AIP-C01 Sample Questions Answers

The least operational overhead approach is to use managed Amazon Bedrock model evaluation workflows with datasets stored in Amazon S3 , and then publish results into Amazon CloudWatch for dashboards. That is exactly what options B and C combine.

Step B correctly places standardized evaluation inputs in Amazon S3 and focuses on granting the evaluation workflow the right permissions to read those datasets. In practice, the key requirement is controlled access to the S3 objects used as evaluation datasets. Establishing IAM permissions and private access patterns (such as using VPC connectivity patterns where applicable to the organization’s networking posture) is aligned with enterprise requirements and avoids building custom storage or data distribution systems for evaluators.

Step C then operationalizes the evaluation lifecycle with minimal infrastructure: a scheduled AWS Lambda function starts evaluation jobs using the S3 dataset location, and a second Lambda function checks job status and pushes results and operational signals to CloudWatch . This meets the platform requirement to surface accuracy metrics in dashboards because CloudWatch metrics/logs can be visualized in dashboards and queried through CloudWatch Logs Insights . It also supports continuous, standardized comparisons across models without requiring developers to run ad-hoc experiments.

The alternatives introduce more operational burden. D and E rely on Amazon SageMaker -based tooling, notebook jobs, and open source evaluation frameworks, which require more environment management, dependency control, scaling considerations, and maintenance over time. A includes CORS, which is primarily a browser-access concern and does not address how Bedrock-managed evaluation jobs securely access S3 in the typical service-to-service pattern.

Therefore, B + C achieves standardized model evaluation, automated scheduling, and dashboard-ready observability with the smallest operations footprint.

The errors described indicate missing permissions at both the application orchestration and data access levels. The 400 Bad Authorization from BedrockAgentRuntime indicates the Lambda execution role lacks the identity permission to invoke the agent; adding bedrock:InvokeAgent and aoss:APIAccessAll (which allows the principal to interact with OpenSearch Serverless APIs) is necessary. The 403 Forbidden error from OpenSearch Serverless specifically relates to data-plane permissions. Unlike traditional OpenSearch, Serverless uses data access policies . To " manage collections at scale " automatically, a policy must be created that uses pattern-based resource rules (e.g., matching a prefix), ensuring that as new collections or indexes are created, the required principals (the Lambda role and the Bedrock service role) are granted the necessary access without manual policy updates for every new resource.

Option A is correct because Amazon Bedrock Guardrails provides a native sensitive-information filter for personally identifiable information. The filter can detect supported PII types and use the MASK action so detected values in model requests or responses are replaced with placeholders such as the PII type. This directly satisfies the requirement to mask PII from foundation model responses with minimal operational effort. It avoids creating and maintaining an additional preprocessing pipeline. Option B can detect or redact PII with Amazon Comprehend, but it requires Lambda logic and data-processing workflows before Bedrock invocation. Options C and D require scanning, copying, and segregating objects across S3 buckets and still do not directly enforce response masking. For response-level protection in Bedrock, the managed Guardrails capability is the simplest and most purpose-built control. AWS Documentation

================

Option A is the optimal solution because it provides scalable semantic search, rich metadata filtering, and tight integration with Amazon Bedrock while minimizing operational overhead. Amazon OpenSearch Serverless is designed for high-volume, low-latency search workloads and removes the need to manage clusters, capacity planning, or scaling policies.

With support for vector search and structured metadata filtering, OpenSearch Serverless enables efficient similarity search across 10 million embeddings while applying constraints such as language, publication date, regulatory agency, and document type. This is critical for financial services use cases where relevance and compliance depend on precise filtering.

Integrating OpenSearch Serverless with Amazon Bedrock Knowledge Bases enables a fully managed RAG workflow. The knowledge base handles embedding generation, retrieval, and context assembly, while Amazon Bedrock generates responses using a foundation model. This significantly reduces custom glue code and operational complexity.

Multilingual support is handled at the embedding and retrieval layer, allowing documents in English, Spanish, and Portuguese to be searched semantically without language-specific query logic. OpenSearch’s distributed architecture ensures consistent low-latency responses for real-time customer interactions.

Option B increases operational overhead by requiring database tuning and scaling for vector workloads. Option C does not support advanced metadata filtering, which is a key requirement. Option D introduces unnecessary complexity and is not optimized for large-scale semantic document retrieval.

Therefore, Option A best meets the requirements for performance, scalability, multilingual support, and minimal management effort in an Amazon Bedrock–based RAG application.

Option A is the best solution because it natively delivers retrieval grounding, source attribution, and low operational overhead through Amazon Bedrock Knowledge Bases. The key requirements are: retrieve from company data sources, cite sources, link claims to source documents, and keep latency under 3 seconds. Knowledge Bases are a managed RAG capability that handles document ingestion, chunking, embeddings, retrieval, and assembly of context for model generation. This eliminates the need to build and maintain custom retrieval infrastructure.

Source attribution is crucial: the application must “link data claims to source documents.” When source attribution is enabled, the RAG pipeline can return references to the underlying documents and segments used for generation. This enables traceable citations that can be surfaced to end users and used for internal auditing.

Using the Anthropic Claude Messages API (or equivalent conversational interface) with RAG allows the application to generate recommendations grounded in retrieved context while keeping responses conversational. Setting relevance thresholds helps reduce noisy retrieval, which supports both accuracy and latency targets by limiting the context passed to the model.

Storing reasoning and citations in Amazon S3 supports audit and retention needs with minimal operational burden. While the prompt may request step-by-step reasoning, AWS best practice is to produce user-facing explanations that are faithful and attributable without exposing internal reasoning traces unnecessarily. With source-grounded outputs, the system can provide concise rationale tied to citations while maintaining fast response times.

Option B emphasizes extended thinking, which increases latency and does not ensure source linkage. Option C adds significant operational overhead through custom model hosting and separate citation systems. Option D requires more custom tracking work than A while not improving retrieval attribution beyond what Knowledge Bases already provide.

Therefore, Option A best meets the requirements with the least operational overhead.

Option B is the optimal solution because it maximizes similarity search accuracy and performance for a small, proprietary dataset while maintaining low operational complexity. Amazon MemoryDB is a fully managed, in-memory database that provides microsecond-level latency, making it ideal for real-time RAG workloads that require fast vector similarity searches.

For small datasets with low index counts, the Hierarchical Navigable Small World (HNSW) algorithm is recommended by AWS for its high recall and accuracy. Unlike approximate methods optimized for massive datasets, HNSW excels at returning the most semantically relevant vectors with minimal loss of precision, which directly improves the quality of responses generated by the Amazon Bedrock foundation model.

Vertical scaling in MemoryDB is sufficient for this use case because the dataset size is limited. Scaling up instance size provides increased memory and compute capacity without the complexity of managing distributed indexes or sharding strategies. This simplifies operations while maintaining predictable performance.

Option A’s Flat algorithm is computationally expensive and inefficient at scale, even for moderate query volumes. Option C introduces higher latency and operational overhead by using a relational database not optimized for in-memory vector search. Option D is unsuitable because Amazon DocumentDB is not designed for high-performance vector similarity workloads and introduces unnecessary replica management complexity.

Therefore, Option B best meets the requirements for accuracy, performance, and efficient integration with an Amazon Bedrock–based RAG application.

Option C is the correct solution because it directly addresses both correctness and performance issues by grounding the model’s responses in authoritative product data using Retrieval Augmented Generation. Amazon Bedrock Knowledge Bases are designed to connect foundation models to trusted enterprise data sources, ensuring that generated responses are constrained to known, validated content.

By ingesting the product catalog into a knowledge base, the GenAI application retrieves only products that actually exist in the catalog. This prevents hallucinated or unavailable recommendations, which is a common issue when models rely solely on prompt instructions without retrieval grounding. RAG ensures that the model’s output is based on retrieved facts rather than learned generalizations.

Setting the PerformanceConfigLatency parameter to optimized enables Bedrock to prioritize lower-latency retrieval and inference paths, improving responsiveness for real-time recommendation scenarios. This directly addresses the reported performance issues without requiring provisioned throughput or caching strategies that are ineffective for mostly unique interactions.

Option A improves safety and latency predictability but does not ensure recommendations are limited to valid products. Option B relies on prompt constraints, which are not sufficient to prevent hallucinations. Option D introduces additional validation and caching layers but increases complexity and does not improve generation relevance.

Therefore, Option C best resolves both relevance and latency challenges using AWS-native, low-maintenance GenAI integration patterns.

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 B provides the least operational overhead because it keeps the solution primarily inside managed Amazon Bedrock capabilities, minimizing custom orchestration code and infrastructure to operate. The core requirements are domain grounding, reduced semantic dilution for complex questions, and consistent low-latency responses at high request volume. A Bedrock knowledge base is purpose-built for Retrieval Augmented Generation by ingesting domain documents, chunking content, generating embeddings, and retrieving the most relevant passages at runtime. This directly addresses the need to reference domain-specific medical terminology from authoritative documents to reduce ambiguity and improve factual accuracy.

Reducing semantic dilution typically requires improving the retrieval query so that the retriever focuses on the most relevant concepts, especially for long or multi-intent questions. Enabling query decomposition allows the system to break a complex medical query into smaller, more targeted sub-queries. This increases retrieval precision and recall for each sub-question, which helps the model generate a more accurate synthesized response grounded in the retrieved medical context.

Amazon Bedrock Flows provide a managed way to orchestrate multi-step generative AI workflows, such as preprocessing the input, performing retrieval against the knowledge base, invoking a foundation model, and formatting the final response. Because flows are managed, the com pany avoids maintaining custom state machines, multiple Lambda functions, or bespoke routing logic. This reduces operational overhead while still supporting repeatable, observable execution.

Compared with the alternatives, option A introduces an agent plus API Gateway routing and multiple model choices, increasing configuration and runtime complexity. Option C requires hosting and scaling custom models on SageMaker AI, which adds significant operational burden and latency risk. Option D relies on multiple Lambda functions orchestrated by an agent, which adds more moving parts and increases cold-start and integration overhead. Option B most directly meets the requirements with the smallest operational footprint.

Options A and E are correct because the failure pattern is caused by exceeding the model’s usable context window and by sending too much raw customer data directly to the FM. Amazon Bedrock Knowledge Bases follows the RAG pattern by splitting source content into manageable chunks, converting chunks into embeddings, storing them in a vector index, and using semantic similarity to retrieve relevant content for a user query. This supports option E because the application can index customer purchases, profiles, and review-related information, then retrieve only the most relevant records for the current recommendation request instead of stuffing all raw data into one prompt.

Option A is also correct because chunking and staged synthesis are standard ways to handle inputs that exceed an FM’s context capacity. Processing smaller segments avoids context-length-exceeded errors, and a final synthesis call can combine intermediate findings into a complete recommendation. This is especially useful when the company says it wants the system to consider all customer data, not merely truncate older or less important data. Amazon Bedrock Knowledge Bases also lets teams configure how content is chunked for storage and retrieval, which supports a structured approach rather than an oversized one-shot prompt.

Option B is not sufficient because truncating “less important” data conflicts with the requirement to consider all customer data. Option C violates the implied design direction because the company wants to use Knowledge Bases, and simply choosing a larger context model does not solve long-term growth of customer histories. Option D is technically incorrect: model parameters such as max_tokens control output generation limits, not the model’s maximum context window, and different Claude models have model-specific maximum values. You cannot use additionalModelRequestFields to bypass the FM’s context limit.

==========

Option B is the correct solution because Amazon Bedrock Prompt Management is purpose-built to manage, govern, and standardize prompt usage at scale across teams and Regions. It provides native version control, allowing teams to track prompt changes over time and ensure that only approved versions are used in production workflows.

Prompt Management supports approval workflows that align with enterprise governance requirements. Approval permissions can be enforced through IAM policies, ensuring that only authorized reviewers can approve or publish prompt versions. This removes the need for custom workflow engines or external storage systems, significantly reducing operational overhead.

Parameterized prompt templates enable consistent prompt structure while allowing controlled variation through defined variables. This ensures consistent quality standards and reduces prompt drift, which is critical when hundreds of prompts are reused across multiple applications and teams.

AWS CloudTrail integrates natively with Amazon Bedrock to provide immutable audit logs for prompt creation, updates, approvals, and usage. These detailed audit trails satisfy compliance requirements and allow security and governance teams to trace prompt activity across Regions and users.

Option A requires significant custom development to coordinate approvals and maintain state. Option C relies on general-purpose workflow services and manual versioning mechanisms that are error-prone and difficult to scale. Option D uses services not designed for large-scale GenAI prompt governance and introduces unnecessary complexity.

Therefore, Option B best meets the requirements for scalable, auditable, and low-overhead governance of AI-generated content using Amazon Bedrock.

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 is the correct solution because it parallelizes independent foundation model inference tasks while maintaining orchestration, observability, and time-bound execution. AWS Generative AI best practices emphasize reducing end-to-end latency by parallelizing independent inference calls rather than scaling individual calls vertically.

In this scenario, each report requires multiple independent analyses such as financial extraction, sentiment analysis, and compliance validation. These tasks do not depend on each other’s output, making them ideal candidates for parallel execution. AWS Step Functions provides a Parallel state that can invoke multiple AWS Lambda functions simultaneously, drastically reducing total processing time compared to sequential execution.

By invoking Amazon Bedrock from separate Lambda functions in parallel, the system can reduce batch execution time from 45 seconds to well under the 10-second requirement, assuming each inference call remains within acceptable latency bounds. Step Functions also provide built-in error handling, retries, and state tracking, which improves reliability without increasing complexity.

CloudWatch metrics allow teams to monitor both workflow execution time and individual model inference latency, enabling performance tuning and operational visibility. Configuring client-side timeouts ensures that slow or failed model invocations do not block the entire batch.

Option A still processes tasks sequentially and therefore cannot meet the strict latency requirement. Option C introduces queuing delays and sequential processing within each report, which increases total execution time. Option D relies on container-based sequential processing and adds unnecessary operational overhead for a workload that is event-driven and latency-sensitive.

Therefore, Option B best meets the performance, scalability, and operational efficiency requirements for high-speed batch document analysis using Amazon Bedrock.

Option B is correct because it uses the managed evaluation capability in Amazon Bedrock that is intended specifically for comparing foundation models using a consistent prompt set and producing structured results with minimal custom tooling. In a Bedrock evaluation workflow, you provide an input dataset of prompts, typically in JSON Lines format so each line represents one evaluation record. Storing the JSONL file in Amazon S3 allows Bedrock to read the dataset at scale and write standardized evaluation outputs back to S3 for downstream analysis, sharing, and retention.

The key requirement is to assess both quality and safety across multiple models. A Bedrock evaluation job can use a judge model to score the generated outputs against defined criteria. This approach supports repeatable, apples-to-apples comparisons because the same judge model and scoring rubric can be applied to every candidate foundation model. The candidate models are configured as generators, meaning each evaluation job run uses one selected FM to produce answers for the same prompt set, and the judge model evaluates those answers. That matches the requirement to generate evaluation reports that help a data scientist select the best FM.

Option A does not use Bedrock evaluation jobs, and a knowledge base plus RetrieveAndGenerate is a RAG pattern, not an evaluation framework. It would produce responses but not standardized scoring and reporting suitable for model selection. Option C is incorrect because Bedrock evaluation outputs are delivered to S3, not directly to a BI destination, and selecting the candidate FM as the evaluator conflicts with the intended pattern of using a stable judge model. Option D misuses knowledge bases and retrieval evaluation types when the requirement is prompt-based model assessment rather than evaluating retrieval quality.

Amazon CloudWatch provides the most integrated path for unifying technical and business metrics. By importing business metrics into CloudWatch (via custom metrics or metric streams), teams can build custom dashboards that provide a single pane of glass for both system health and conversion performance. Composite alarms allow stakeholders to be notified only when multiple conditions are met (e.g., high latency and dropping conversion rates), reducing alert fatigue. Applying anomaly detection to these metrics is essential for GenAI workloads because performance baselines can shift subtly; CloudWatch can automatically detect these deviations and trigger alerts through Amazon SNS . This solution provides comprehensive correlation and automated alerting with less operational complexity than managing external visualization servers (Option B) or multi-service analytics pipelines (Option C).

The correct combination is A, D, and F because these guardrail features directly map to the stated financial compliance and governance requirements.

Option A is required because denied topics guardrails are explicitly designed to block entire categories of requests, such as requests for guaranteed returns or specific stock recommendations. These are regulatory-sensitive scenarios where partial filtering is insufficient and full blocking is required to prevent violations.

Option D is correct because custom word filters are the appropriate guardrail mechanism to block references to specific competitor names. Content filters are category-based (such as hate, sexual, or violence-related content) and are not suitable for blocking organization-specific competitor references. Custom word filters allow precise blocking at both input and output stages.

Option F is required because a high grounding score threshold enforces that model outputs must be strongly supported by approved source material. This prevents the AI assistant from making speculative or unfounded claims that are not aligned with the company’s approved financial guidance, which is critical in regulated financial environments.

Option B is incorrect because content filters do not target domain-specific financial advice patterns. Option C is incorrect for the same reason—competitor names are not a content filter category. Option E would weaken factual grounding and increase hallucination risk.

Therefore, A, D, and F together provide topic blocking, competitor exclusion, and factual grounding enforcement.

Option B is the correct solution because it uses native AWS governance, access control, and auditing capabilities to protect PII while enabling controlled FM access to authorized data subsets. AWS Lake Formation is designed specifically to manage fine-grained permissions for data lakes, including column-level access control, which is critical when handling sensitive financial and PII data.

LF-Tags allow data administrators to define scalable, attribute-based access control policies. By tagging databases, tables, and columns with business unit and Region metadata, the company can enforce policies that ensure the foundation model only accesses approved datasets with PII-redacted columns. This eliminates the risk of sensitive data leaking into production inference workflows.

IAM role-based authentication ensures that the FM accesses data using least-privilege credentials. This integrates cleanly with Amazon Bedrock, which supports IAM-based authorization for service-to-service access. AWS CloudTrail provides immutable audit logs for all access attempts, satisfying compliance and regulatory requirements.

Option A introduces unnecessary data duplication and weak governance controls. Option C relies on custom application logic, increasing operational risk and complexity. Option D bypasses Lake Formation’s fine-grained controls and relies on presigned URLs, which reduces governance visibility and control.

Therefore, Option B best meets the requirements for security, compliance, scalability, and auditability when integrating Amazon Bedrock with a Lake Formation–governed data lake.

Option B is the correct solution because it delivers end-to-end governance, security, and auditability across Amazon Bedrock, Amazon Rekognition, and the underlying data layer while meeting strict privacy and compliance requirements.

Using IAM attribute-based access control (ABAC) allows the company to control access to foundation models and data based on department, role, or workload attributes rather than static permissions. This is critical for controlling FM access patterns at scale. Enforcing specific ModelId and GuardrailIdentifier values with IAM condition keys ensures that only approved models and guardrails are used, which directly supports secure model I/O and governance requirements.

Configuring VPC endpoints for Amazon Bedrock ensures that all model invocations remain on private AWS network paths, reducing data exfiltration risk and supporting privacy standards. AWS CloudTrail captures both management and data events, providing a definitive audit trail of who accessed which resources and when. Sending logs to CloudTrail Lake enables centralized, long-term, queryable auditing across services.

Amazon S3 server access logging adds file-level visibility into video archive access, which is essential for compliance and forensic analysis. Amazon CloudWatch alarms provide near real-time detection of anomalous or unauthorized activity across Amazon Bedrock, Amazon Rekognition, and AWS KMS.

Option A focuses primarily on model-level tracing but lacks comprehensive IAM governance and S3 access auditing. Option C provides partial controls but lacks identity-aware auditing and model governance. Option D focuses on anomaly detection and classification but does not explicitly control FM access patterns.

Therefore, Option B best satisfies all stated requirements in a unified, auditable, and security-first architecture.

Option C is the correct solution because Amazon Bedrock guardrails are purpose-built to enforce defense-in-depth safety controls for GenAI applications with minimal operational overhead. Guardrails provide managed, policy-based enforcement that operates before prompts are sent to the foundation model and after responses are generated, which directly satisfies the requirement that PII must not be sent to the model and must not appear in outputs.

By configuring a sensitive information policy, the application can automatically detect and redact PII in user inputs and model responses without building custom preprocessing pipelines. This approach is more reliable and scalable than regex or prompt engineering techniques, which are brittle and error-prone for sensitive data handling.

The topic policy capability in Amazon Bedrock guardrails allows the bank to explicitly block investment advice topics, ensuring regulatory compliance. This policy-based approach is safer and more auditable than attempting to steer the model only through prompt instructions.

Using the Converse API enables structured, standardized interactions with the model and supports consistent logging of requests and responses. Enabling delivery logging and image logging to Amazon S3 ensures that all customer interactions, including documents and images, are captured in a durable, auditable storage layer. This directly supports compliance, regulatory audits, and forensic analysis.

Option A incorrectly relies on Amazon Macie, which is designed for data-at-rest discovery rather than real-time conversational filtering. Option B introduces custom Lambda pipelines and topic modeling, increasing operational complexity. Option D relies on regex and prompt engineering, which do not meet financial-grade compliance standards.

Therefore, Option C delivers the strongest security, governance, and auditability with the least operational effort.

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 C is the correct solution because it provides a secure, scalable, and standards-compliant way to expose an MCP server to an AI agent while enforcing strong user authorization. The Model Context Protocol supports HTTP-based transports for remote MCP servers, making Streamable HTTP the appropriate choice when the server is hosted as a managed service rather than a local process.

Hosting the MCP server in AWS Lambda enables automatic scaling and cost-efficient execution. By placing Amazon API Gateway in front of the Lambda function, the company creates a secure, managed HTTP endpoint that the AI agent can invoke reliably. This architecture cleanly separates transport, authentication, and business logic, which aligns with AWS serverless best practices.

Using Amazon Cognito to enforce OAuth 2.1 ensures that only authenticated and authorized users can access the MCP server. This satisfies security and compliance requirements when the MCP server handles sensitive user information. Cognito integrates natively with API Gateway, removing the need for custom authentication logic and reducing operational overhead.

Option A lacks user-level authorization controls. Option B and Option D rely on STDIO transport, which is intended for local or tightly coupled processes and is not suitable for distributed, serverless architectures. Option D also introduces security risks by handling credentials through environment variables.

Therefore, Option C best meets the requirements for secure access control, scalability, and correct MCP integration in an AWS-based AI agent architecture.

Option A is the correct solution because it provides proactive, model-aware token management with fine- grained visibility and alerting, which is required for regulated financial workloads. Amazon Bedrock currently exposes token usage metrics after invocation, but it does not natively enforce proactive, model-specific token limits across multiple applications or business units.

By implementing model-specific tokenizers in AWS Lambda, the company can estimate input and output token usage before sending requests to Amazon Bedrock. This enables early detection of requests that are approaching or exceeding model limits and allows the application to block, truncate, or reroute requests proactively rather than reacting to failures.

Publishing token usage metrics to Amazon CloudWatch enables real-time monitoring and alerting at scale, easily supporting more than 5,000 requests per minute. Storing detailed token usage data in Amazon DynamoDB allows the company to attribute usage and costs to specific applications, teams, or business units—an essential requirement for regulatory reporting and internal chargeback.

Option B is incorrect because Amazon Bedrock Guardrails do not currently provide token quota enforcement or proactive token alerts. Option C is reactive and only analyzes failures after they occur. Option D throttles requests but cannot enforce token-based limits or provide per-model cost attribution.

Therefore, Option A best satisfies proactive alerting, scalability, compliance reporting, and cost allocation requirements with acceptable operational effort.

Option A is the correct solution because it satisfies authentication, private connectivity, fine-grained authorization, and auditing using AWS-recommended patterns.

SAML federation between Microsoft Entra ID and IAM is a mature, well-supported integration that enables centralized enterprise authentication. Department-specific IAM roles allow precise control over which Bedrock ModelId values each department can invoke, enforcing access by model family.

Using AWS PrivateLink interface VPC endpoints for Amazon Bedrock runtime services ensures that all inference traffic stays on private AWS network paths, with no public internet exposure. NAT gateways and public endpoints, as used in other options, violate this requirement.

AWS CloudTrail provides authoritative audit logs of all Bedrock API calls, which is required for compliance. Amazon Bedrock model invocation logging complements CloudTrail by capturing detailed prompt and response metadata for deeper auditing and investigation.

Option B uses public endpoints via NAT. Option C incorrectly claims public endpoints can be private. Option D relies on IdP-side logs, which do not capture Bedrock API activity.

Therefore, Option A is the only solution that fully meets security, compliance, and observability requirements.

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 re trieving 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.

Alright, after comparing List B (txt file) against List A (Word file) , I have identified the unique questions. These questions cover scenarios or architectural configurations that were not present in the existing list.

Here are the unique questions from List B, formatted as requested:

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.

Options A and C provide the most AWS-native governance approach. Amazon Bedrock Prompt Management supports reusable parameterized prompts and explicit prompt versions, allowing teams to preserve approved configurations and deploy stable versions instead of uncontrolled working drafts. An organizational approval gate can therefore be applied before a new prompt version becomes production-approved. AWS CloudTrail records Amazon Bedrock API activity, including the identity making the request, the operation performed, time, source information, and other event details, providing the required audit trail for Bedrock resource modifications and use. CloudWatch can complement this with operational usage monitoring and reporting. Option B recreates prompt governance through S3, Lambda, and SNS. Option D uses general-purpose configuration storage rather than Bedrock-native prompt management. Option E adds substantial custom state and filtering logic without providing the same managed prompt-version lifecycle. AWS Documentation

================

Option B is the correct solution because Amazon Bedrock provisioned throughput is only used when the application explicitly invokes the provisioned model ARN, not the base foundation model ID. In the provided code, the application is calling the standard model identifier (anthropic.claude-v2), which routes requests to on-demand capacity instead of the purchased provisioned throughput.

When the CreateProvisionedModelThroughput API is used, Amazon Bedrock returns a provisioned model ARN that represents the reserved capacity. Applications must reference this ARN in the modelId parameter when invoking the model. If the base model ID is used instead, Bedrock treats the request as on-demand traffic, which explains why CloudWatch metrics show unused provisioned capacity alongside throttled on-demand requests.

Option A would increase capacity but would not fix the root cause because the application is not using the provisioned resource at all. Option C adds resiliency but does not ensure usage of provisioned throughput and would still incur throttling. Option D changes the response delivery mechanism but does not affect capacity routing.

Therefore, Option B directly resolves the throttling issue by correctly routing traffic to the reserved capacity and ensures that the company benefits from the provisioned throughput it has purchased.

Option B best fulfills all functional, scalability, and collaboration requirements by combining purpose-built AWS services with Amazon Bedrock capabilities. Amazon Bedrock Data Automation is designed to orchestrate large-scale, multimodal data processing pipelines and integrates naturally with foundation models for summarization and concept extraction. Using BDA to process document files ensures consistent preprocessing and model invocation at scale, which is essential for handling more than 10,000 sources per day with high concurrency.

Integrating Amazon Textract for PDFs enables accurate extraction of structured and unstructured text from scanned and digital documents, while Amazon Transcribe is the appropriate service for converting recorded videos into text for downstream semantic analysis. These services are optimized for their respective media types and feed clean, normalized inputs into Bedrock foundation models, improving the quality of contextual summaries.

Storing processed content in Amazon S3 with versioning enabled directly addresses the requirement for version control. S3 versioning provides immutable object history and rollback capabilities without additional complexity. Metadata storage in Amazon DynamoDB supports high-throughput, low-latency access patterns and scales automatically to handle peak upload concurrency.

Real-time collaboration is achieved through AWS AppSync GraphQL subscriptions combined with DynamoDB. AppSync enables real-time updates to connected clients whenever study materials are created or modified, making it well suited for collaborative editing and live synchronization. DynamoDB streams integrate seamlessly with AppSync to propagate changes efficiently.

The other options misuse services or fail to meet key requirements. Amazon SNS does not support collaborative state synchronization, Amazon DocumentDB is not optimized for versioned document storage, Amazon Neptune is unsuitable for document-centric workloads, and Amazon ElastiCache is not designed for durable storage or version control. Option B aligns with AWS best practices for scalable, multimodal generative AI systems built on 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 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.

Amazon Bedrock Prompt Management is the purpose-built service for prompt lifecycle management. it provides native version control , allowing developers to test and compare variants side-by-side. Use of parameterized variables ensures that a single prompt structure can be consistently reused across different sub-applications (assistants vs. graders) while still being tailored to the specific context. To " integrate into the main application " with minimal overhead, Amazon Bedrock Flows provide a managed orchestration layer. Flows allow developers to link managed prompts with AWS services (like knowledge bases or Lambda functions) without writing complex state-machine logic in Step Functions (Option B). This combination ensures consistent, auditable, and easily deployable prompt assets across the university ' s diverse use cases.

Option A best meets the requirements because it directly implements a Retrieval Augmented Generation pattern for conversational recommendations using managed Amazon Bedrock capabilities and a scalable vector store. The company’s source data already resides in Amazon S3, which aligns naturally with Amazon Bedrock Knowledge Bases ingestion workflows. A knowledge base can ingest book text, reviews, and metadata, generate embeddings using a supported embedding model, and persist those vectors in a purpose-built vector backend such as Amazon OpenSearch Service. This enables semantic retrieval that is well suited to conversation-driven intent, where user prompts are often descriptive and do not map cleanly to keyword filters.

The requirement to suggest books based on conversations implies the system must interpret natural language context and retrieve relevant passages, reviews, and metadata to ground the recommendation. Knowledge Bases provide managed orchestration for embedding creation and retrieval, which reduces development effort compared to building custom embedding pipelines. OpenSearch Service provides scalable vector search and k-nearest neighbors style similarity retrieval, which supports low-latency responses when properly indexed and sized.

For scaling to more than 10,000 concurrent users, the API layer design in option A is a common AWS pattern: Amazon API Gateway provides a managed front door with throttling and request handling, while AWS Lambda scales horizontally with demand and can invoke the knowledge base retrieval operations. This separates compute scaling from the vector store scaling and helps keep latency predictable under load.

Option B is not the best choice because DynamoDB is not the standard native vector store target for Amazon Bedrock Knowledge Bases in this context and would introduce additional implementation complexity around vector indexing and similarity search behavior. Option C requires substantial ML lifecycle work, model hosting, tuning, and continuous iteration to achieve quality recommendations at scale. Option D provides strong enterprise search, but it focuses on retrieval and FAQs rather than a managed RAG recommendation workflow grounded in embeddings and conversational context for generative responses.

Option C is the best answer because it implements a decoupled, queue-based moderation pipeline that invokes the expensive model only when the low-latency model is not confident enough. Amazon SQS is designed to decouple distributed application components and support asynchronous processing. AWS documentation describes SQS as a fully managed message queuing service that enables decoupling and scaling of microservices, distributed systems, and serverless applications. This matches the requirement for high resiliency and sudden demand spikes because incoming requests can be buffered in a durable queue rather than overwhelming the model-processing layer.

Using AWS Fargate to process queue messages is also appropriate because Fargate provides serverless container compute for Amazon ECS or Amazon EKS workloads. It allows the company to run scalable processing workers without managing EC2 capacity directly. AWS Prescriptive Guidance includes architectures that use API Gateway, Amazon SQS, and AWS Fargate to process events asynchronously, which supports the same decoupled processing model required in this question.

The two-stage queue design also optimizes cost. The small, low-latency classifier is used first for all requests. Only requests with confidence below 0.65 are placed into the second queue and processed by the larger model. This avoids running the larger model for every moderation request. High-confidence results can be completed quickly by the first-stage processor, while uncertain results are isolated into an asynchronous second-stage workflow.

Option A is incorrect because it synchronously calls the larger model for low-confidence results, which violates the requirement to process low-confidence requests asynchronously. Option B is incorrect because it invokes both models for every request, increasing cost and eliminating the benefit of confidence-based escalation. Option D requires managing EC2 instances and uses keyword heuristics instead of model confidence, so it is less resilient and less aligned with Bedrock-based moderation. Therefore, option C is correct.

Option C most completely satisfies the mandatory controls. A model-independent fairness classifier can evaluate every generated response at inference time, enforce a blocking threshold, preserve classifier scores and associated metadata for auditability, and route questionable cases for human compliance review without retraining the underlying FM. Option B provides automated blocking but omits the stronger audit metadata and regulatory-review workflow explicitly required by the scenario. Option A is insufficient because SageMaker Clarify can monitor bias and publish bias metrics, but scheduled offline or periodic analysis does not provide a non-bypassable control on every Bedrock response. Option D is inappropriate because AWS WAF matching operates primarily on HTTP request components and pattern-based conditions; detecting prohibited words is not equivalent to evaluating demographic fairness or semantic bias in generated investment guidance.

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 B is correct because the workload has predictable short peak periods, strict low-latency requirements, and lower demand between spikes. Amazon SageMaker Serverless Inference is designed for intermittent or unpredictable traffic because SageMaker manages the infrastructure and the customer pays based on usage rather than continuously running idle instances. AWS documentation describes serverless inference as suitable when traffic is intermittent or unpredictable and when users do not want to manage instances or scaling policies.

Provisioned concurrency is the key part of this answer. For latency-sensitive serverless inference workloads, provisioned concurrency keeps the required number of serverless instances initialized and ready to respond. AWS documentation states that SageMaker Serverless Inference integrates with Application Auto Scaling so provisioned concurrency can be scaled up or down based on a target metric or schedule. This fits a daily 2-hour peak window because the company can configure enough provisioned concurrency for 500 concurrent requests during peak periods and scale down when demand decreases.

Deploying each model to a separate serverless endpoint is also important. The categorization, extraction, and response-generation models likely have different memory, latency, and concurrency needs. Separate endpoints allow independent memory sizing, maximum concurrency configuration, monitoring, and scaling for each task. AWS API documentation also shows that serverless endpoint configuration includes maximum concurrency and provisioned concurrency settings, with provisioned concurrency required to be less than or equal to maximum concurrency.

Option A is less suitable because multi-model endpoints are usually best when many models can share infrastructure, but model loading and shared capacity can add latency risk. Option C assumes Amazon Bedrock provisioned throughput for models, but the company is developing specialized NLP models and needs task-specific deployment controls. Request batching can also add latency. Option D uses asynchronous inference, which is inappropriate for a less-than-500-ms synchronous response requirement. Therefore, option B best satisfies latency, concurrency, accuracy isolation, and resource optimization.

==========

Amazon Bedrock AgentCore Gateway is specifically designed to expose existing APIs, Lambda functions, services, and MCP servers to agents through a standardized Model Context Protocol interface. AWS documents that Gateway can transform REST APIs represented by OpenAPI specifications into MCP-compatible tools and provide agents with a unified endpoint for tool discovery and invocation. This directly satisfies the requirement to add or expose warehouse, shipping, and customs capabilities through MCP without repeatedly modifying agent integration code.

AWS Step Functions is appropriate for deterministic workflow orchestration. Task states can represent individual reasoning or tool-execution stages, while built-in Retry configuration supports IntervalSeconds , MaxAttempts , and BackoffRate . These settings provide controlled retries with exponential backoff and a defined maximum retry budget rather than requiring bespoke retry code. AWS explicitly documents MaxAttempts as the mechanism that stops retry behavior after the configured limit is reached.

A Choice state supplies deterministic conditional routing. The shipment value can be evaluated and requests above $100,000 can be sent to an approval branch. The approval task can use the Step Functions callback/task-token integration, which pauses workflow execution until an external process—such as a human approval system—returns success or failure. AWS specifically identifies human approval as a callback-task use case.

D is weaker because critical retry and approval policy should not depend solely on probabilistic orchestration prompts. E and G introduce unnecessary custom operational logic. F misuses Guardrails: Bedrock Guardrails governs model input/output safety and policy filtering; it is not a general-purpose human workflow orchestrator for shipment authorization.

==========

Option A is the appropriate AWS-native approach because it keeps the authoritative documents in an Amazon S3 bucket located in the regulated Region while using managed Amazon Bedrock foundation-model infrastructure instead of maintaining containerized models. Amazon Bedrock supports private connectivity through AWS PrivateLink interface VPC endpoints. Applications inside the VPC can therefore reach Bedrock privately without requiring an internet gateway, NAT gateway, public IP address, or public internet path.

Amazon Bedrock Knowledge Bases can use Amazon S3 as a RAG data source. AWS requires the S3 bucket used by a knowledge base to be in the same Region as the Amazon Bedrock knowledge base. During ingestion, source content is converted into vector embeddings and stored in the configured vector store so similarity-based retrieval can locate relevant passages for augmentation. This creates an AWS-managed RAG architecture while preserving explicit regional placement of the underlying source documents.

Option B introduces AWS Outposts unnecessarily. More importantly, AWS documentation states that S3 on Outposts object data physically remains on the Outpost and “is not in an AWS Region.” That conflicts with a requirement written specifically as keeping data within a particular AWS Region and also introduces additional infrastructure and operational cost.

C fails because “a Region close to” the regulated Region does not meet a requirement for the specified Region. Encryption does not override residency requirements. D requires the company to deploy and operate foundation-model containers, directly contradicting the objective of minimizing model infrastructure and maintenance.

Therefore, regional S3 storage combined with privately accessed managed Amazon Bedrock services provides the closest match to the stated residency, RAG, cost, and operational requirements.

==========

AWS Glue Data Catalog and its associated crawlers are the standard AWS tools for automatic discovery and centralized cataloging of datasets. For the generated summaries, storing them in Amazon S3 allows the use of object tags for metadata (like source IDs), making them easily queryable. The critical requirement for " tamper-evident, immutable audit logs " is met by enabling Bedrock model invocation logging to an S3 bucket protected by S3 Object Lock (compliance mode). To further guarantee that logs have not been altered, AWS CloudTrail log file integrity validation uses cryptographic hashes to provide non-repudiation and a verifiable audit trail. This combination covers data management, metadata attribution, and high-standard security compliance.

The correct answers are B and C because they directly address hallucination reduction while maintaining high throughput and low latency.

Option B reduces hallucinations at their source by grounding model outputs in verified content through Retrieval Augmented Generation (RAG). Using an Amazon Bedrock knowledge base with semantic chunking ensures that long technical documents are broken into meaningfully coherent sections. This allows the model to retrieve only the most relevant chunks, rather than processing an entire document in one pass, which significantly improves factual accuracy and reduces cognitive overload on the model. This approach scales efficiently and supports processing more than 1,000 documents per hour.

Option C adds a defense-in-depth safety layer by using Amazon Bedrock guardrails to detect and block hallucination-like output patterns. Guardrails operate at inference time with minimal performance overhead, making them suitable for low-latency requirements. While guardrails do not eliminate hallucinations entirely, they effectively prevent unsafe or clearly fabricated outputs from reaching users.

Option A increases latency and cost due to explicit reasoning steps and does not scale well for high-throughput workloads. Option D increases randomness and worsens hallucinations. Option E repeats the existing flawed approach.

Therefore, Options B and C together provide scalable grounding and runtime protection that meet accuracy, performance, and throughput requirements.

Option C is the best answer because the scenario is centered on a foundation-model GenAI application that needs explainability, fairness iteration, and responsible AI controls inside an Amazon Bedrock workflow. Amazon Bedrock Agents support tracing, and AWS documentation states that traces can show the agent’s path from user input to response, including action group inputs and outputs, knowledge base queries, and the reasoning the agent uses to decide which action or query to take. AWS also describes trace data as a way to understand how an agent arrived at a response. This directly addresses clinicians’ need to review diagnostic reasoning and decision flow.

Amazon Bedrock Guardrails are also the right service for policy compliance in GenAI applications. AWS documentation states that Guardrails can implement safeguards aligned with responsible AI policies, configure denied topics, filter harmful content, and remove sensitive information. For healthcare and life sciences GenAI use cases, AWS Prescriptive Guidance recommends evaluating bias, fairness, and hallucinations and implementing guardrails to prevent harmful responses. This supports strict governance and privacy-sensitive clinical workflows.

The prompt testing and A/B testing component supports rapid iteration. AWS guidance for generative AI operations recommends prompt template management, creating and testing prompt variants, using A/B testing workflows for prompt variants, and analyzing performance against metrics. This is relevant for testing fairness behavior across demographic prompt sets and clinical scenarios.

Option A includes SageMaker Clarify, which is useful for bias detection and model explainability, but it is less directly aligned to Bedrock-native real-time tracing and policy enforcement for an FM application. Option B handles medical text extraction and terminology but not reasoning transparency or governance. Option D provides operational metrics and custom reports, but not native Bedrock reasoning traces or guardrails. Therefore, option C best meets the GenAI governance requirements.

==========

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.

Option C is the correct solution because it provides near real-time monitoring, hallucination detection, and cost anomaly awareness using built-in Amazon Bedrock and Amazon CloudWatch capabilities, with minimal custom development.

By configuring Amazon Bedrock invocation logging with text output logging, the company captures detailed prompt and response data for auditing and analysis without building custom logging pipelines. This data is stored in Amazon S3, providing durable storage for compliance and retrospective investigation.

Using Amazon Bedrock guardrails with contextual grounding checks allows the application to automatically detect hallucinations by verifying whether generated summaries are grounded in the provided clinical documents. This is the AWS-recommended approach for hallucination detection in RAG and summarization workloads and avoids the need to maintain custom evaluation models or pipelines.

Creating Amazon CloudWatch anomaly detection alarms for InputTokenCount and OutputTokenCount metrics enables automatic detection of abnormal token usage patterns that often correlate with runaway prompts, inefficient summarization, or prompt injection attempts. Anomaly detection adapts dynamically to usage trends, making it more effective than static thresholds for early cost warnings.

Option A introduces batch analytics with Glue and Athena, which is not near real time and increases operational overhead. Option B requires managing evaluation jobs and Lambda-based notification logic. Option D focuses on infrastructure-level monitoring and offline dashboards rather than near real-time GenAI quality and cost signals.

Therefore, Option C best meets the requirements with the least operational effort and maintenance overhead.

Amazon Bedrock Knowledge Bases is designed specifically for managed retrieval-augmented generation. A knowledge base connects source repositories to an embedding model and vector store. During ingestion, source content is transformed into numerical vector embeddings. At retrieval time, the query is similarly represented so the knowledge base can compare semantic similarity and return passages that are conceptually relevant rather than depending exclusively on exact keyword matches.

Amazon Bedrock supports managed data-source connectors for multiple repositories. The AWS documentation lists Amazon S3, Confluence, Microsoft SharePoint, Salesforce, web crawling, and custom data sources among supported connection patterns. These connectors reduce the amount of ingestion, crawling, and synchronization code an organization needs to maintain.

For Atlassian Confluence specifically, Bedrock can crawl supported Confluence content and supports incremental synchronization for added, modified, or deleted material. Current managed Confluence integration also supports crawling pages, blog posts, and attachments, subject to the documented connector limitations.

This architecture supplies the retrieval layer needed to augment an FM with source-grounded context. It centralizes retrieval semantics while letting the application use Bedrock ' s managed ingestion and retrieval capabilities instead of implementing its own embedding pipelines.

B explicitly uses keyword-oriented mappings and therefore does not meet the semantic-search requirement. C could technically implement RAG, but Lambda-based embedding generation, synchronization, and custom retrieval logic create precisely the operational burden the company wants to avoid. D is not an appropriate semantic RAG architecture because ordinary DynamoDB queries do not automatically produce vector-based semantic retrieval from unstructured documentation.

For an internal wiki not covered by a built-in connector, the knowledge-base custom data-source capability can be used while keeping the overall retrieval interface centralized. Therefore, A provides the closest fit to every stated architectural requirement.

==========

Option C is correct because Amazon Bedrock agent tracing exposes the internal execution path needed to identify precisely where a multi-step workflow fails. When tracing is enabled for InvokeAgent, the response can include structured trace events. AWS documents OrchestrationTrace for orchestration activity and FailureTrace for the reason a particular step failed. Those records can be aggregated to calculate per-step attempts, successes, failures, and completion rates. Option A monitors broad client/server error metrics; even with custom metrics, it does not inherently provide the same structured execution context. Option B uses CloudTrail, which is primarily an API audit trail rather than a step-by-step agent reasoning trace. Option D requires custom EventBridge instrumentation and storage. Native agent trace data therefore provides the most direct evidence for exact failure-point analysis and detailed workflow completion analytics. AWS Documentation

================