Question

A financial services company deploys a customer-facing chatbot on Amazon Bedrock that answers questions using a company knowledge base. Compliance requires that the chatbot never fabricate information and only respond based on retrieved source documents. The team wants a managed capability that automatically detects and filters responses that are not factually grounded in the provided source material. Which approach best meets this requirement?

Accepted Answer

Enable the contextual grounding check in Guardrails for Amazon Bedrock to filter responses that are not grounded in the source content

Answer

Use Amazon SageMaker Clarify to generate feature attribution reports for each chatbot response

Answer

Lower the model temperature to 0 so the chatbot always produces the same deterministic answer

Answer

Increase the maximum token limit so the model can include more of the source documents in each answer