AINewsnow

AWS launches Web Search API for Bedrock AgentCore and boosts runtime capacity

This story is from 2026-11-10. It is preserved in the archive; the latest stories are on the live feed.

AWS introduced a Web Search API for Amazon Bedrock AgentCore, letting applications fetch ranked, cited web results with a single signed call and no gateway, while also upgrading AgentCore runtime compute, memory efficiency, and startup times.

Read the full story at AWS Machine Learning Blog ↗

Timeline · 6 reports

  1. 2026-11-13 22:02 · AWS Machine Learning Blog
    Architecture patterns for fast session startup on Amazon Bedrock AgentCore runtime
  2. 2026-11-12 21:47 · AWS Machine Learning Blog
    How Natera designed an agentic AI system for lab ops with Amazon Bedrock AgentCore
  3. 2026-11-12 12:38 · InfoWorld AI
    AWS boosts Bedrock AgentCore runtime compute capacity to speed up AI agent development
  4. 2026-11-11 23:28 · Unite.AI
    AWS Adds Direct Web Search API for Custom Agents and Data Pipelines
  5. 2026-11-11 23:13 · AWS Machine Learning Blog
    Introducing the Web Search API on Amazon Bedrock AgentCore
  6. 2026-11-10 23:34 · AWS Machine Learning Blog
    Build a daily dependency watcher with LangGraph and Amazon Bedrock AgentCore web search

More stories

  1. AWS expands Bedrock AgentCore with Web Search API and upgraded runtime — AWS Machine Learning Blog
  2. AWS expands Amazon Bedrock Managed Knowledge Base tooling for agents and migration — AWS Machine Learning Blog
  3. AWS adds silent data corruption detection and data capture tooling to SageMaker HyperPod — AWS Machine Learning Blog
  4. Amazon building 'World Product Graph' to own global product data and counter AI shopping agents — Economic Times Tech
  5. Meta infrastructure chief Santosh Janardhan to step down in early 2027 — DigiTimes Asia
  6. AWS adds usage-based pricing for SageMaker AI bidirectional streaming — AWS Machine Learning Blog
  7. Anthropic's bankers weigh raising IPO valuation to $1.5 trillion — Bloomberg AI
  8. Amazon reportedly plans to gather data on nearly every product sold, including by crawling rivals' sites — Techmeme

Get the daily brief of stories like this at 6:30 every morning →