AITOPAI热报
ProductsOfficial

Amazon Bedrock AgentCore 推出 Web Search API，一次签名调用即可联网搜索

Introducing the Web Search API on Amazon Bedrock AgentCore

Primary sourceAWS Machine Learning Blog@Shubham Divekar
Blog/Media
Read the original
Why we picked it

AWS 给 Bedrock AgentCore 加了个 Web Search API，一行签名调用就能让程序或智能体搜网页，不用自己搭网关。做 Agent 或数据管道的开发者可以直接在 SDK 和 CLI 里接上用，省掉不少基建活。

AWS 宣布在 Amazon Bedrock AgentCore 上推出 Web Search API，代码只需一次签名的 API 调用即可搜索网页，无需创建网关或任何额外资源。

Image · AWS Machine Learning Blog
Body

开发者可以通过 AWS SDK 或 AWS CLI 直接调用，把它嵌入应用程序、Agent 循环和数据管道中。由于不用预先搭建网关和基础设施，接入成本和维护负担明显降低。

对开发智能体的团队来说，这是一个即插即用的联网能力选项，可在 AgentCore 生态内与现有工具链组合使用。

Original · AWS Machine Learning Blog

Introducing the Web Search API on Amazon Bedrock AgentCore

Today we're announcing the Web Search API on Amazon Bedrock AgentCore: your own code can search the web with a single signed API call, with no gateway and no resources to create. Call it from the AWS SDKs or the AWS CLI and use it in applications, agent loops, and data pipelines.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Amazon Bedrock, AgentCore, Web Search API, AWS.

Primary source verification: published directly by AWS Machine Learning Blog with first-party authority.

#Amazon Bedrock#AgentCore#Web Search API#AWS#智能体

Keep reading

Recent stories with the same tag or section
How-toBuildersOfficialSelected09:39
Amazon Bedrock and Spring AI enable autonomous agents in Java

The notable shift is that Spring AI plus AgentCore gives Java shops a first-class route to autonomous agents, closing the gap with Python frameworks like LangChain. Enterprise architects and backend engineers maintaining JVM-based systems can adopt this stack instead of standing up separate Python services. Teams deploying in AWS regions serving ASEAN can host agents on local Bedrock infrastructure to keep data and latency close to users.

#Amazon Bedrock#Spring AI#agents#Java
Primary sourceAWS Machine Learning Blog@Viquar KhanSource
ProductsBuildersOfficial06:43
Chinese contentAmazon Bedrock 与 AgentCore 10 月更新汇总

这份 AWS 官方月度汇总把 10 月 Bedrock、AgentCore 和 Strands 的新功能整理在了一起。智能体稳定性、模型按任务选型和成本拆账，这三件事都是企业开发者在落地时最头疼的。正在用 Bedrock 搭智能体的团队可以直接对照清单排优先级。

#Amazon Bedrock#AgentCore#Strands#AWS
Primary sourceAWS Machine Learning Blog@Tymofii KryvtsunSource
ProductsBuildersOfficial05:03
Chinese contentDXC Technology 基于 Amazon Bedrock 搭建多模型 AI 底座

DXC 在 70 国做 IT 托管服务，把 AI 架构拆成 Bedrock 多模型底座加自建治理层，agent 的编排、权限、审计全走一套 harness。做企业级 agent 落地的开发者值得看它的分层设计，尤其受监管行业的团队。

#Amazon Bedrock#DXC Technology#AI agent#企业架构
Primary sourceAWS Machine Learning Blog@Asif FouziSource
ModelsBuildersOfficial09:29
Chinese contentMoonshot AI 的 Kimi K3.1 Pro 上架 Amazon Bedrock

Moonshot 的 Kimi K3.1 Pro 进了 Amazon Bedrock，AWS 用户直接调 API 就能用，支持 OpenAI 兼容接口，迁移代码几乎不用改。文中还教了怎么开 prompt caching 省钱、怎么在 OpenCode 里当编程助手。做多云部署或想比较中美模型成本的工程师可以看看。

#Kimi#Moonshot AI#Amazon Bedrock#提示词工程
Event
Primary sourceAWS Machine Learning Blog@Aris TsakpinisSource
How-toBuildersOfficial07:50
Chinese content用 LangGraph 和 Amazon Bedrock AgentCore Web Search 搭建每日依赖监控

AWS 出的实战教程，教你用 LangGraph 加 Bedrock AgentCore 的 Web Search API 做一个每日依赖监控智能体。亮点是规则写代码里、搜索结果带引用可核验，还能并行查多个包生态。常维护开源依赖的工程师可以直接照抄这套工作流。

#LangGraph#Amazon Bedrock#AgentCore#智能体
Primary sourceAWS Machine Learning Blog@Sundar RaghavanSource
PapersBuildersOfficial07:00
Chinese contentAgentCore Evaluations 评测手册：内置、DeepEval 与 AutoEval 三种方案

AWS 这篇手册把智能体评测拆成了任务完成、跑题、数据泄露这些具体维度，教你怎么在 AgentCore 上选对评测器。写智能体的开发者可以直接照着搭回归测试，不用再靠肉眼验收。

#Amazon Bedrock#AgentCore#DeepEval#智能体
Primary sourceAWS Machine Learning Blog@Bharathi SrinivasanSource