A company has a customer service application that uses Amazon Bedrock to generate personalized responses...

Option B is the correct solution because Amazon Bedrock evaluation jobs are purpose-built to assess prompt effectiveness, model behavior, and response quality in a repeatable and automated manner. Evaluation jobs support both quantitative metrics and LLM-based judgment, making them suitable for detecting subtle response quality regressions that simple sentiment or latency metrics cannot capture.

By using custom prompt datasets, the company can consistently test multiple prompt templates and model configurations against the same inputs. This enables accurate comparison across updates and eliminates variability introduced by live traffic sampling. Amazon Bedrock evaluation jobs also support structured scoring outputs, which can be used to enforce objective quality thresholds.

Integrating evaluation jobs directly into AWS CodePipeline ensures that quality checks are automatically triggered whenever prompt templates or configurations change. This creates a gated deployment workflow in which only configurations that meet or exceed the predefined quality threshold are promoted. This directly satisfies the requirement to prevent low-quality configurations from being deployed.

Human reviewers can be incorporated by reviewing evaluation results and scores produced by the jobs, enabling informed feedback without manual data collection. Option A and D rely on custom frameworks and indirect quality signals, increasing complexity and reducing reliability. Option C focuses on operational health rather than response quality.

Therefore, Option B provides the most robust, scalable, and AWS-aligned quality assurance process for Amazon Bedrock–based applications.