Amazon Web Services AIP-C01 - AWS Certified Generative AI Developer - Professional

Option A best meets the combined requirements of low latency, stability, and validated safety controls by using purpose-built Amazon Bedrock features designed for production GenAI operations. The company’s latency target of under 1 second and its observation of degradation during spikes strongly indicate capacity and throughput variability. Provisioned throughput for Amazon Bedrock is intended to deliver more predictable performance by reserving inference capacity for a chosen model, reducing throttling risk and stabilizing response times under load. This directly improves operational consistency across Regions where on-demand capacity can vary.

The requirement to “block unsafe or hallucinated recommendations” is most directly addressed by Amazon Bedrock Guardrails . Guardrails provide managed safety enforcement, including sensitive information controls and configurable content policies. Using semantic denial rules enables the application to prevent unsafe guidance such as dangerous brewing temperatures or other harmful procedural instructions, enforcing safety at the model boundary rather than relying on downstream filtering.

The remaining requirement is “99.5% output consistency for identical inputs.” While generative models can be probabilistic, production systems achieve practical consistency by controlling prompt versions, inputs, and policy behavior. Amazon Bedrock Prompt Management supports controlled prompt lifecycle practices, including versioning and approval workflows, which reduce unintended drift across deployments and Regions. By ensuring the same approved prompt templates and parameters are used consistently, the company can materially improve repeatability for the same structured inputs and retrieval context, which is essential in multi-stage prompt chains.

The other options are incomplete. B improves experimentation and observability but does not enforce safety controls or stabilize latency. C can improve performance, but it does not provide validated safety enforcement at inference time. D can help retrieval relevance, but it does not address unsafe outputs or inference stability. Therefore, A is the only option that simultaneously targets predictable latency, governance of prompt behavior, and strong safety controls within Amazon Bedrock.

Option B best meets the requirement for reusable, versioned, and consistently governed components across multiple business units because it implements “platform-level standardization” through infrastructure as code plus automated compliance enforcement before deployment. Standardized CloudFormation templates provide reusable building blocks for security controls (identity, networking boundaries, encryption), observability practices (metrics, logs, traces), and RAG deployment patterns (knowledge base integration, ingestion pipelines, retrieval controls). This aligns with AWS guidance to operationalize well-architected patterns through repeatable templates rather than ad hoc implementations.

A centralized repository enables version control, change review, and governance of templates across all five business units. This satisfies the “versioned” and “reusable” requirements and provides a single source of truth for approved architectures. Integrating a CI/CD pipeline ensures that deployments are consistent and automated, reducing drift between business units and Regions.

CloudFormation Guard is most effective when used as a preventive control in the pipeline, not only after deployment. By running Guard rules during build or pre-deploy stages, the organization can enforce mandatory security and observability configurations and block noncompliant changes before they reach production. This supports consistent governance while still enabling business units to deploy quickly.

Option A performs compliance validation after deployment, which allows policy violations to be deployed first and remediated later. Option C provides governed provisioning but requiring console-based deployment reduces automation and can slow standardized CI/CD adoption; it also adds an additional governance layer that is not required to meet the stated needs. Option D is not enforceable and does not provide reusable, versioned, governed components.

Therefore, Option B provides the strongest, most scalable, and most consistently governed approach for standardized GenAI deployments across business units.

Option D is the correct solution because the Amazon Bedrock Converse API is purpose-built for multi-turn conversational interactions and is designed to work consistently across SDKs and compute environments. The Converse API standardizes how messages, roles, and context are represented, which ensures consistent behavior whether the application is running in AWS Lambda with Python or in Amazon EKS with JavaScript.

By passing previous messages in the messages array, the application explicitly maintains conversational context across turns without relying on external state stores. This approach is recommended by AWS for conversational GenAI workflows because it avoids state synchronization complexity and ensures deterministic model behavior across environments.

Using IAM roles for authentication provides a single, consistent security model for both Lambda and EKS. IAM roles integrate natively with AWS SDKs, eliminating the need for custom authentication logic or environment-specific credentials. This aligns with AWS best practices for least privilege and simplifies governance.

Option A introduces inconsistent authentication and custom formatting logic, increasing complexity. Option B unnecessarily introduces ElastiCache for state management, which is not required when using the Converse API correctly. Option C stores state in process memory, which is unsafe and unreliable for serverless and containerized workloads.

Therefore, Option D best satisfies the requirements for conversational consistency, multi-environment support, shared model usage, and consistent authentication with minimal operational overhead.

Option A is the correct solution because it uses native Amazon S3 metadata mechanisms to create a consistent, queryable, and model-friendly metadata framework with minimal complexity. S3 system metadata automatically records object creation and modification timestamps, providing reliable and consistent temporal context without additional processing.

Custom user-defined metadata is the appropriate mechanism for storing structured attributes such as author information. These key-value pairs are stored directly with the object, remain consistent across uploads, and can be accessed programmatically by downstream indexing or retrieval systems used by GenAI applications.

S3 object tags are ideal for domain classification because they are designed for lightweight categorization, filtering, and access control. Tags can be standardized across the organization to ensure consistent research domain labeling and can be consumed by search indexes or knowledge base ingestion pipelines without requiring access to the full document body.

Together, system metadata, user-defined metadata, and object tags provide a clean separation of concerns: timestamps for temporal context, metadata for authorship, and tags for classification. This structure allows foundation models to reason about document context (such as recency, domain relevance, and authorship) based on metadata alone, improving retrieval precision and reducing unnecessary token usage.

Options B, C, and D misuse features like Object Lock, access points, Storage Lens, or event notifications for purposes they were not designed for, adding complexity without improving metadata quality or model understanding.

Therefore, Option A best satisfies the metadata consistency, context enrichment, and low-overhead requirements for GenAI-driven document analysis.

Option B best meets the combined resiliency and observability requirements because it applies AWS-recommended retry behavior for transient throttling and enables true distributed tracing across service boundaries. During peak traffic, intermittent failures are commonly caused by throttling and other transient conditions. The AWS SDK standard retry mode provides exponential backoff with jitter, which reduces synchronized retry storms, prevents cascading failures, and improves overall system stability. Jitter is important because it spreads retry attempts over time, reducing load amplification during throttling events.

For observability, AWS X-Ray provides distributed tracing that follows a request across components such as API Gateway or load balancers, application services, and downstream calls to Amazon Bedrock. X-Ray can identify where latency is being introduced and which downstream call is contributing most to end-to-end response time. This is required to “identify latency contributors” and isolate performance issues under load.

The requirement also states that the company must correlate performance issues with specific FM characteristics. X-Ray annotations are designed for this purpose: the application can annotate traces with the model ID, inference parameters, region, or inference profile used. This enables filtering and analysis (for example, comparing latency or error patterns by model, parameter set, or endpoint configuration) without building a separate telemetry system.

Option A’s fixed-delay retries increase synchronized retry behavior and do not provide distributed tracing. Option C does not prevent cascading failures and cannot provide cross-service tracing. Option D is incorrect because CloudTrail is an audit logging service and does not provide distributed tracing for request latency analysis.

Therefore, Option B provides the correct combination of resilient retries and deep, model-correlated distributed observability for Amazon Bedrock workloads.

Option B is the most appropriate solution because it directly aligns with AWS-recommended architectural patterns for building scalable, observable, and resilient generative AI applications on Amazon Bedrock. The requirements clearly distinguish between simple and complex routing decisions, and this option addresses both in an optimal way.

Simple routing based on file extension is latency sensitive. Handling this logic directly in the application code avoids unnecessary orchestration, state transitions, and service calls. This approach ensures that straightforward requests, such as routing images to vision-capable foundation models or text files to language models, are processed with minimal overhead and maximum performance.

For complex routing based on content semantics, AWS Step Functions is specifically designed for multi-step workflows that require analysis, branching logic, and error handling. Semantic routing often requires inspecting meaning, intent, or structure before selecting the appropriate foundation model. Step Functions enables this by orchestrating analysis steps and applying conditional logic to determine the correct model to invoke using the Amazon Bedrock InvokeModel API.

A key requirement is detailed execution history. Step Functions provides built-in execution tracing, including state inputs, outputs, and error details, which is essential for auditing, debugging, and compliance. Additionally, Step Functions supports native retry and catch mechanisms, allowing the workflow to automatically fall back to alternate foundation models if a primary model invocation fails. This directly satisfies the fallback requirement without introducing excessive custom code.

The other options lack one or more critical capabilities. Lambda-only logic lacks deep observability and structured fallback handling, SQS introduces additional latency and limited workflow visibility, and multiple coordinated workflows increase architectural complexity without added benefit.

This complex set of requirements is best addressed by Amazon Bedrock Prompt Management . It allows the creation of parameterized prompts where variables (like demographics) can be injected at runtime, ensuring consistent medical terminology while adapting recommendations to the specific patient. Prompt Management natively supports versioning and approval workflows , which is a requirement for clinical safety and compliance. For audit and retention, Bedrock model invocation logging can be configured to send detailed prompt and response data to Amazon S3 . Storing these logs in S3 supports the 2-year retention requirement and facilitates local audits. S3 is more cost-effective for long-term storage than CloudWatch Logs alone. CloudTrail (Option A) only logs management events, not the actual prompt/response content required for medical auditing.

Option C best satisfies the requirement for rapid, correlated detection of model-related performance degradation. Amazon CloudWatch Application Insights provides automated observability across application components running on Amazon EC2, identifying abnormal behavior patterns without requiring extensive manual configuration.

Using custom metrics for recommendation quality, token usage, and response latency allows the company to directly monitor FM behavior, not just infrastructure health. Applying dimensions such as request type and user segment enables fine-grained correlation between performance issues and specific customer interactions or workloads.

CloudWatch anomaly detection is critical because it establishes dynamic baselines from historical data and detects deviations automatically. This enables alerts to be generated within minutes when FM behavior changes unexpectedly, satisfying the 10-minute alerting requirement without static thresholds that can miss subtle degradations.

CloudWatch Logs Insights complements metrics by enabling rapid analysis of log patterns, error messages, or unusual request flows associated with degraded recommendations. Because all data remains within CloudWatch, correlation between metrics, logs, and alerts is straightforward and operationally efficient.

Option A focuses on infrastructure metrics and lacks behavioral baselining. Option B provides tracing but not automated anomaly detection. Option D adds significant operational overhead and ingestion complexity for a use case already well supported by CloudWatch-native features.

Therefore, Option C delivers the most effective, scalable, and low-overhead observability solution for detecting FM-related performance deviations.

Option A is the best solution because it directly addresses both observed problems: user-perceived latency and resolver timeouts that occur more frequently for complex prompts. In the current design, an AWS AppSync Lambda resolver is configured with synchronous RequestResponse behavior. That means the client receives nothing until the entire retrieval and generation workflow completes. For longer-running knowledge base queries, this increases the likelihood of hitting request time limits in the synchronous path and creates a poor user experience because the UI appears stalled.

Using AWS Amplify AI Kit to implement streaming responses allows the application to return partial output incrementally as the model produces tokens. This improves perceived responsiveness because users can see the answer forming immediately, even when the full response takes longer. Streaming also reduces the impact of variable model latency and retrieval time because the client no longer waits for a single final payload before rendering content. From a troubleshooting perspective, streaming makes it easier to distinguish “slow generation” from “no response,” and it provides faster feedback during testing of complex questions.

Option B is not sufficient because increasing timeouts and adding retries can worsen load and cost while still producing a stalled UI experience. Retries also risk duplicating requests to the knowledge base and can amplify token usage. Option C introduces an awkward polling model for GraphQL interactions and adds significant operational complexity, while not inherently improving interactivity. Option D adds major architectural changes by replacing the knowledge base RetrieveAndGenerate call path with a different streaming invocation API and introducing a WebSocket layer, which is unnecessary when the goal is primarily to fix timeouts and improve UX within the existing AppSync and Amplify design.

Therefore, streaming through Amplify AI Kit is the most effective and lowest-friction improvement.

Thought for 24s