AIP-C01 Questions and Answers

The correct combination is C and D because together they enforce centralized governance over both model access and prompt content controls , which are the two core requirements of the scenario.

To ensure employees can use only approved Amazon Bedrock models , governance must be enforced at the organization level and not rely on individual application logic. Service Control Policies (SCPs) are the strongest control mechanism available in AWS Organizations because they define the maximum permissions an account or principal can have. In option C , the SCP prevents any Amazon Bedrock model invocation unless a centrally approved guardrail identifier is specified. This ensures that guardrails are always enforced, regardless of how or where the invocation originates. The additional use of IAM permissions boundaries ensures that even within allowed accounts, employees are restricted to invoking only explicitly approved foundation models.

To prevent specific topics and proprietary information from being included in prompts , Amazon Bedrock Guardrails must be used. Guardrails operate inline during model invocation and can block disallowed content before it is processed by the model. Option D correctly specifies a block filtering policy , which is appropriate when content must be prevented entirely rather than partially redacted. Deploying the guardrail using AWS CloudFormation StackSets allows the company to centrally manage and consistently deploy the same guardrail configuration across all accounts in the organization, ensuring uniform enforcement.

Option E uses mask filtering, which is better suited for redacting sensitive output rather than preventing prohibited content from being submitted in prompts. Option B attempts to use SCPs alone but does not enforce guardrail deployment or content filtering. Option A incorrectly places guardrail enforcement in permissions boundaries, which are not designed to validate request parameters such as guardrail identifiers.

By combining SCP-based enforcement with centrally deployed Bedrock guardrails , options C and D together provide strong, scalable, and centrally managed controls for both content safety and model governance across the organization.

Option B best meets the multimodal, ethical, and auditability requirements using managed AWS services designed for research-grade GenAI systems. Multimodal data such as audio, video, sensor telemetry, and tracking data must be curated and summarized before being consumed by a foundation model. Amazon SageMaker Processing and Amazon Transcribe provide scalable, managed preprocessing for audiovisual and textual data.

By ingesting summarized, validated observations into Amazon Bedrock Knowledge Bases, the GenAI assistant can answer natural language queries using grounded, evidence-based context instead of raw sensor signals. This significantly reduces the risk of speculative or anthropomorphic interpretations.

Amazon Bedrock guardrails are critical for preventing speculative behavioral claims, enforcing scientific and ethical constraints at inference time. Guardrails provide a validated, auditable safety layer that custom Lambda-based filters cannot reliably replicate.

AWS AppConfig enables controlled prompt management and change governance, ensuring that research prompts remain consistent and reviewable. AWS CloudTrail captures all access, query, and configuration changes, supporting ethical research audits and regulatory reviews.

Option A lacks grounding and speculative safeguards. Option C focuses on text analytics and does not properly handle multimodal reasoning or safety enforcement. Option D relies heavily on custom logic and introduces unnecessary operational risk.

Therefore, Option B provides the most robust, ethical, and auditable GenAI architecture for wildlife behavior research.

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 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 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.

The correct answers are A and D because they collectively satisfy the requirements for structured inputs, consistent output formatting, and non-blocking detection of bullying language.

Option A is required because Amazon Bedrock Prompt Management enables prompt templates with explicit input variables and defined output formats. By defining the four required inputs as variables, the company ensures that every invocation of the Amazon Nova Pro FM receives the correct structured inputs. Specifying the output format ensures consistent responses, which is essential for a grants application workflow. Adding the managed prompt to the prompts node of the flow allows Bedrock Flows to invoke the model using this standardized configuration.

Option D addresses the requirement to receive notifications when bullying language is detected without blocking responses. Amazon Bedrock guardrails support content filters with configurable actions. By applying the insults content filter and setting the response action to detect, the system flags responses containing bullying or insulting language while still allowing the response to be returned. This enables monitoring, alerting, and auditing without interrupting application functionality.

Option B is incorrect because setting the filter response to block contradicts the requirement not to block all flagged responses. Option C introduces a prompt router, which is unnecessary because the application uses a single Amazon Nova Pro FM. Option E incorrectly attempts to enforce input variables and output formatting through an inference profile, which does not provide prompt-level variable enforcement or formatting guarantees.

Therefore, A and D together provide structured prompt management and non-blocking safety detection with minimal operational complexity.

Option B is correct because the application is currently invoking the base foundation model identifier, which routes traffic to the on-demand capacity pool rather than the company’s purchased provisioned throughput. In Amazon Bedrock, provisioned throughput is attached to a specific provisioned resource created through the provisioned throughput APIs. To consume that reserved capacity, inference requests must target the provisioned resource identifier that represents the purchased throughput, not the generic model identifier used for on-demand inference.

The code snippet uses modelId= " anthropic.claude-v2 " . This value selects the on-demand endpoint for that model. As a result, requests are subject to on-demand quotas and throttling behavior, while the provisioned throughput remains idle. This directly explains the CloudWatch observation: provisioned capacity metrics show unused capacity because no traffic is being directed to the provisioned resource, and the on-demand path is throttling because it is exceeding the applicable on-demand limits during peak volume.

Replacing the modelId value with the provisioned throughput ARN returned by the CreateProvisionedModelThroughput workflow ensures the runtime invocation is routed to the reserved capacity. Once traffic is directed correctly, the purchased model units provide the consistent throughput required for predictable performance during business hours, which is exactly why provisioned throughput is used.

Option A could increase capacity, but it does not fix the core issue that the application is not using the provisioned resource at all. Option C can reduce the impact of throttling temporarily, but it adds latency and does not guarantee consistent throughput; it also still wastes the provisioned capacity. Option D changes the response delivery mechanism, but throttling is a capacity routing and quota issue, not a streaming API issue.

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 C best satisfies the requirement to change routing decisions without redeploying code while supporting complex, frequently changing business logic at scale. AWS AppConfig is designed for centrally managing dynamic configuration (feature flags, rules, thresholds, and policy parameters) and deploying changes safely. It supports controlled deployments, validation, and rapid propagation of updated configuration values, which aligns with “real-time cost metrics that change hourly” and the need for “immediate propagation across thousands of concurrent requests.”

In this design, the Lambda function becomes the policy decision point. For each request, it evaluates user attributes (tier, transaction value), context (regulatory zone, Region), and live cost/performance thresholds stored in AppConfig to determine which Amazon Bedrock FM to invoke. Because the routing rules and FM identifiers are delivered as configuration, the company can switch models, adjust A/B testing weights, or update compliance routing rules by deploying new AppConfig configuration versions rather than pushing new application code. This reduces operational risk and accelerates iteration.

Exposing a single API Gateway endpoint also minimizes client complexity and keeps routing logic server-side, which is important when rules change frequently. Lambda can cache configuration between invocations (within the execution environment) to reduce repeated fetch overhead while still picking up changes quickly, enabling both low latency and rapid rule rollout under high concurrency.

Option A relies on Lambda environment variables, which are not intended for frequent real-time updates and typically require function configuration updates that are slower and operationally brittle. Option B uses mapping templates and stage variables, which are limited for complex rule evaluation and safe rollout patterns. Option D misuses authorizers for business routing, adds extra latency and complexity, and complicates observability and error handling by splitting decisioning from execution.

Option B is the correct solution because it leverages native Amazon Bedrock intelligent prompt routing, which is specifically designed to reduce cost and complexity in multi-model GenAI architectures. Intelligent prompt routing automatically analyzes incoming prompts and selects the most appropriate foundation model based on prompt characteristics and complexity—without requiring custom classification logic or orchestration code.

This approach directly meets the requirement for least implementation effort. The company does not need to deploy additional Lambda functions, maintain routing rules, or manage separate classification stages. Routing decisions are handled by Bedrock, which simplifies architecture and reduces operational risk.

By routing the majority (70%) of simple product inquiries to smaller, lower-cost models, the company minimizes inference cost and latency. More complex return policy inquiries are automatically routed to larger models that provide better reasoning capabilities, preserving response quality and customer satisfaction.

Because routing is handled inline by Bedrock, response latency remains low compared to multi-stage architectures that require an additional classification model call before inference. This is critical for customer service scenarios where responsiveness directly impacts satisfaction.

Option A introduces additional inference steps and custom logic. Option C increases cost by overusing a mid-sized model for all queries. Option D relies on brittle keyword rules and increases operational overhead through endpoint management.

Therefore, Option B delivers the optimal balance of cost efficiency, performance, and simplicity for dynamic model selection in Amazon Bedrock.

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 C best meets the requirements by combining native Amazon Bedrock logging with adaptive monitoring and minimal operational overhead. Amazon Bedrock model invocation logging can be sent directly to CloudWatch Logs, where detailed fields such as InputTokenCount, OutputTokenCount, and tool invocation metadata are captured for each request.

CloudWatch metric filters allow extraction of structured metrics from logs, including tool-specific token consumption patterns. By defining filters per tool integration, the company can isolate which tools are responsible for increased token usage without building custom log-processing pipelines.

CloudWatch anomaly detection provides automatic baseline modeling and dynamic thresholds based on historical traffic patterns. Unlike static alarms, anomaly detection adapts as usage evolves, making it ideal for applications with changing workloads or seasonal usage patterns. This directly satisfies the requirement to automatically adjust thresholds as traffic patterns change.

When abnormal token consumption occurs, anomaly detection alarms trigger immediately, enabling rapid investigation and remediation. Because this solution uses fully managed AWS services without custom analytics jobs or manual threshold tuning, it significantly reduces operational effort.

Option A fails to adapt to changing patterns. Option B introduces batch analysis and delayed insights. Option D requires manual intervention and custom code, increasing maintenance burden.

Therefore, Option C provides the most scalable, adaptive, and low-maintenance solution for monitoring and controlling token consumption in Amazon Bedrock–based applications.

Option B is the most appropriate solution because it uses AWS-native, purpose-built data engineering and governance services to address data quality validation, metadata creation, monitoring, and transformation with minimal custom development. AWS Glue is designed specifically for large-scale data preparation and integrates seamlessly with Amazon S3, making it ideal for preprocessing unstructured datasets for downstream GenAI applications.

AWS Glue crawlers automatically infer schemas and populate the AWS Glue Data Catalog, creating auditable, queryable metadata for all datasets. This satisfies the requirement for traceability and governance, which is especially critical in financial services environments. Glue ETL jobs allow teams to implement customizable transformation logic, including text normalization and chunking strategies optimized for foundation model context windows.

AWS Glue Data Quality provides built-in rulesets for validating completeness, accuracy, and consistency. It also publishes quality metrics that can be monitored over time, meeting the requirement for ongoing data quality monitoring without building custom validation frameworks.

Because AWS Glue is fully managed, it eliminates the need to manage infrastructure, scaling, or orchestration. This significantly reduces development and operational effort compared to custom Lambda pipelines or EC2-based processing. The processed and validated data can then be safely ingested into Amazon Bedrock workflows or knowledge bases.

Option A and C require custom logic for validation, monitoring, and chunking, increasing development complexity. Option D introduces unnecessary infrastructure management and services not optimized for data preprocessing.

Therefore, Option B best meets the requirements while minimizing development effort and aligning with AWS Generative AI data preparation best practices.

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

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

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

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

Option D is the best fit because it implements a reliable event-driven MLOps workflow that automates retraining and redeployment with clear orchestration, auditability, and production-grade error handling. The requirement is explicit: whenever a new file is uploaded to Amazon S3, the system must retrain and then redeploy the model used by a web application. A common AWS pattern is to use an S3 event notification to trigger an AWS Lambda function, which then starts a controlled workflow. In option D, Lambda serves as the event handler that reacts immediately to the S3 upload event and passes the necessary context (bucket, object key, dataset version) into an AWS Step Functions Standard state machine.

Step Functions Standard is appropriate for model retraining pipelines because training and deployment steps can be long-running and benefit from durable state, retries, and failure handling. It provides execution history, making it easier to troubleshoot why a particular retraining run failed and to prove which dataset version produced which model version. This operational visibility is critical when the dataset is “growing rapidly” and retraining is frequent.

Within the workflow, Amazon SageMaker Pipelines is the right service to run the ML lifecycle stages in a repeatable way: data processing (if needed), training, evaluation/quality checks, mod el registration, and deployment to an endpoint used by the application. SageMaker Pipelines is purpose-built for CI/CD-style ML, supporting automated redeployments when a new approved model artifact is produced. By calling a pipeline execution from Step Functions, the company can add governance gates (for example, only deploy if evaluation metrics meet thresholds), and can apply consistent rollback and notification steps when deployment fails.

The other options are weaker: A confuses inference with retraining and does not provide deployment orchestration. B adds unnecessary webhook complexity and describes an awkward event bus configuration. C introduces Autopilot/Data Wrangler, which may be useful but adds extra moving parts and is not required to meet the trigger-and-redeploy requirement.

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 C is the correct solution because it uses Amazon Bedrock cross-Region inference profiles, which are explicitly designed to support regional data residency, private connectivity, and resilience with minimal operational overhead.

By using a Europe-scoped inference profile, the application ensures that all inference requests are routed only within European Regions where the FM is deployed, such as eu-central-1 and eu-west-3. This satisfies data residency requirements while still providing resilience and load distribution across Regions.

Configuring an Amazon Bedrock VPC endpoint ensures that all traffic remains on the AWS private network. No public endpoints are used, which aligns with the company’s private networking requirements.

Extending existing SCPs to allow inference profile usage ensures that employees can access the FM only in approved Regions, maintaining governance across the Control Tower environment.

Options A and B introduce unnecessary custom routing layers and EC2 management. Option D moves away from Amazon Bedrock entirely and increases operational complexity.

Therefore, Option C is the only solution that satisfies private access, regional confinement, governance controls, and low operational overhead.

Option C is the correct solution because it uses a single, well-tuned Amazon Bedrock guardrail that applies different actions to different content types, which is the recommended approach for minimizing false positives while enforcing strong policy controls.

Setting content filters to medium rather than high reduces overblocking of benign customer conversations while still preventing harmful content. Amazon Bedrock guardrails are designed to balance precision and recall, and medium sensitivity is commonly recommended for customer-facing financial services use cases.

Denied topics explicitly prevent the assistant from discussing investment advice, which is a regulatory requirement. Including definitions and sample phrases improves detection accuracy and reduces ambiguity.

Sensitive information filters support different actions per context. Masking PII in responses preserves conversational usefulness for legitimate customer support while preventing exposure of sensitive data. Blocking sensitive financial information in inputs prevents downstream processing of disallowed content before it reaches the foundation model.

Critically, enabling both input and output evaluation ensures that guardrails are applied consistently at every stage of interaction. Custom blocked messages and audit logging provide clear compliance evidence for regulators and internal audits.

Option A causes excessive false positives by blocking all PII outright. Option B introduces unnecessary complexity and is not how Bedrock guardrails are intended to be applied. Option D uses orchestration logic that Bedrock guardrails already handle natively.

Therefore, Option C best satisfies enforcement, flexibility, auditability, and accuracy requirements.

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 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.

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.

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.

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 B is the only solution that satisfies all strict real-time, streaming, and latency requirements. Amazon Transcribe streaming with partial results allows transcription fragments to be delivered before the speaker finishes a sentence. This significantly reduces perceived latency and enables downstream processing to begin immediately, which is essential for maintaining sub-1-second end-to-end response times.

Using Amazon Bedrock’s InvokeModelWithResponseStream API enables token-level or chunk-level streaming responses from the foundation model. This allows the GenAI assistant to begin delivering suggestions to call center agents incrementally instead of waiting for a full model response. This streaming inference capability is critical for interactive, real-time agent assistance use cases.

Amazon API Gateway WebSocket APIs provide fully managed, bidirectional communication between backend services and agent dashboards. This ensures that updates flow continuously to agents as new transcription fragments and model outputs become available, preserving real-time responsiveness without requiring custom socket infrastructure.

Option A introduces additional synchronous processing layers and storage writes that increase latency. Option C uses batch transcription and post-call processing, which cannot meet real-time requirements. Option D uses embeddings and asynchronous messaging, which are not suitable for live incremental suggestions and bidirectional streaming.

Therefore, Option B best aligns with AWS real-time GenAI architecture patterns by combining streaming transcription, streaming model inference, and managed bidirectional communication while maintaining low latency and operational simplicity.

Option B best satisfies the requirements because it directly applies Retrieval Augmented Generation principles using managed Amazon Bedrock Knowledge Bases, which are designed to handle large, complex documents while preserving contextual relationships. Financial reports often interleave tables with explanatory narrative, and accurate analysis depends on keeping those elements logically connected. By segmenting documents based on their structural layout —for example, sections, subsections, tables, and surrounding commentary—the knowledge base can retrieve semantically relevant chunks that maintain this relationship during inference.

Amazon Bedrock Knowledge Bases support contextual chunking strategies that go beyond simple fixed-size segmentation. This is critical for financial documents, where a metric in a table may be explained in adjacent paragraphs or footnotes. Context-aware chunking ensures that retrieved content includes both the numeric data and its interpretation, enabling the foundation model to generate accurate, grounded responses. Including citations further improves analyst trust and auditability by allowing users to trace answers back to specific source sections, which is a common requirement in financial environments.

Scalability is another key requirement. Knowledge Bases manage embedding generation, indexing, and retrieval orchestration as a managed service, which allows the solution to scale across large document collections without requiring custom infrastructure or model hosting. This approach also supports efficient updates as new quarterly reports are added, ensuring the retrieval layer remains current.

Option A does not scale well because processing entire 5–100 page documents in a single prompt increases token usage, latency, and cost while risking context truncation. Option C relies on fixed-size chunking triggered at query time, which often breaks semantic relationships in structured financial content. Option D introduces unnecessary architectural complexity by splitting structured and unstructured data into separate applications, increasing operational overhead without providing better contextual retrieval than a unified RAG approach.

Option B is the correct solution because legal research workloads require both semantic understanding and exact lexical precision, especially for statutes, citations, and domain-specific terminology. A hybrid search architecture directly addresses this need by combining vector similarity search with traditional keyword-based retrieval.

Vector search alone is often insufficient for legal research because exact phrases, citation formats, and jurisdiction-specific terms must be matched precisely. Keyword search ensures high recall and precision for citations and legal terms, while vector search captures deeper semantic relationships between legal concepts, precedents, and arguments. Amazon OpenSearch Service natively supports hybrid search, enabling efficient scoring and ranking without external orchestration.

Applying an Amazon Bedrock reranker model further improves relevance by reordering retrieved documents based on deeper contextual understanding. Reranking is especially valuable in legal research because multiple documents may appear relevant, but only a subset truly addresses the user’s legal question. The reranker optimizes final results before they are passed to the Anthropic Claude FM, improving answer accuracy and reducing hallucinations.

Option A relies on default vector search, which does not reliably handle citations and exact terminology. Option C focuses on query suggestions and post-processing rather than retrieval quality. Option D introduces unnecessary operational complexity by merging results across multiple systems.

Therefore, Option B best meets the requirements for precision, performance, and semantic understanding in a legal research AI assistant.

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

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

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

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

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

Option B is the 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.