Passed Exam Today AIP-C01

Option A is the correct solution because it uses native Amazon Bedrock governance and evaluation capabilities to meet regulatory, performance, and deployment timeline requirements with the least operational overhead.

Amazon Bedrock guardrails provide built-in safety controls that enforce responsible AI policies directly during inference. Custom content filters and toxicity detection protect customer interactions and prevent disallowed investment guidance patterns without requiring custom application logic. Guardrails operate inline and are optimized for low latency, which helps meet the strict 200 ms response-time requirement.

Hallucination detection is addressed through Amazon Bedrock Model Evaluation, which supports automated evaluation at scale using LLM-as-a-judge techniques. This enables the company to detect factual inaccuracies and policy violations systematically, without building custom evaluation pipelines or requiring extensive human review. Evaluation outputs can be surfaced as metrics.

Storing all prompt-response pairs in Amazon DynamoDB provides a low-latency, highly scalable audit store that aligns with financial regulatory requirements. Using TTL enforces data retention policies automatically, reducing compliance risk and storage overhead.

Amazon CloudWatch custom metrics integrate seamlessly with existing compliance dashboards, allowing near–real-time monitoring of safety interventions, hallucination rates, and drift indicators. CloudWatch anomaly detection can be applied to these metrics to surface behavior changes quickly.

Option B relies on custom Lambda logic and S3-based auditing, increasing latency and operational complexity. Option C introduces additional services that increase setup time and may exceed the 60-day deployment window. Option D uses non–Bedrock-native monitoring and adds unnecessary infrastructure layers.

Therefore, Option A provides the most complete, compliant, and low-overhead governance solution for a regulated GenAI financial services application.

Option B best meets all requirements because it combines AWS-recommended resiliency patterns for transient failures with streaming-aware handling and adaptive protection against cascading retries during peak load. When timeouts and throttling occur, naïve retries can amplify traffic and worsen outages. Exponential backoff with jitter is the standard AWS best practice because it spreads retry attempts over time, reduces synchronized retry storms, and lowers the probability of repeatedly colliding with service limits.

The requirement also states the strategy must “adapt to changing service availability” and “prevent overwhelming Amazon Bedrock.” A circuit breaker pattern directly addresses this by temporarily stopping or reducing retries when failure rates exceed a threshold, allowing the system to degrade gracefully instead of continually hammering the service. This is a key mechanism to prevent cascading failures during throttling events.

Because the application uses response streaming and experiences broken chunks, the retry strategy must be streaming-aware. A streaming response handler that detects chunk delivery timeouts and buffers already received chunks prevents the user from losing progress when a connection drops. Resuming from the last successfully received chunk minimizes redundant generation and reduces additional load on the model compared with restarting the entire stream. This supports better user experience and better service efficiency during intermittent failures.

Token-aware request handling is supported in this architecture because the application can apply token budgeting before invoking the model (for example, trimming or summarizing excessive context) while still preserving streaming output behavior. Option B provides the correct backbone for this by focusing on adaptive control and robust streaming recovery.

Option A is too simplistic and risks retry storms. Option C combines conflicting elements (global token limit, cached completions for streaming) and includes impractical “request only missing chunks” behavior that is not a reliable property of streamed generative output. Option D includes useful ideas (load shedding) but relies on static caps and does not provide as strong adaptive retry control as circuit breaking.

Therefore, Option B is the most correct and operationally safe strategy for peak-load Bedrock streaming workloads.

Option B is the correct evaluation configuration because it enables end-to-end assessment of both retrieval and generation quality while supporting direct comparison of chunking strategies and foundation models. Amazon Bedrock evaluation jobs are designed to support RAG workflows by evaluating how well retrieved context supports accurate and high-quality model outputs.

A retrieve-and-generate evaluation job evaluates the complete RAG pipeline, not just retrieval. This is essential for medical information use cases, where both the relevance of retrieved content and the correctness of generated responses directly impact user safety and trust. Including multiple chunking strategies in the evaluation dataset allows side-by-side comparison under identical prompts and conditions.

Custom precision-at-k metrics measure how effectively the retrieval component surfaces relevant chunks, while an LLM-as-a-judge metric provides qualitative scoring of generated responses. Using a numeric scale enables consistent, repeatable evaluation and supports automated quality gates. Amazon Bedrock supports LLM-based evaluators to score dimensions such as accuracy, completeness, and relevance.

Using the same evaluator model to assess outputs from both FMs ensures consistent scoring and eliminates evaluator bias. This configuration allows the company to define quantitative thresholds that must be met before deployment, enabling automated promotion through CI/CD pipelines.

Option A evaluates retrieval only and cannot assess generation quality. Option C introduces manual review, which does not scale and delays deployment. Option D separates retrieval and generation evaluation, making it harder to correlate chunking strategies with final output quality.

Therefore, Option B best meets the requirements for systematic evaluation, comparison, and quality enforcement in an Amazon Bedrock–based RAG system.

Option B is the correct solution because it aligns with AWS guidance for building high-throughput, ultra-low-latency GenAI applications while maintaining predictable costs and automatic scaling. Amazon Bedrock provides access to foundation models that are specifically optimized for real-time inference use cases, including conversational and recommendation-style workloads that require responses within milliseconds.

Low-latency models in Amazon Bedrock are designed to handle very high request rates with minimal per-request overhead. Purchasing provisioned throughput ensures that sufficient model capacity is reserved to handle peak loads, eliminating cold starts and reducing request queuing during traffic surges. This is critical when supporting up to 500,000 concurrent calls with strict latency requirements.

Automatic scaling policies allow the application to dynamically adjust capacity based on demand, ensuring cost efficiency during off-peak hours while maintaining performance during peak usage. This directly supports the requirement to stay within a predefined monthly compute budget.

Option A fails because batch processing and complex reasoning models introduce higher latency and are not suitable for real-time suggestions. Option C introduces significantly higher operational and cost overhead due to dedicated GPU instances and manual scaling responsibilities. Option D is optimized for batch workloads and cannot meet the sub-200 ms latency requirement.

Therefore, Option B provides the best balance of performance, scalability, cost control, and operational simplicity using AWS-native GenAI services.