ToolsThe story, in brief

Introducing Web Search on Amazon Bedrock for foundation model grounding

Amazon Bedrock now grounds LLM responses in live web data natively—no third-party APIs, no extra security reviews.

Illustration of a transparent lens revealing connected networks across layers of paper.
Exploring the next frontier of AI research.AI illustration by KeyNews
The KeyNews take

Why it matters

A built-in grounding tool reduces operational friction for enterprises deploying foundation models on AWS. Practitioners can now add real-time web context to model outputs without orchestrating external vendors or APIs.

The key facts

11 to know
  1. Web Search on Amazon Bedrock now generally available

  2. Server-side built-in tool for grounding model responses in current web knowledge

  3. No third-party vendors, external APIs, or additional security reviews required

  4. Native capability integrated into Amazon Bedrock platform

  5. Compatible with OpenAI Responses API

  6. Web Search on Amazon Bedrock now in general availability

  7. No third-party vendor onboarding required

  8. No external API orchestration needed

  9. Eliminates additional third-party vendor security reviews

  10. Native capability integrated into Bedrock platform

  11. Supports OpenAI Responses API integration

Go to the source

AWS Machine Learning Blogaws.amazon.com

Publisher excerpt: 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…
Read original report
Back to today's editionMore tools news

Keep reading

Related stories

More from Tools