Anthropic Ships Sonnet 5 With Agentic Safety and Pricing Details
1 July 20265 min read
Enterprise Technology
AWS Makes Enterprise Knowledge Retrieval a Managed Bedrock Capability
AWS introduced Amazon Bedrock Managed Knowledge Base at Summit New York, packaging retrieval, parsing, storage, permissions and agent integration into a managed service for enterprise AI applications.
Illustrative image. Cedar S. Insights uses editorial stock photography; images do not depict specific events described in articles.
AWS announced Amazon Bedrock Managed Knowledge Base on 17 June as part of its AWS Summit New York announcements, positioning it as a managed way to build enterprise-grade generative AI applications using proprietary data.
The service abstracts retrieval-augmented generation infrastructure that teams often assemble themselves, including connectors, parsing, vector storage, retrieval orchestration, embeddings, re-ranking and foundation-model selection.
AWS says the service integrates with Amazon Bedrock AgentCore Gateway as a pre-built target type, can auto-generate role-based permissions, and reports observability and evaluation metrics through AgentCore Observability.
AWS says Managed Knowledge Base is available now in US East, US West, Sydney, Tokyo, Dublin, Frankfurt, London and AWS GovCloud (US-West), with pricing based on indexed data storage and retrieval use.
Sourcing note: Availability, feature scope and pricing model are AWS statements. Claims about faster or more accurate applications are product claims and should be tested against each enterprise dataset, access-control model and latency requirement.
Why It Matters
Enterprise AI agents depend on reliable access to governed internal knowledge. By turning RAG plumbing into a managed Bedrock primitive, AWS is competing on the operational layer around models: permissions, connectors, observability, cost controls and deployment speed.
Primary Sources
Our sourcing: Cedar S. Insights provides source-led editorial analysis. Reported company, institutional and regulatory claims are attributed to their original sources unless stated otherwise.
Corrections: If a material factual error is identified, Cedar S. Insights will update the relevant article and preserve the distinction between the corrected statement and supporting evidence.
Topics
AWSAmazon BedrockEnterprise AIRAGAgentCore