AWS published two posts on building agentic retrieval with Managed Amazon Bedrock Knowledge Bases: one on observability for enterprise agentic retrieval using AWS CloudFormation, and one on multi-tenant agentic chat over enterprise data. Both target the step beyond single-source RAG, where an agent routes questions across knowledge bases and retrieves iteratively. The multi-tenant post emphasizes per-tenant document isolation enforced from verified identity rather than client-supplied values.
AWS published a technical how-to for building an insurance claims assistant on Amazon Bedrock Knowledge Bases, using agentic retrieval to answer natural-language questions over claim documents with citations. The guide combines S3-indexed claim files, metadata filtering, Guardrails grounding checks, and multi-turn conversation. A 40-question evaluation on synthetic data showed 90.5% retrieval recall and 81.2% citation recall.
AWS published a technical how-to for building an insurance claims assistant on Amazon Bedrock Knowledge Bases, using agentic retrieval to answer natural-language questions over claim documents with citations. The guide combines S3-indexed claim files, metadata filtering, Guardrails grounding checks, and multi-turn conversation. A 40-question evaluation on synthetic data showed 90.5% retrieval recall and 81.2% citation recall.
Amazon Bedrock Managed Knowledge Base is a new service that abstracts away the complexity of building enterprise-grade retrieval-augmented generation (RAG) pipelines for AI agents. It handles connectors, parsers, vector stores, knowledge graphs, and retrieval logic, enabling teams to ground agents on enterprise data without stitching together custom infrastructure.
Amazon Bedrock Managed Knowledge Base is a new service that abstracts away the complexity of building enterprise-grade retrieval-augmented generation (RAG) pipelines for AI agents. It handles connectors, parsers, vector stores, knowledge graphs, and retrieval logic, enabling teams to ground agents on enterprise data without stitching together custom infrastructure.
An AWS engineering post demonstrates agentic retrieval on Amazon Bedrock Managed Knowledge Bases via the langchain-aws package, contrasting it with standard single-shot Retrieve for multi-part RAG questions. A test question containing six intents was only partially covered by similarity search at five chunks, while the agentic planning loop decomposes the question into sub-queries and iterates until evidence is sufficient. It matters to practitioners choosing between cheaper single-shot retrieval and costlier agentic retrieval.
An AWS engineering post demonstrates agentic retrieval on Amazon Bedrock Managed Knowledge Bases via the langchain-aws package, contrasting it with standard single-shot Retrieve for multi-part RAG questions. A test question containing six intents was only partially covered by similarity search at five chunks, while the agentic planning loop decomposes the question into sub-queries and iterates until evidence is sufficient. It matters to practitioners choosing between cheaper single-shot retrieval and costlier agentic retrieval.
AWS describes how Amazon Quick and Amazon Bedrock Knowledge Bases enforce document-level permissions in enterprise RAG over sources like SharePoint, Google Drive, and Confluence. The system uses a hybrid two-stage design: pre-retrieval ACL filtering on a cached vector index, followed by real-time permission verification with the authoritative source at query time. This addresses stale or incorrectly replicated ACLs that could leak sensitive documents through AI answers.
AWS describes how Amazon Quick and Amazon Bedrock Knowledge Bases enforce document-level permissions in enterprise RAG over sources like SharePoint, Google Drive, and Confluence. The system uses a hybrid two-stage design: pre-retrieval ACL filtering on a cached vector index, followed by real-time permission verification with the authoritative source at query time. This addresses stale or incorrectly replicated ACLs that could leak sensitive documents through AI answers.
Qlik Answers lets employees ask questions of company data in natural language and get answers grounded in sources. It is built on Amazon Bedrock to address hallucination, verifiability, and deployment-in-regulated-environments concerns. It targets enterprises whose analysts spend hours searching documents and dashboards.
Qlik Answers lets employees ask questions of company data in natural language and get answers grounded in sources. It is built on Amazon Bedrock to address hallucination, verifiability, and deployment-in-regulated-environments concerns. It targets enterprises whose analysts spend hours searching documents and dashboards.