产品
别名：AgentCore、Bedrock AgentCore
Bedrock 的浏览器工具组件，用于在真实环境中动态验证 UI 行为。
已跟踪 14 条高相关材料
最近变化
2026-06-02 · Baz 通过 Amazon Bedrock AgentCore 实现 UI 动态验证，覆盖静态代码检查无法触及的视觉与行为一致性。
为什么值得关注
Amazon Bedrock AgentCore 被反复提及时，通常意味着它正在影响产品路线、开发者工作流或 AI 产业判断。这个页面把分散材料合并成一个可持续更新的观察入口。
Secure AI agents with Policy and Lambda interceptors in Amazon Bedrock AgentCore gateway
AWS Machine Learning Blog · 9 分
Amazon Bedrock AgentCore Gateway 通过 Cedar 策略与 Lambda 拦截器实现 AI 代理的动态与静态安全控制，支持企业级权限治理和地理围栏访问控制。
Powering agentic AI sales strategy with Amazon Bedrock AgentCore
AWS Machine Learning Blog · 9 分
AWS 使用 Amazon Bedrock AgentCore 构建了一个名为 Field Advisor 的智能销售助手，解决了代理无编排的问题，提高了销售团队的工作效率。
How Baz improved its AI Agent Code Review accuracy using Amazon Bedrock AgentCore
AWS Machine Learning Blog · 8.5 分
Baz 使用 Amazon Bedrock AgentCore 构建 AI 代码审查代理，实现从设计到行为的端到端自动化验证，准确率提升显著。
已收录 14 条与 Amazon Bedrock AgentCore 相关的内容，按评分排序。
Amazon Bedrock AgentCore Gateway secures AI agents via Cedar policies for static control and Lambda interceptors for dynamic validation, enabling enterprise governance and geo-fenced access.
入选理由：使用 Cedar 策略可对 MCP 工具执行确定性访问控制，自动记录审计日志，适用于角色/资源/动作三元组授权。
This article discusses how AWS used Amazon Bedrock AgentCore to build Field Advisor, an intelligent sales assistant, to address the issue of unorchestrated agents and improve sales efficiency.
入选理由：Field Advisor 通过集中管理多个代理，减少了认知负担，使销售代表能够专注于客户互动。
Baz built an AI agent using Amazon Bedrock AgentCore to automate end-to-end validation from design to behavior, significantly improving review accuracy.
入选理由：Baz 通过 Amazon Bedrock AgentCore 实现 UI 动态验证，覆盖静态代码检查无法触及的视觉与行为一致性。
Amazon Bedrock AgentCore 提供版本化数据集管理，确保代理测试的稳定性和可重复性，提升开发与 CI/CD 流程中的评估质量。
入选理由：Amazon Bedrock AgentCore 支持预定义场景和用户模拟场景两种测试模式。
AWS uses Amazon Bedrock AgentCore to build an intelligent conversational assistant called NarrateAI, which automates narrative generation and enables real-time interactions to achieve scalable business intelligence, addressing limitations of traditional BI such as time-consuming preparation, data fragmentation, and limited access.
入选理由：NarrateAI 通过批处理和实时交互的两层架构，实现了大规模业务智能。
Amazon Bedrock AgentCore payments introduces a managed service for AI agents to handle microtransactions efficiently, addressing complex issues like billing and security.
入选理由：Amazon Bedrock AgentCore payments enables AI agents to perform microtransactions with ease using a simple API.
Amazon Bedrock AgentCore solves long-document analysis context window limits via Recursive Language Models (RLM), enabling unlimited document processing through iterative sub-LLM calls and code interpreter workflows.
入选理由：RLM架构通过将文档视为环境，使用根LLM编写代码与之交互，并通过子LLM处理特定段落，突破上下文窗口限制。
Amazon Bedrock AgentCore solves core challenges of tenant isolation, cost, and observability in multi-tenant agent applications through session-isolated microVM architecture and tiered model strategies, providing built-in tenant identity management and data isolation.
入选理由：AgentCore的微VM架构实现会话级隔离，每个租户会话拥有独立文件系统，降低数据泄漏风险，同时避免全虚拟机的资源开销
AI agents optimize radiology workflows by integrating radiologist specialization, workload, and fatigue factors, reducing 17.7-minute diagnostic delays and saving millions in costs.
入选理由：传统系统导致17.7分钟延迟和每年210万至420万美元的损失
AWS introduces Chrome enterprise policies to enhance AI agent security by restricting domains, disabling sensitive features, and trusting custom root CAs.
入选理由：支持 450+ 浏览器设置，可配置 URL 过滤和下载限制
This post demonstrates how to implement OAuth 2.0 Authorization Code Flow as an inbound authentication mechanism for MCP servers hosted on Amazon Bedrock AgentCore Gateway. By the end of this guide, you will have a production-ready setup where each AI assistant request is authenticated with a valid user identity token issued from your organization’s identity provider.
入选理由：使用 AgentCore Gateway 实现 MCP 服务的入站认证，支持 OAuth 2.0 授权码流程。
This article introduces how to build high-performance generative AI systems on AWS by combining NVIDIA NIM, Amazon Bedrock AgentCore, and Strands Agents.
入选理由：通过结合 NVIDIA NIM、Amazon Bedrock AgentCore 和 Strands Agents，可以在 AWS 上构建高性能的生成式 AI 系统。
AgentWatch is an active AWS resource monitoring solution that continuously observes and analyzes infrastructure, reducing the need for constant human intervention and improving DevOps team efficiency and proactive problem prevention.
入选理由：AgentWatch 每 15 分钟进行一次基础设施检查，汇总 CloudWatch 指标、日志和警报，并将 actionable 报告直接发送到 Slack。
AWS proposes three architectural patterns for voice agents—direct tool calling, agent-as-tool delegation, and session segmentation—built on Amazon Nova Sonic, Bedrock AgentCore, and Strands BidiAgent, achieving sub-500ms end-to-end latency while solving multi-agent coordination and real-time audio streaming challenges.
入选理由：AgentCore Gateway 支持 MCP 协议，让 Nova Sonic 直接调用工具，消除中间推理层以降低延迟
