{"version":1,"type":"story","url":"https://digestai.news/story/aws-builds-agentic-retrieval-on-managed-bedrock-knowledge-base-with-cd","json":"https://digestai.news/story/aws-builds-agentic-retrieval-on-managed-bedrock-knowledge-base-with-cd.json","markdown":"https://digestai.news/story/aws-builds-agentic-retrieval-on-managed-bedrock-knowledge-base-with-cd.md","slug":"aws-builds-agentic-retrieval-on-managed-bedrock-knowledge-base-with-cd","headline":"AWS builds agentic retrieval on managed Bedrock knowledge base with CDK","summary":"AWS explains how to construct an enterprise‑level agentic retrieval system using its Managed Bedrock Knowledge Base and the AWS Cloud Development Kit (CDK). The post builds on a 2024 guide that used a single‑shot RAG pipeline with Amazon S3, OpenSearch Serverless, and custom CDK stacks. In the updated version, Bedrock now offers a fully managed knowledge base that owns ingestion, storage, indexing, and retrieval, eliminating the need for an OpenSearch Serverless collection and its associated compute units.\n\nThe new architecture introduces the AgenticRetrieveStream API, which performs multi‑turn planning, iterative retrieval, and grounded, cited answers. A reasoning agent decides whether to retrieve, which knowledge base to consult, and whether to loop for more context. The CDK application provisions four stacks, automatically wiring seven observability layers into Amazon CloudWatch and AWS X‑Ray, and includes two evaluation dashboards.\n\nThe guide shows how to ingest two small corpora—synthetic financial data and a public weather report—into separate managed knowledge bases, then route queries through an AgentCore Runtime, Gateway, and the AgenticRetrieveStream tool. The result is a fully instrumented, agentic retrieval pipeline that can be deployed with a single CDK command.","keyPoints":["managed bedrock knowledge base removes need for opensearch serverless collection","agenticretrievestream api enables multi‑turn retrieval and cited answers","cdk app provisions four stacks and seven observability layers automatically"],"whyItMatters":"Enterprise users can now deploy agentic retrieval without managing vector stores, gaining richer, cited answers and built‑in observability. The CDK automation reduces operational complexity and speeds time‑to‑value for production systems.","category":{"slug":"enterprise","name":"Enterprise & Industry","url":"https://digestai.news/category/enterprise"},"entities":{"companies":["Amazon Bedrock","AWS","Amazon S3","Amazon OpenSearch Serverless","Amazon CloudWatch","AWS X-Ray"],"models":[],"people":[]},"firstPublishedAt":"2026-10-26T17:15:14Z","updatedAt":"2026-10-26T17:15:14Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"AWS Machine Learning Blog","title":"Build agentic retrieval on a Managed Amazon Bedrock Knowledge Base with CDK","url":"https://aws.amazon.com/blogs/machine-learning/build-agentic-retrieval-on-a-managed-amazon-bedrock-knowledge-base-with-cdk","publishedAt":"2026-10-26T17:15:14Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":{"title":"Amazon Bedrock Powers Enterprise Automation","url":"https://digestai.news/thread/cornerstone-ondemand-cuts-database-diagnosis-time-by-78-with-amazon-bedrock","storyCount":3},"cite":{"text":"Digest AI, \"AWS builds agentic retrieval on managed Bedrock knowledge base with CDK\", 26 October 2026, https://digestai.news/story/aws-builds-agentic-retrieval-on-managed-bedrock-knowledge-base-with-cd","publisher":"Digest AI","title":"AWS builds agentic retrieval on managed Bedrock knowledge base with CDK","datePublished":"2026-10-26T17:15:14Z","url":"https://digestai.news/story/aws-builds-agentic-retrieval-on-managed-bedrock-knowledge-base-with-cd"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}