AWS Machine Learning Blog

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：The Amazon SageMaker AI Spaces add-on for Amazon EKS runs managed JupyterLab and Code Editor environments on the cluster your ML team already operates. This post shows how to install and configure the add-on, connect from the browser and from VS Code over SSH-over-SSM, and move your team to OpenID Connect sign-in with Amazon Cognito.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：nOps rebuilt its Clara FinOps AI agent on Amazon Bedrock AgentCore, replacing a self-managed Amazon EKS stack running LangChain and LangGraph. The move cut time-to-production by 75% (from 10-12 months to 4 months), improved response quality, and reduced operational overhead while keeping analytics governed through Databricks Lakehouse Metric Views.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：In this post, you learn how Cohere Health built a multi-tenant agentic architecture on AgentCore using AgentCore Runtime’s secure MicroVM isolation, unified tool access through AgentCore Gateway, AgentCore Memory, and the Agent Skills open standard to rapidly scale policy digitization capabilities, while preserving transparency, version control, and human oversight.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：TReNDS, a research center at Georgia State University, built an agentic AI pipeline on Amazon Bedrock and the open-source Strands Agents SDK that automatically investigates production errors in real time, reducing root-cause analysis from 15 to 30 minutes of manual work to under 60 seconds.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：The AWS Generative AI Innovation Center built an automated system that uses constraint programming and custom tree search to determine, with mathematical certainty, when and how an NHL team clinches a playoff spot. The approach was validated against four full NHL seasons of officially published results.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Temporal policies in Amazon Bedrock AgentCore let you define stateful rules that evaluate authorization based on an agent's session history. Learn how to enforce workflow sequencing, prevent data fabrication, cap financial exposure, and require human approval for high-value actions.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Learn how to configure rate limits on Amazon Bedrock AgentCore gateway to enforce per-user and per-target traffic controls. Define request, token, and connection limits scoped by JWT claims or IAM identity to protect downstream models, tools, and agents from traffic spikes.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Learn about new capabilities in Amazon Bedrock AgentCore: temporal policies powered by Dogwood, a new open source policy language for AI agents, and rate limiting on the gateway. These features give you deterministic control over sequences of agent actions and cost ceilings that hold regardless of agent behavior.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：As engineering teams adopt coding agents like Codex, leaders need visibility into adoption, consumption, and reliability. This post shows how to route Codex OpenTelemetry metrics through a local collector to Amazon CloudWatch for an AWS native view of usage by user, team, and cost center.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：A regulated customer needed all Claude Code inference processed in a single AWS Region (London), not just in-geography. This post shows two ways to pin Claude Code on Amazon Bedrock to one Region: an application inference profile or the Mantle endpoint, paired with an IAM Region condition, plus how to verify compliance in AWS CloudTrail.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Learn how to run the full Amazon Bedrock Automated Reasoning policy lifecycle from your coding agent. A suite of open source Agent Skills builds, reviews, tests, debugs, deploys, and validates a custom policy end to end, turning a specialized console task into a repeatable engineering workflow.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：PDI Technologies built PDI Brew, an agentic platform on AWS where non-technical employees describe a tool in plain English and receive a fully provisioned, multi-tenant web application in seconds. See how a pluggable planner and an AWS Lambda provisioning agent turn plain-English intent into governed, multi-tenant apps backed by Amazon Bedrock.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：The Amazon SageMaker Python SDK v3 now exposes generative AI inference recommendations in Amazon SageMaker AI directly in your notebook. Benchmark an endpoint, generate data-driven deployment recommendations, and deploy the recommended configuration without leaving your notebook workflow.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Learn how LendingTree built a production multi-agent mortgage assistant on Amazon Bedrock. Three coordinated agents use LangGraph, the Model Context Protocol, and Amazon Nova models with built-in guardrails to deliver 24/7 personalized mortgage guidance while meeting strict financial-services compliance.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：In this post, we'll explore how Mobileye deployed an AI support agentic solution on Amazon Bedrock AgentCore - from the support bottleneck that sparked the idea, through the proof of concept that validated it, to the hybrid architecture that bridges on-premises systems with AWS cloud services. This approach is relevant for enterprises struggling to scale AI Agents while maintaining enterprise grade governance and security standards.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：AI agents on Amazon Bedrock AgentCore run in the cloud, but users' tools and files live on their laptops. Learn how to build a secure MCP bridge that lets a cloud-hosted agent call local MCP servers by tunneling signed messages over the existing WebSocket connection through a browser extension and Chrome native messaging, with no open ports or VPN required.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Amazon Bedrock AgentCore harness is now generally available. Learn how to add it as an agent step in n8n workflows using a new open-source community node, and build agents with persistent memory, real tools, code execution, and VPC isolation — all from the n8n editor with no infrastructure or agent code.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Today, we are introducing the general availability of Web Search on Amazon Bedrock. It is a server-side built-in tool that grounds model responses in current web knowledge. With Web Search, grounding becomes a native capability of Amazon Bedrock, with no third-party vendors to onboard, no external APIs to orchestrate, and no additional third party vendor security reviews to conduct. In this post, we walk through what Web Search on Amazon Bedrock is, why it matters, how to enable it using the OpenAI Responses API, and how to get started with the tool.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Extracting insights from dozens of websites by hand quickly becomes overwhelming. This post shows how to build an automated web insight extraction solution with Amazon Bedrock AgentCore Browser, Amazon Bedrock, Amazon OpenSearch Serverless, and AWS Lambda that monitors RSS feeds, renders pages reliably, and makes AI-extracted insights searchable.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Formula 1® partnered with AWS to build the Data Accelerator, using agentic AI on Amazon Bedrock AgentCore to transform its MarTech data platform. Learn how F1 cut data source onboarding from up to 8 weeks to about 40 minutes, automated schema evolution, and gained end-to-end observability across its fan-engagement data estate.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Amazon Bedrock now supports automatic Automated Reasoning policy refinement. The refinement engine diagnoses failing tests and proposes formal-logic fixes for rule issues and language issues, and you approve every change before it takes effect. This post walks through both refinement modes with complete API and console workflows.

Amazon Quick 宣佈推出 Agentic Catalog Experience（預覽版），這是一種 AI 驅動的工作流，幫助數據管理員通過自然語言發現上游目錄資產，並自動創建數據集和主題，同時繼承上游語義。該體驗旨在消除數據發現和語義重建的最後一公里瓶頸，將數據準備時間從數週縮短到分鐘，首批支持 AWS Glue Data Catalog 和 Databricks Unity Catalog。

本文介紹了在AWS上部署Moonshot AI的2.8萬億參數開源MoE模型Kimi K3的兩種方法：使用Amazon SageMaker HyperPod或Amazon EKS。需要p6-b300實例（8塊B300 GPU）和預留容量，通過vLLM提供OpenAI兼容的推理端點。

本文展示了Yahoo如何利用Amazon Bedrock與生成式AI增強其搜索重定向（SRT）功能，顯著提升關鍵詞擴展的語義相關性和受眾覆蓋範圍。

瞭解如何使用 Amazon Quick 為 Amazon SageMaker AI 端點構建推理元監控系統。這一治理層位於生產機器學習推理管道之上，持續跟蹤預測和數據質量、檢測漂移、整合延遲的真實值，並提供自動化的性能儀表板。

OpenAI GPT-5.6 Sol、Terra 和 Luna 模型已在 Amazon Bedrock 上正式可用，同時引入了顯式提示緩存功能，可精確控制提示的緩存和重用部分。本文介紹瞭如何開始使用、設置顯式緩存以及遷移現有 GPT 工作負載以降低推理成本。

Amazon Bedrock高級提示優化功能可同時針對最多5個模型優化提示，並比較原始與優化後的性能（質量、延遲和成本）。該功能旨在將數天到數週的手動迭代工作縮短為幾分鐘的引導式流程，支持模型遷移和當前模型改進。

Amazon Bedrock AgentCore Identity 現在支持私鑰 JWT 客户端身份驗證，使代理能夠使用簽名的 JWT 而不是共享密鑰向身份提供商進行身份驗證。私鑰安全地存儲在 AWS KMS 中，公鑰註冊到身份提供商。本文解釋了工作流程、支持的授權流程（M2M、OBO、用户委託），並提供了詳細的配置步驟，包括創建 KMS 簽名密鑰、註冊公鑰以及設置憑證提供程序。還展示了用於審計的 CloudTrail 事件示例。

本文介紹瞭如何通過Amazon Bedrock AgentCore實現自主、跨系統的商業智能，無需自定義代碼。利用預構建的MCP服務器連接器、細粒度訪問控制和持久內存，企業可以用自然語言查詢多個數據源，同時自動執行基於角色的邊界。

瞭解如何使用 Amazon Quick 構建無代碼的客户留存管道，通過通話記錄和 CSAT 數據識別有流失風險的客户，利用自定義 MCP Action 按留存優先級評分，並生成個性化留存信函，將響應時間從幾天縮短到幾分鐘。