In this post, we demonstrate how you can use the A2A protocol for AI agents built with different frameworks to collaborate seamlessly. You’ll learn how to deploy A2A servers on AgentCore Runtime, configure agent discovery and authentication, and build a real-world multi-agent system for incident response. We’ll cover the complete A2A request lifecycle, from agent card discovery to task delegation, showing how standardized protocols eliminate the complexity of multi-agent coordination.

AWS Partners are leveraging Amazon Bedrock AgentCore to rapidly transform proof-of-concept AI innovations into production-ready enterprise solutions, delivering transformative value across industries from financial services to travel and banking. Early adopters like Caylent, Cisco, Genpact, PwC Australia, and Reply are achieving remarkable results—including faster response times, reduced developer cognitive load, and significant ROI—by utilizing AgentCore’s serverless runtime, memory management, and enterprise-grade security features.

    Amazon Bedrock AgentCore Runtime now supports direct code deployment 0 views Eyal Estrin unread, 4:22 AM (11 minutes ago)    to https://aws.amazon.com/about-aws/whats-new/2025/11/amazon-bedrock-agentcore-runtime-code-deployment/ https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-get-started-code-deploy.html https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/agentcore-get-started-toolkit.html Eyal Estrin CISSP, CCSP, CISM, CISA, CDPSE, CCSK Blog: https://security-24-7.com | Books: https://amzn.to/42Xai9A | https://amzn.to/3Sggbtv Twitter: @eyalestrin | Bluesky: @eyalestrin.bsky.social Reply all Reply to author Forward

Amazon Bedrock AgentCore is an agentic platform for building, deploying, and operating effective agents securely at scale. Amazon Bedrock AgentCore Runtime is a fully managed service of Bedrock…

Amazon Bedrock AgentCore is an agentic platform for building, deploying, and operating effective agents securely at scale. Amazon Bedrock AgentCore Runtime is a fully managed service of Bedrock AgentCore, which provides low latency serverless environments to deploy agents and tools. It provides session isolation, supports multiple agent frameworks including popular open-source frameworks, and handles multimodal [...]

Wow, can you all believe it? We’re nearing the end of the year already. Next thing you know, AWS re:Invent will be here! This is our biggest event that takes place every year in Las Vegas from December 1st to December 5th where we reveal and release many of the things that we’ve been working […]

AWS has made Amazon Bedrock AgentCore generally available, introducing a modular, enterprise-grade platform for securely building, deploying, and managing production AI agents using any framework or m...

Amazon Bedrock AgentCore is an agentic platform to build, deploy and operate highly capable agents securely at scale using any framework, model, or protocol. AgentCore lets you build agents faster, 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. With general availability, all AgentCore services now have Virtual Private Cloud (VPC) support, enabling secure, private agent deployment. AgentCore Runtime builds on its preview capabilities of industry-leading eight-hour execution windows and complete session isolation by adding support for the Agent-to-Agent (A2A) protocol, with broader A2A support coming soon across all AgentCore services. AgentCore Gateway now connects to existing Model Context Protocol (MCP) servers in addition to transforming APIs and Lambda functions into agent-compatible tools. Gateway provides a single, secure endpoint for agents to discover and use tools without the need for custom integrations. AgentCore Identity now offers identity-aware authorization, secure vault storage for refresh tokens, and native integration with additional OAuth-enabled services so agents can securely act on behalf of users or by themselves with enhanced access controls. AgentCore Observability now delivers complete visibility into end-to-end agent execution and operational metrics across all AgentCore services through dashboards powered by Amazon CloudWatch, and it is OTEL compatible, offering seamless integration with Amazon CloudWatch and external observability providers like Dynatrace, Datadog, Arize Phoenix, LangSmith, and Langfuse. AgentCore works with any open source framework (CrewAI, LangGraph, LlamaIndex, Google ADK, OpenAI Agents SDK) and any model in or outside Amazon Bedrock, giving you freedom to use your preferred frameworks and models, and innovate with confidence. Amazon Bedrock AgentCore is available in nine AWS Regions: US East (N. Virginia), US East (Ohio), US West (Oregon), Asia Pacific (Mumbai), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Europe (Frankfurt), and Europe (Ireland). Learn more about AgentCore through the https://aws.amazon.com/blogs/machine-learning/amazon-bedrock-agentcore-is-now-generally-available/, deep dive using the https://aws.amazon.com/bedrock/agentcore/resources/, and get started with the https://github.com/aws/bedrock-agentcore-starter-toolkit. AgentCore offers https://aws.amazon.com/bedrock/agentcore/pricing/ with no upfront costs.

Amazon Bedrock AgentCore is an agentic platform to build, deploy and operate highly capable agents securely at scale using any framework, model, or protocol. AgentCore lets you build agents faster, 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. With general availability, all AgentCore services now have Virtual Private Cloud (VPC) support, enabling secure, private agent deployment. AgentCore Runtime builds on its preview capabilities of industry-leading eight-hour execution windows and complete session isolation by adding support for the Agent-to-Agent (A2A) protocol, with broader A2A support coming soon across all AgentCore services. AgentCore Gateway now connects to existing Model Context Protocol (MCP) servers in addition to transforming APIs and Lambda functions into agent-compatible tools. Gateway provides a single, secure endpoint for agents to discover and use tools without the need for custom integrations. AgentCore Identity now offers identity-aware authorization, secure vault storage for refresh tokens, and native integration with additional OAuth-enabled services so agents can securely act on behalf of users or by themselves with enhanced access controls. AgentCore Observability now delivers complete visibility into end-to-end agent execution and operational metrics across all AgentCore services through dashboards powered by Amazon CloudWatch, and it is OTEL compatible, offering seamless integration with Amazon CloudWatch and external observability providers like Dynatrace, Datadog, Arize Phoenix, LangSmith, and Langfuse. AgentCore works with any open source framework (CrewAI, LangGraph, LlamaIndex, Google ADK, OpenAI Agents SDK) and any model in or outside Amazon Bedrock, giving you freedom to use your preferred frameworks and models, and innovate with confidence. Amazon Bedrock AgentCore is available in nine AWS Regions: US East (N. Virginia), US East (Ohio), US West (Oregon), Asia Pacific (Mumbai), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Europe (Frankfurt), and Europe (Ireland). Learn more about AgentCore through the blog, deep dive using the AgentCore resources, and get started with the AgentCore Starter Toolkit. AgentCore offers consumption-based pricing with no upfront costs.

AI agents are evolving beyond basic single-task helpers into more powerful systems that can plan, critique, and collaborate with other agents to solve complex problems. Deep Agents—a recently introduced framework built on LangGraph—bring these capabilities to life, enabling multi-agent workflows that mirror real-world team dynamics. The challenge, however, is not just building such agents but [...]

AI agents are a new class of software applications that use generative AI models to reason, plan,...

This blog explores how AWS Bedrock empowers founders, investors, and architects to build AI-powered products quickly and securely, without the burden of managing infrastructure. It also shares practical architecture patterns and security best practices to protect data, ensure compliance, and create a competitive moat.

    Amazon Bedrock AgentCore Runtime, Browser, and Code Interpreter add support for VPC, AWS PrivateLink, CloudFormation, and tagging 0 views Eyal Estrin unread,    to https://aws.amazon.com/about-aws/whats-new/2025/09/amazon-bedrock-agentcore-runtime-browser-code-interpreter-vpc-privatelink-cloudformation-tagging/ https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/agentcore-vpc.html https://docs.aws.amazon.com/AWSCloudFormation/latest/TemplateReference/AWS_BedrockAgentCore.html https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/tagging.html Eyal Estrin CISSP, CCSP, CISM, CISA, CDPSE, CCSK Blog: https://security-24-7.com | Books: https://amzn.to/42Xai9A | https://amzn.to/3Sggbtv Twitter: @eyalestrin | Bluesky: @eyalestrin.bsky.social Reply all Reply to author Forward

This new standardized interface allows developers to analyze, transform, and deploy production-ready AI agents directly in their preferred development environment. Get started with AgentCore faster and more easily with one-click installation that integrates Agentic IDEs like Kiro and AI coding assistants (Claude Code, Cursor, and Amazon Q Developer CLI). Use natural language to iteratively develop your agent, including transforming agent logic to work with the AgentCore SDK and deploying your agent into development accounts. The open-source MCP server is available globally via GitHub. To get started, https://github.com/awslabs/mcp?tab=readme-ov-file#available-mcp-servers-quick-installation for documentation and installation instructions. You can also learn more about this launch https://aws.amazon.com/blogs/machine-learning/accelerate-development-with-the-amazon-bedrock-agentcore-mcpserver/. For more information about Amazon Bedrock AgentCore and it’s services visit the https://aws.amazon.com/blogs/aws/introducing-amazon-bedrock-agentcore-securely-deploy-and-operate-ai-agents-at-any-scale/ and explore in-depth implementation details in the https://docs.aws.amazon.com/bedrock-agentcore/. For pricing information, visit the https://aws.amazon.com/bedrock/agentcore/pricing/.

AWS Weekly Roundup highlights include Kiro AI IDE, AWS Lambda remote debugging, Amazon ECS blue/green deployments, Amazon Bedrock AgentCore, and new AWS Free Tier credits for developers and cloud enthusiasts.

Introduction In the part 2 and part 3 of this series, we've already explained the...

Learn why customers choose AgentCore to build secure, reliable AI solutions using their choice of frameworks and models for production workloads.

技術的負債の蓄積しやすい AI エージェントの開発 ここで「技術的負債」とは、ベストプラクティスが日々更新されることで開発時点とリリース時点で実装の洗練度合いに無視できないギャップが生まれる状況を指します。ご存じの通り、生成 AI はこの意味での「技術的負債」が蓄積しやす...