← Back
AWS ML Blog

Introducing the Web Search API on Amazon Bedrock AgentCore

•15 min read•
#bedrock#agents
Level:Intermediate
For:AI Engineers
✦TL;DR

Amazon Bedrock AgentCore now offers a standalone Web Search API called **InvokeWebSearch**, letting developers retrieve ranked web results—including text extracts, titles, URLs, and publication times—with a single SDK or CLI call. The request is signed with AWS Signature Version 4 using existing IAM credentials, requiring no prior resource creation. This low‑level integration complements the existing AgentCore Gateway, enabling custom orchestration frameworks, non‑agent workloads, and tighter control over retries and caching. Engineers can now add real‑time web grounding to applications, dashboards, or pipelines without deploying the full gateway stack.

⚡ Key Takeaways

  • InvokeWebSearch operation returns ranked results with text extract, page title, URL, and publication time.
  • Uses the same bedrock‑agentcore data‑plane endpoint as AgentCore Browser, eliminating the need for a separate gateway resource.
  • Requests are signed with AWS Signature Version 4 (SigV4) using standard IAM credentials—no API keys required.
  • Can be called from AWS SDKs or the AWS CLI, optionally routing through a VPC interface endpoint.
  • Suitable for custom agent loops, LangChain/LlamaIndex integrations, or any non‑agent application needing web grounding.
💡 Why It Matters

By exposing web search as a direct API, engineers can enrich real‑time data pipelines and AI applications with up‑to‑date information while retaining full control over request handling and without the overhead of deploying AgentCore Gateway infrastructure.

✅ Practical Steps

  1. Use the AWS SDK or AWS CLI to call the **InvokeWebSearch** operation, providing your query parameters.
  2. Ensure your call is signed with SigV4 by using the IAM credentials already configured for your AWS environment.
  3. (Optional) Route the request through a VPC interface endpoint if operating within a private network.

Want the full story? Read the original article.

Read on AWS ML Blog ↗

More like this

Introducing Gemini 4 Neon

Google DeepMind•#llm

DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency

Hugging Face Blog•#llm

Mathematical proof, powered by AI. And no hallucinations!

Amazon Science•#agents

AI’s GPU focus meets a CPU reality check at Dell and AMD

SiliconANGLE AI•#agents

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING