Connect Amazon Bedrock AgentCore to cross-account knowledge bases
Learn how Amazon Bedrock AgentCore agents in one account can generate answers from an Amazon Bedrock knowledge base backed by Amazon Redshift Serverless in another account, without copying source data. This post covers the architecture, security boundary, and two orchestration models: a code-based Strands agent and a declarative AgentCore harness.
Organizations often deploy AI agents using Amazon Bedrock AgentCore, a platform enabling development, connection, and optimization of agents at scale across any framework or model. When these agents need to access governed knowledge bases hosted in separate AWS accounts, cross-account separation can introduce integration challenges.
This post outlines how AgentCore agents in one account can retrieve answers from a knowledge base (using Amazon Bedrock Knowledge Bases) backed by Amazon Redshift Serverless in another account without transferring source data. The post covers architecture, security boundaries, request flow, and decision criteria for two generally available AgentCore orchestration models.
Linked GitHub sample provides deployment procedures and implementation details for both variants: a code-based Strands agent on AgentCore runtime and a declarative AgentCore harness, both capabilities of Amazon Bedrock AgentCore.
Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.