---
format: "aidr-story-markdown/v1"
id: "4a7054c6c35b5478ae973d976c82cd3af2188cbeef1f614b55b29d2c854f7386"
canonical_url: "https://aidr.today/4a7054c6?lang=en"
title: "Query claims in natural language with Amazon Bedrock Knowledge Bases"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-30T15:37:15.000Z"
category: "Agents"
topics: ["amazon","agent"]
source_urls: ["https://aws.amazon.com/blogs/machine-learning/query-claims-in-natural-language-with-amazon-bedrock-knowledge-bases/"]
summary: "This technical how-to builds a conversational claims assistant on Amazon Bedrock Knowledge Bases that answers natural-language questions with citations. It covers ingesting claim documents from Amazon S3, querying with the AgenticRetrieveStream API, multi-turn follow-ups, metadata filters, and contextual grounding guardrails."
---

# Query claims in natural language with Amazon Bedrock Knowledge Bases

> [Open the canonical story](<https://aidr.today/4a7054c6?lang=en>)

**Published:** 2026-09-30T15:37:15.000Z
**Category:** Agents
**Topics:** amazon, agent

## Summary

This technical how\-to builds a conversational claims assistant on Amazon Bedrock Knowledge Bases that answers natural\-language questions with citations\. It covers ingesting claim documents from Amazon S3, querying with the AgenticRetrieveStream API, multi\-turn follow\-ups, metadata filters, and contextual grounding guardrails\.

## Sources

- [Story source](<https://aws.amazon.com/blogs/machine-learning/query-claims-in-natural-language-with-amazon-bedrock-knowledge-bases/>)