Build agentic retrieval on a Managed Amazon Bedrock Knowledge Base with CDK
Build enterprise agentic retrieval on a Managed Amazon Bedrock Knowledge Base with the AWS CDK: an agent that routes across two knowledge bases, retrieves through the AgentCore Gateway, and returns grounded, cited answers, with seven layers of observability and both on-demand and continuous evaluation, all deployed as a single CDK application.
First seen by Oriel on .
AI summary
This AWS post presents a Python CDK application for enterprise agentic retrieval across two Managed Amazon Bedrock Knowledge Bases, using AgentCore, cited answers, and provisioned observability and evaluation.
- The reasoning agent routes questions between financial and weather knowledge bases exposed as MCP tools through an AgentCore Gateway.
- AgenticRetrieveStream decomposes questions, retrieves iteratively, synthesizes grounded citations, and allows the agent to loop when returned context is insufficient.
- Managed Knowledge Bases handle ingestion, storage, indexing, embedding, reranking, and retrieval, eliminating customer-managed OpenSearch Serverless infrastructure.
- Four CDK stacks provision knowledge bases, Gateway targets, an instrumented AgentCore Runtime agent, and CloudWatch dashboards with cross-stack dependencies derived automatically.
- The solution provides seven telemetry layers and on-demand or continuous evaluation, but dashboards remain empty until traffic generates observations and scores.
#amazon bedrock #agentcore #aws cdk #observability
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| AWS Machine Learning Blog | 5e1286dfb4f90dcf4a044cccd75a633bcf5c972a | https://aws.amazon.com/blogs/machine-learning/build-agentic-retrieval-on-a-managed-amazon-bedrock-knowledge-base-with-cdk/ Read discussion |