A company is building an AI advisory application by using Amazon Bedrock. The application will provide recommendations to customers. The company needs the application to explain its reasoning…

Question

Options

• AUse Amazon Bedrock Knowledge Bases with source attribution enabled. Use the Anthropic
• BUse Amazon Bedrock with Anthropic Claude models and extended thinking. Configure a 4,000-
• CConfigure Amazon SageMaker AI with a custom Anthropic Claude model. Use the model's
• DUse Amazon Bedrock with Anthropic Claude models and chain-of-thought reasoning. Configure

• A
  84% (48)
• B
  2% (1)
• C
  5% (3)
• D
  9% (5)

Explanation

Option A is the best solution because it natively delivers retrieval grounding, source attribution, and low operational overhead through Amazon Bedrock Knowledge Bases. The key requirements are: retrieve from company data sources, cite sources, link claims to source documents, and keep latency under 3 seconds. Knowledge Bases are a managed RAG capability that handles document ingestion, chunking, embeddings, retrieval, and assembly of context for model generation. This eliminates the need to build and maintain custom retrieval infrastructure. Source attribution is crucial: the application must "link data claims to source documents." When source attribution is enabled, the RAG pipeline can return references to the underlying documents and segments used for generation. This enables traceable citations that can be surfaced to end users and used for internal auditing. Using the Anthropic Claude Messages API (or equivalent conversational interface) with RAG allows the application to generate recommendations grounded in retrieved context while keeping responses conversational. Setting relevance thresholds helps reduce noisy retrieval, which supports both accuracy and latency targets by limiting the context passed to the model. Storing reasoning and citations in Amazon S3 supports audit and retention needs with minimal operational burden. While the prompt may request step-by-step reasoning, AWS best practice is to produce user-facing explanations that are faithful and attributable without exposing internal reasoning traces unnecessarily. With source-grounded outputs, the system can provide concise rationale tied to citations while maintaining fast response times.

No community discussion yet for this question.