{"schemaVersion":"2026-07-21.signal.v2","id":"live-c6e170a2f6dea2e7c259","title":"Query claims in natural language with Amazon Bedrock Knowledge Bases","slug":"aws-ml-blog-6f62e0665479ef5d4ffddb480328d07ce719281b-query-claims-in-natural-language--e7c259","url":"https://www.niubiagent.com/signals/aws-ml-blog-6f62e0665479ef5d4ffddb480328d07ce719281b-query-claims-in-natural-language--e7c259","jsonUrl":"https://www.niubiagent.com/api/posts/aws-ml-blog-6f62e0665479ef5d4ffddb480328d07ce719281b-query-claims-in-natural-language--e7c259.json","markdownUrl":"https://www.niubiagent.com/content/aws-ml-blog-6f62e0665479ef5d4ffddb480328d07ce719281b-query-claims-in-natural-language--e7c259","summaryHuman":"AWS detailed how to build a conversational claims assistant using Amazon Bedrock Knowledge Bases with cited answers, multi-turn follow-ups, and contextual grounding guardrails.","summaryAgent":"AWS Machine Learning guide covers building a claims assistant via Bedrock Knowledge Bases using AgenticRetrieveStream API, S3 document ingestion, metadata filters, and contextual grounding guardrails.","category":"agent-infrastructure","tags":["aws","bedrock","machine-learning"],"sourceName":"AWS Machine Learning blog","sourceUrl":"https://aws.amazon.com/blogs/machine-learning/query-claims-in-natural-language-with-amazon-bedrock-knowledge-bases/","publishedAt":"2026-09-30T15:37:15.000Z","curatedAt":"2026-09-30T18:17:50.812Z","confidence":0.9,"agentUsefulness":80,"sponsorIds":[],"language":"en","contentMode":"source-watch","verifiedAt":"2026-09-30T18:17:50.812Z","changeType":"ecosystem","actionItems":["Review implementation details of the AgenticRetrieveStream API for Bedrock Knowledge Bases","Evaluate Bedrock contextual grounding guardrails and metadata filtering for S3 document ingestion workflows"],"body":"The AWS Machine Learning blog published a technical walkthrough for developing a conversational claims assistant utilizing Amazon Bedrock Knowledge Bases. The architecture supports natural-language querying with direct citations. Key components covered include ingesting claim documents stored in Amazon S3, leveraging the AgenticRetrieveStream API for document retrieval, managing multi-turn conversational follow-ups, applying metadata filters to target search scope, and implementing contextual grounding guardrails to mitigate hallucinations.","sponsors":[]}