RFC
Experian
“Experian, a global data and technology leader, prioritized enhancing B2B client experience in data exploration, risk management, and fraud investigation. Our Experian Ascend Platform™ integrates data, software, and AI to help financial institutions manage risk while growing their business. Traditional agent deployment created bottlenecks through complex infrastructure requirements and limited scalability. AgentCore's Runtime service solved deployment challenges by providing a secure, standardized layer, while its Memory service helps maintain conversation context across customer interactions. AgentCore's modular architecture eliminates infrastructure complexity, accelerating our prototype-to-production timeline. Since implementing these agents through our Ascend platform, we've improved business service processing times and fraud detection accuracy while maintaining compliance standards.”
— Ravi Devesetti, Global CTO, Experian Software Solutions
Cox Automotive
“At Cox Automotive, we’re transforming our customer experience with generative and agentic AI. AgentCore is one of the strategic platforms we’re using to deploy AI agents at scale, ranging from virtual assistants that improve our omnichannel dealer experience to an agentic marketplace that streamlines vehicle discovery and buying. AgentCore’s key services – Runtime for secured deployments, Observability for monitoring, and Identity for authentication – are enabling our teams to develop and test these agents efficiently as we scale AI across the enterprise"
— Marianne Johnson, EVP & Chief Product Officer, Cox Automotive
Amazon Devices
“Within Amazon Devices Operations & Supply Chain team, we’re leveraging AgentCore to develop agentic solutions for manufacturing processes to save on development costs and accelerate time-to-market. We implemented specialized agents — including a Task Planning agent for converting business requirements into station-level instructions and a Model Training agent for optimizing robotic vision. As a result, fine-tuning an object detection model, which used to take days of engineering time, can now be done in under an hour with high precision. With AgentCore's built-in monitoring and multi-agent communication capabilities, our teams can spend more time on core functionality rather than infrastructure management.”
— John Powell, Leader of Advanced Manufacturing and Quality, Amazon Devices
Pricing
Tailor AgentCore to your needs—mix and match services, use them independently or together, and pay for what you use as your AI initiatives grow. Learn more on the AgentCore pricing page.
I want to
learn more about AgentCore
Did you find what you were looking for today?
Let us know so we can improve the quality of the content on our pages