AIP-C01 AWS Certified Generative AI Developer - Professional Questions and Answers

Option D is the correct solution because it relies primarily on managed, purpose-built AWS services and minimizes custom infrastructure and model management. Amazon Bedrock guardrails provide native, configurable content safety controls that can block or redact disallowed content before or after model inference. This directly ensures that the platform does not process or produce inappropriate outputs while maintaining low operational overhead.

Using Amazon Comprehend PII detection as a preprocessing step integrates cleanly with an Amazon S3–based ingestion workflow. Comprehend is a fully managed service that detects and optionally redacts PII in text without requiring custom models or pipelines. This ensures that sensitive information is removed before content is passed to Amazon Bedrock for generation.

Amazon Rekognition image moderation is purpose-built for detecting unsafe or inappropriate visual content and integrates naturally into Step Functions workflows. Step Functions provides orchestration without requiring servers or long-running infrastructure, allowing the company to integrate text and image moderation steps in a clear, auditable pipeline.

Option A introduces redundant monitoring logic and alarms that do not directly enforce content safety. Option B requires building and maintaining custom SageMaker models, increasing complexity and operational burden. Option C applies moderation at authentication time and uses services like Textract that are not designed for content moderation, increasing latency and management overhead.

Therefore, Option D best satisfies content safety, PII protection, S3 integration, and minimal infrastructure management requirements.

Option B is the most appropriate solution because it directly uses Amazon Bedrock cross-Region inference profiles, which are designed to provide resilience and load distribution while respecting data residency boundaries. Cross-Region inference profiles allow applications to distribute inference requests across multiple Regions within a defined geographic boundary, such as Europe or North America, without requiring custom failover logic.

By specifying geographical codes in the inference profile ID, the application ensures that European user data is processed only within Europe-based Regions, satisfying regulatory requirements. At the same time, Bedrock automatically routes requests to healthy Regions within that geography when traffic spikes or service quotas are reached, improving availability and maintaining low latency.

Using separate Amazon API Gateway HTTP APIs for Europe and North America provides a clean, simple routing layer that directs users to the appropriate regional inference profile. This avoids complex custom routing or retry logic in application code and minimizes operational overhead.

Option A relies on custom routing and manual monitoring, which increases complexity and does not provide automatic resilience. Option C introduces custom retry and fallback logic that risks violating data residency requirements if misconfigured. Option D requires significant application-level failover logic and adds operational burden with Global Accelerator configuration.

Therefore, Option B best meets the requirements for low latency, data residency compliance, resilience during traffic spikes, and minimal operational complexity.

Option D is the correct solution because it directly addresses all three requirements: high retrieval accuracy, hallucination detection, and reduced human review costs. AWS recommends a layered evaluation strategy for high-stakes domains such as healthcare, where generative outputs must be both accurate and safe.

Using an automated LLM-as-a-judge evaluation enables scalable, consistent assessment of generated responses for factual grounding, relevance, and hallucination risk. This automated screening significantly reduces the number of responses that require manual inspection. Only responses that fall below defined quality thresholds or exhibit ambiguous behavior are escalated to targeted human reviews, which optimizes review effort and cost.

The use of Amazon Bedrock built-in evaluations provides standardized metrics specifically designed for RAG systems, including retrieval precision, faithfulness to source documents, and hallucination rates. These evaluations integrate directly with Amazon Bedrock knowledge bases and models, eliminating the need to build and maintain custom evaluation pipelines.

Option A focuses on entity extraction confidence, which does not reliably detect hallucinations in generative text. Option B requires maintaining and scaling a separate fine-tuned evaluation model, increasing complexity and cost. Option C is useful for regression testing but cannot detect hallucinations in real-world, open-ended clinical queries.

Therefore, Option D provides the most effective and operationally efficient approach to maintaining clinical-grade accuracy while minimizing human review effort.

Option D is the correct solution because it directly satisfies all three core requirements: data source registration, metadata-based attribution, and end-to-end audit logging, while remaining service-agnostic and scalable across internal and external data sources.

The AWS Glue Data Catalog is the AWS-native service for registering datasets and managing metadata centrally. It supports structured registration of diverse data sources and enables consistent tagging that can be used to attribute generated content back to its original source. This is essential for GenAI applications that combine multiple datasets and must provide traceability for outputs.

Metadata tags applied within the Glue Data Catalog ensure a consistent attribution framework that downstream systems—such as Retrieval Augmented Generation (RAG) pipelines or evaluation systems—can reference without embedding attribution logic directly in application code. This improves maintainability and governance.

AWS CloudTrail provides immutable audit logs of API activity across AWS services, including data access, metadata changes, and pipeline interactions. CloudTrail logs are critical for compliance and regulatory review because they capture who accessed which data, when, and through which service. This satisfies the requirement to maintain audit logs “throughout the pipeline,” not just at storage or application layers.

Option A introduces Lake Formation, which is primarily intended for fine-grained data lake permissions and is not required solely for traceability. Option B relies on CloudWatch Logs, which does not provide authoritative audit logging across services. Option C limits audit scope to S3 access and does not register or govern all data sources comprehensively.

Therefore, Option D provides the most complete and least intrusive solution for traceable, auditable GenAI data pipelines.

Option B is the best fit because hierarchical chunking is designed to preserve local detail while keeping broader document context available during retrieval, which directly addresses the problem of questions spanning methodology, results, and discussion. In large scientific papers, a single answer often depends on linked paragraphs across adjacent sections. If the knowledge base retrieves only small, isolated chunks, the RAG system can cite text that is semantically close to a query term but not contextually correct, producing inconsistent answers and irrelevant citations.

With hierarchical chunking, the knowledge base creates child chunks that are small enough for high-precision vector similarity matching, such as 200 tokens, which improves the likelihood that the retrieved text is tightly related to the user’s query. At the same time, each child chunk is associated with a larger parent chunk, such as 1,000 tokens, which retains the surrounding narrative and section-level context. This structure helps the retrieval pipeline return passages that include the relevant subsection plus the explanatory framing that prevents misinterpretation, which is especially important in scientific writing where methods, results, and discussion are interdependent.

The configured overlap further reduces boundary effects where key statements split across chunks. This improves continuity for paragraphs that bridge sections, such as a results paragraph that references the methodological setup or a discussion paragraph interpreting a specific metric.

Option A can improve consistency slightly, but fixed-size chunking still risks separating related paragraphs and does not provide a built-in mechanism to retrieve broader context linked to precise matches. Option C can create more meaningful boundaries, but it does not guarantee the parent-level context that hierarchical chunking provides at retrieval time. Option D increases operational burden and is not practical at the scale of 25 million

Option C is the correct solution because it resolves throttling while preserving performance and avoiding fixed costs during low-traffic periods. Amazon Bedrock supports on-demand inference with usage-based pricing, making it well suited for applications with time-zone–dependent traffic spikes.

Throttling during peak hours typically occurs when inference requests exceed available regional capacity. Cross-Region inference allows Amazon Bedrock to automatically distribute requests across multiple AWS Regions, reducing contention and preventing throttling without requiring reserved or provisioned capacity. This approach ensures continuous operation while maintaining low latency for users in different geographic locations.

Invocation logging and native metrics such as InvocationThrottles, InputTokenCount, and OutputTokenCount provide visibility into usage patterns and capacity constraints. Monitoring these metrics enables teams to validate that traffic distribution is working as intended and that performance remains consistent during peak periods.

Option A introduces fixed hourly costs by relying on provisioned throughput, which directly violates the requirement to avoid unnecessary spend during low-traffic periods. Option B introduces regional failover complexity and reactive behavior instead of proactive load distribution. Option D does not address the root cause of throttling, as distributing traffic across model versions within the same Region does not increase available capacity.

Therefore, Option C best aligns with AWS Generative AI best practices for scalable, cost-efficient, global serverless applications.

Option A is the correct solution because Amazon Q Business is explicitly designed to provide secure, governed access to enterprise data while preserving customer ownership and control. Each customer maintains their own Amazon Q Business index, which ensures that data never leaves the customer’s control boundary unless explicitly shared through approved access mechanisms.

By designating Example Corp as a data accessor, customers can allow controlled, auditable access to their indexed content through secure APIs. This model satisfies strict data governance requirements, including data ownership, access transparency, and revocation capability. Customers do not need to expose raw data or deploy infrastructure in Example Corp’s environment.

Amazon Q Business provides high semantic accuracy through managed indexing, ranking, and retrieval optimizations. Because real-time access is not required, this approach avoids the complexity and latency challenges of live federated retrieval while still delivering fast query performance suitable for customer experience use cases.

Option B introduces unnecessary operational complexity by requiring real-time MCP servers per customer. Option C requires customers to manage Amazon Bedrock knowledge bases and enable cross-account access, which increases integration complexity and governance risk. Option D requires shared Amazon Kendra indexes across accounts, which complicates access control and data ownership boundaries.

Therefore, Option A provides the cleanest, lowest-overhead architecture that meets data governance, accuracy, performance, and scalability requirements while minimizing operational burden for both Example Corp and its customers.

Option A is the correct answer because Amazon Bedrock Flows is purpose-built to orchestrate generative AI workflows that combine data access, deterministic transformations, and model invocation with minimal operational overhead. The requirements explicitly state that the workflow must retrieve content from Amazon S3, extract a specific portion of a predefined template, send that portion to an Amazon Bedrock model, and store the model’s response back into the same S3 bucket. Amazon Bedrock Flows natively supports all of these steps.

By configuring S3 action nodes at the beginning and end of the flow, the workflow can retrieve the original communications and persist the reviewed output without custom code. The expression step allows deterministic parsing of a specific portion of the template, which is essential when only part of the message should be reviewed. This avoids relying on generative logic for parsing, which would be less predictable and harder to audit. The agent step is then used specifically for the review task, where the foundation model evaluates or modifies the extracted content.

Option B uses AWS Step Functions, which can achieve similar outcomes but requires more explicit orchestration logic and does not provide GenAI-native constructs such as expressions and agent steps in a single managed experience. Options C and D rely on Amazon Bedrock agents and AWS Lambda functions to handle parsing and data movement, which increases complexity, operational overhead, and maintenance burden.

Because Amazon Bedrock Flows directly integrates S3 actions, parsing expressions, and model review steps in a single managed workflow, Option A best meets the requirements with the least development and operational effort.

Option B best meets the requirements because it provides systematic diagnosis, measurable comparison, and historical traceability of prompt performance. By placing prompts under version control and testing them against complex clinical documents, the company can consistently reproduce issues, track regressions, and compare prompt behavior using quantifiable metrics such as factual accuracy, completeness, and consistency. Automated testing ensures scalability and repeatability, while version history preserves prompt evolution over time.

Option A lacks objective metrics and does not address complex documents. Option C focuses on live traffic experimentation but does not inherently diagnose prompt inconsistencies or preserve detailed historical evaluations. Option D adds medical entity analysis but introduces unnecessary service coupling and does not provide robust prompt version history or automated comparative benchmarking. Therefore, Option B is the most complete and disciplined solution.

The correct combination is A, B, and D because these three options collectively satisfy the mandatory requirements for structured extraction, PII redaction before inference, regional human review, data residency, auditability, and high-scale availability with managed AWS services.

Option A is essential because Amazon Textract is the AWS-managed service designed to extract structured data from scanned documents such as forms, tables, and financial statements. Textract provides confidence scores, and Amazon Augmented AI (A2I) is purpose-built to route low-confidence extractions to human reviewers. Deploying Textract and A2I within the same Region ensures that the human review loop remains regionally constrained, meeting strict data residency requirements for applicants.

Option B satisfies the requirement to redact PII before inference by using AWS Lambda preprocessing. It also adds Amazon Bedrock guardrails to enforce safety controls on model outputs. Region-specific IAM roles ensure that only authorized principals in the correct Region can access the extracted data and invoke downstream services, strengthening residency enforcement and auditability.

Option D ensures that source documents are stored in Amazon S3 in the same Region as the applicant. Object metadata and tagging provide an auditable trail, supporting compliance reporting and traceability. S3 also provides the durability and availability needed to support 99.9% application availability as part of a well-architected pipeline.

Option C is not the correct approach for structured extraction from scans. Option E adds useful quality validation but is not strictly required to meet the stated requirements compared to A, B, and D. Option F is unrelated to the extraction/redaction/residency workflow requirements.

Therefore, A, B, and D are the best three choices to meet all stated requirements with minimal operational overhead.

Option A provides the most complete, AWS-native defense-in-depth solution for protecting against prompt injection attacks while meeting audit and resiliency requirements. Amazon Bedrock guardrails are designed specifically to enforce safety policies on both user inputs and model outputs, including protections against prompt injection and jailbreak attempts.

Setting content filters to high increases sensitivity to malicious or manipulative inputs. Guardrail profiles allow the same guardrail configuration to be applied consistently across multiple Regions, enabling cross-Region inference and failover without configuration drift. This directly satisfies the requirement for regional resilience.

Amazon CloudWatch Logs captures detailed guardrail intervention events, including when content is blocked, modified, or flagged. Custom metrics derived from these logs enable fine-grained auditing, alerting, and reporting on safety enforcement actions. This provides a more detailed audit trail of safety interventions than API-level logs alone.

Option B adds WAF protection but lacks detailed guardrail intervention logging. Option C introduces additional services and custom logic that increase complexity and may miss model-specific injection patterns. Option D references replication concepts that are not aligned with Bedrock guardrail operational models and relies on word filters, which are insufficient against sophisticated prompt injection techniques.

Therefore, Option A best meets the requirements for layered protection, auditability, and cross-Region resilience using managed Amazon Bedrock safety controls.

Option C is the correct solution because AWS AppConfig is designed for real-time, validated, centrally managed configuration changes with safe rollout, immediate propagation, and rollback support—exactly matching the company’s requirements.

By storing routing rules, cost thresholds, regulatory constraints, and A/B testing logic in AWS AppConfig, the company can switch between Amazon Bedrock foundation models without redeploying Lambda code. AppConfig supports feature flags, dynamic configuration updates, JSON schema validation, and staged rollouts, which are essential for safely managing complex and frequently changing routing logic.

Using the AWS AppConfig Agent, Lambda functions can retrieve cached configurations efficiently, ensuring low latency even under thousands of concurrent requests. This approach allows the Lambda function to apply proprietary business logic—such as user tier, transaction value, Region compliance, and real-time cost metrics—before selecting the appropriate FM.

Option A is operationally fragile because environment variable changes require function restarts and do not support validation or controlled rollouts. Option B is too limited for complex, dynamic logic and is difficult to maintain at scale. Option D misuses Lambda authorizers, which are intended for authentication and authorization, not high-frequency dynamic routing decisions.

Therefore, Option C provides the most scalable, flexible, and low-overhead architecture for dynamic, regulation-aware FM routing in a global GenAI system.

Option C directly addresses the root cause of truncated and inconsistent responses by using AWS-recommended semantic chunking and dynamic retrieval rather than static or sequential chunk processing. Amazon Bedrock documentation emphasizes that foundation models have fixed context windows and that sending oversized or poorly structured input can lead to truncation, loss of context, and degraded output quality.

Semantic chunking breaks documents based on meaning instead of fixed token counts. By using a breakpoint percentile threshold and sentence buffers, the content remains coherent and semantically complete. This approach reduces the likelihood that important concepts are split across chunks, which is a common cause of inconsistent summarization results.

The RetrieveAndGenerate API is designed specifically to handle large documents that exceed a model’s context window. Instead of forcing all content into a single inference call, the API generates embeddings for chunks and dynamically selects only the most relevant chunks based on similarity to the user query. This ensures that the FM receives only high-value context while staying within its context window limits.

Option A is ineffective because chaining chunks sequentially does not align with how FMs process context and risks exceeding context limits or introducing irrelevant information. Option B improves structure but still relies on larger parent chunks, which can lead to inefficiencies when processing very large documents. Option D processes segments independently, which often causes loss of global context and inconsistent summaries.

Therefore, Option C is the most robust, AWS-aligned solution for resolving truncation and consistency issues when processing large technical documents with Amazon Bedrock.

The first option labeled B is the correct solution because it fully satisfies both private connectivity and fine-grained cross-account data governance requirements using AWS-native services.

Creating interface VPC endpoints for Amazon Bedrock runtimes ensures that all inference calls remain on the AWS private network and never traverse the public internet. Running AWS Lambda functions in private subnets enforces network isolation, and using IAM conditions that restrict access to specific VPC endpoints and roles prevents unauthorized inference calls.

For the governed data lake, AWS Lake Formation LF-tag–based access control is the recommended AWS mechanism for enforcing cross-account, column-level permissions. LF-tags allow the company to define data access policies once and apply them consistently across accounts, databases, tables, and even individual columns. This is required for sensitive customer records and is not achievable with S3 bucket policies or IAM alone.

The second option labeled B uses a NAT gateway, which violates the private connectivity requirement. Option C uses public Bedrock endpoints and only database-level grants, which are insufficient. Option D relies on IAM path-based policies, which cannot enforce column-level access and introduces public fallback paths.

Therefore, the first option labeled B is the only solution that meets all networking, security, and data governance requirements.

Option A is the best solution because it satisfies streaming, token control, and retry requirements while keeping operational overhead low by using fully managed, serverless AWS services. Amazon API Gateway HTTP APIs provide a lightweight, cost-effective front door for APIs and integrate cleanly with AWS Lambda for request processing and security controls.

AWS Lambda response streaming allows the API to begin returning content to the client as soon as partial model output is available, reducing perceived latency and improving user experience for long responses. Using Lambda as the integration layer also provides a centralized place to enforce token-aware request handling, such as rejecting oversized requests, truncating optional context, or applying consistent limits across users and tenants to manage compute usage.

Retry logic is best handled in the client or integration layer for transient failures such as timeouts and throttling. Lambda can implement controlled retries with exponential backoff and jitter, while API Gateway timeouts help bound request lifetimes and prevent hung connections from consuming resources indefinitely. Because the model service is managed, the company avoids infrastructure management and focuses only on request shaping, safety, and resiliency behavior.

Option B is not suitable because client-side polling is not true streaming, front-end token enforcement is insecure and inconsistent, and API Gateway does not provide model-aware retry behavior on its own. Option C introduces container hosting and scaling complexity, which increases operational overhead compared to serverless. Option D can work, but REST APIs are generally heavier than HTTP APIs for this pattern and do not reduce overhead compared to Option A.

Therefore, Option A provides the required streaming and resiliency capabilities with the least infrastructure management effort.

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 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

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 B best satisfies the requirements while minimizing development effort by combining managed semantic search capabilities with fully managed foundation models. AWS Generative AI guidance describes semantic search as a vector-based retrieval pattern where both documents and user queries are embedded into a shared vector space. Similarity search (such as k-nearest neighbors) then retrieves results based on meaning rather than exact keywords.

Amazon OpenSearch Service natively supports vector indexing and k-NN search at scale. This makes it well suited for large datasets such as 20 million restaurants and 200 million reviews while still achieving sub-second latency for the majority of queries. Because OpenSearch is a distributed, managed service, it automatically scales during peak traffic periods and provides cost-effective performance compared with building and tuning custom vector search pipelines on relational databases.

Using Amazon Bedrock to generate embeddings significantly reduces development complexity. AWS manages the foundation models, eliminates the need for custom model hosting, and ensures consistency by using the same FM for both document embeddings and query embeddings. This aligns directly with AWS-recommended semantic search architectures and removes the need for model lifecycle management.

Hourly updates to restaurant data can be handled efficiently through incremental re-indexing in OpenSearch without disrupting query performance. This approach cleanly separates transactional data storage from search workloads, which is a best practice in AWS architectures.

Option A does not meet the semantic search requirement because keyword-based search cannot reliably interpret complex natural language intent. Option C introduces scalability and performance risks by running large-scale vector similarity searches inside PostgreSQL, which increases operational complexity. Option D adds unnecessary ingestion and abstraction layers intended for retrieval-augmented generation, not high-throughput semantic search.

Therefore, Option B provides the optimal balance of performance, scalability, data freshness, and minimal development effort using AWS Generative AI services.

Option C best addresses both core problems: hallucinated recommendations that do not exist in the catalog and slow response times, while keeping operational overhead low. The most direct way to prevent the model from recommending unavailable products is to ground generation on authoritative product catalog data at inference time. An Amazon Bedrock knowledge base is designed for this pattern by ingesting domain data, chunking content, creating embeddings, and retrieving the most relevant catalog entries when a user asks for recommendations. Implementing Retrieval Augmented Generation ensures the foundation model receives only approved, catalog-backed context and can cite or base its output on those retrieved items. This sharply reduces the likelihood of inventing products, because the response is conditioned on retrieved catalog records rather than relying on the model’s parametric memory.

The requirement also notes that most interactions are unique. That makes response caching far less effective, because there are fewer repeated prompts to benefit from cached outputs. Instead, improving the retrieval and model invocation path is the better optimization. Using the PerformanceConfigLatency parameter set to optimized prioritizes lower latency behavior for model inference, helping meet faster recommendation generation without requiring the company to build and operate additional infrastructure.

The other options do not solve the root cause as reliably. Prompt engineering and streaming can improve perceived latency, but they do not guarantee catalog-only recommendations because the model can still hallucinate items. Guardrails can help detect or block certain undesired outputs, but without consistent catalog grounding they do not ensure every recommendation is derived from the company’s product data. Building a custom OpenSearch validation and caching layer increases operational complexity, and caching is misaligned with predominantly unique interactions.

The correct combination is B and C because together they address both workload diversity and hybrid deployment requirements with minimal custom engineering.

Option B provides consistent, high-throughput access by configuring provisioned throughput in Amazon Bedrock. Provisioned throughput guarantees predictable capacity and performance, which is essential for batch processing workloads that require sustained inference rates. This eliminates cold starts and throttling concerns that can occur with purely on-demand usage, making it well suited for high-volume enterprise workloads.

Option C enables hybrid deployment across cloud and on-premises environments by deploying foundation models to Amazon SageMaker AI endpoints and using Amazon SageMaker Neo for edge and on-premises optimization. SageMaker Neo compiles models for target hardware, allowing inference to run efficiently outside the AWS cloud while still using AWS-managed tooling. Orchestrating these deployments with AWS Lambda allows consistent invocation patterns across environments.

Option A uses asynchronous endpoints, which are not suitable for real-time, low-latency inference. Option D addresses scaling but does not support on-premises or hybrid deployment. Option E simplifies model onboarding but does not address hybrid execution or guaranteed throughput.

Therefore, Options B and C together provide real-time and batch support, predictable performance, and true hybrid deployment while minimizing operational overhead.

AWS Step Functions provides native support for human-in-the-loop workflows, making it the best fit for regulatory oversight requirements. The waitForTaskToken integration pattern is explicitly designed to pause a workflow until an external actor—such as a human reviewer—completes a task.

In this architecture, AI-generated recommendations are sent to a human technician for review. The workflow pauses execution using a task token. Once the technician approves or rejects the recommendation, an AWS Lambda function calls SendTaskSuccess or SendTaskFailure, allowing the workflow to continue deterministically.

This approach ensures full auditability, as Step Functions records every state transition, timestamp, and execution path. Storing review outcomes in Amazon DynamoDB provides durable, queryable audit records required for regulatory compliance.

Option A requires custom orchestration and lacks native workflow state management. Option C incorrectly uses AWS Glue, which is not designed for approval workflows. Option D uses caching instead of durable audit storage and introduces unnecessary complexity.

Therefore, Option B is the AWS-recommended, lowest-risk, and most auditable solution for mandatory human review of AI outputs.

Option B best satisfies the requirements with the least custom development effort by using native Amazon Bedrock capabilities for prompt experimentation, traffic management, fairness monitoring, and alerting. Amazon Bedrock Prompt Management allows teams to define and manage multiple prompt variants without code changes, making it ideal for comparing recommendation strategies across demographic groups.

Amazon Bedrock Flows enables controlled traffic allocation between prompt variants, which supports real-time A/B testing. This allows the company to collect live fairness metrics under production conditions instead of relying on offline analysis. Because Flows are fully managed, they eliminate the need for custom routing or experimentation frameworks.

Amazon Bedrock guardrails provide built-in monitoring and intervention mechanisms. When configured for fairness-related checks, guardrails can detect policy violations and surface metrics such as InvocationsIntervened, which indicate when outputs are modified or blocked due to rule enforcement. These metrics integrate directly with Amazon CloudWatch, enabling real-time dashboards and threshold-based alarms. Setting an alarm at a 15% discrepancy threshold satisfies the alerting requirement with minimal configuration.

Weekly reporting can be generated from CloudWatch metrics using scheduled exports or dashboards without building custom analytics pipelines. Option A requires significant custom post-processing logic. Option C introduces an additional service with higher operational overhead and is not optimized for real-time monitoring. Option D focuses on offline evaluation jobs and does not provide continuous real-time fairness monitoring.

Therefore, Option B provides the most AWS-native, scalable, and low-effort solution for fairness evaluation and monitoring.

Option A best satisfies the requirement to capture multi-hop, highly interconnected relationships with minimal operational overhead. Traditional vector similarity search excels at finding semantically similar text but is not optimized for reasoning over explicit entity-to-entity relationships, especially when analysts need indirect, multi-hop connections (for example, fund → holding → issuer → sector → regulation). Graph-based retrieval is designed specifically for these kinds of relationship traversals.

GraphRAG combines retrieval-augmented generation with graph-aware context selection. By representing entities and their relationships in a graph store, the system can traverse multiple hops to assemble a holistic set of relevant facts. This improves completeness and reduces the chance that the model misses indirect relationships that are essential for accurate investment guidance.

Amazon Neptune Analytics provides a managed graph analytics environment capable of efficiently traversing and analyzing complex relationship networks. When integrated with Amazon Bedrock Knowledge Bases, it reduces custom engineering by providing managed ingestion, retrieval, and orchestration patterns suitable for GenAI applications. This lowers operational overhead compared to building and maintaining custom multi-stage retrieval logic.

Meeting the sub-3-second requirement is also more feasible with a graph-optimized engine because multi-hop traversals can be executed efficiently compared to chaining multiple vector searches and joining results in an application layer. The managed nature of Knowledge Bases and Neptune Analytics reduces maintenance, scaling, and operational burden while enabling strong performance.

Option B and C require extensive custom logic and orchestration, increasing complexity and latency. Option D is not designed for graph-style multi-hop exploration and would require significant custom indexing and retrieval logic.

Therefore, Option A is the most AWS-aligned and operationally efficient approach for multi-hop relationship-aware RAG with strong performance.