QuestionQ69

VerifiedAI Safety, Security, and Governance

A financial technology company uses Amazon Bedrock to develop an assessment system for its customer-service AI assistant. The AI assistant must give financial recommendations that are factually correct, compliant with financial regulations, and appropriate in conversation. The company must combine automated quality assessments at scale with targeted human review of critical interactions.

Which solution will satisfy these requirements?

Explanation

Amazon Bedrock model evaluation jobs can use an LLM as a judge to score generated responses using selected or custom quality metrics, enabling automated evaluation at scale. Amazon Bedrock Guardrails can apply configurable policies to model inputs and outputs, including controls relevant to financial applications. Amazon A2I custom task types support application-defined conditions for routing selected interactions to human reviewers, which enables targeted review of critical cases. Evaluate model performance using another LLM as a judge, Detect and filter harmful content by using Amazon Bedrock Guardrails, Use Amazon Augmented AI with Custom Task Types

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!