Query claims in natural language with Amazon Bedrock Knowledge Bases

What happened

Query claims in natural language with Amazon Bedrock Knowledge Bases, AWS Machine Learning Blog announced. 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 (the interface one piece of software uses to talk to another), multi-turn follow-ups, metadata filters, and contextual grounding guardrails.

Claim answers are scattered across adjuster diary entries, repair estimates, police reports, payment ledgers, and scanned attachments rather than one searchable field. A policyholder might ask whether a claim was approved, while an adjuster might need every open auto claim over $10,000 from last month.

Both tasks require finding and combining evidence quickly and accurately. Retrieval Augmented Generation (RAG (letting a model look information up instead of relying on memory)) operates with retrieved documents to ground model responses.

Key facts

• Retrieval Augmented Generation (RAG) — uses: retrieved documents to ground model responses