Black Friday Doorbuster Deal - Flat 75% Off - Ends in 0d 00h 00m 00s - Coupon code: 75brite

ExamsBrite Dumps

AWS Certified Generative AI Developer - Professional Question and Answers

AWS Certified Generative AI Developer - Professional

Last Update Nov 16, 2026
Total Questions : 161

We are offering FREE AIP-C01 Amazon Web Services exam questions. All you do is to just go and sign up. Give your details, prepare AIP-C01 free exam questions and then go for complete pool of AWS Certified Generative AI Developer - Professional test questions that will help you more.

AIP-C01 pdf

AIP-C01 PDF

$27.5  $109.99
AIP-C01 Engine

AIP-C01 Testing Engine

$32.5  $129.99
AIP-C01 PDF + Engine

AIP-C01 PDF + Testing Engine

$42.5  $169.99
Questions 1

A company is creating a generative AI (GenAI) application that uses Amazon Bedrock foundation models (FMs). The application must use Microsoft Entra ID to authenticate. All FM API calls must stay on private network paths. Access to the application must be limited by department to specific model families. The company also needs a comprehensive audit trail of model interactions.

Which solution will meet these requirements?

Options:

A.  

Configure SAML federation between Microsoft Entra ID and AWS Identity and Access Management. Create department-specific IAM roles that allow only the required ModelId values. Create AWS PrivateLink interface VPC endpoints for Amazon Bedrock runtime services. Enable AWS CloudTrail to capture Amazon Bedrock API calls. Configure Amazon Bedrock model invocation logging to record detailed model interactions.

B.  

Create an identity provider (IdP) connection in IAM to authenticate by using Microsoft Entra ID. Assign department permission sets to control access to specific model families. Deploy AWS Lambda functions in private subnets with a NAT gateway for egress to Amazon Bedrock public endpoints. Enable CloudWatch Logs to capture model interactions for auditing purposes.

C.  

Create a SAML identity provider (IdP) in IAM to authenticate by using Microsoft Entra ID. Use IAM permissions boundaries to limit department roles ' access to specific model families. Configure public Amazon Bedrock API endpoints with VPC routing to maintain private network connectivity. Set up CloudTrail with Amazon S3 Lifecycle rules to manage audit logs of model interactions.

D.  

Configure OpenID Connect (OIDC) federation between Microsoft Entra ID and IAM. Use attribute-based access control to map department attributes to specific model access permissions. Apply SCP policies to restrict access to Amazon Bedrock FM families based on department. Use Microsoft Entra ID ' s built-in logging capabilities to maintain an audit trail of model interactions.

Discussion 0
Questions 2

A multinational bank wants to implement a RAG solution on AWS to run queries on internal policy and compliance documents. To comply with data residency regulations, the company must ensure that critical customer data remains within a specific AWS Region. The bank wants to use foundation models (FMs) on AWS to reduce infrastructure costs and minimize model maintenance.

Which solution will meet these requirements?

Options:

A.  

Store critical customer data in a dedicated Amazon S3 bucket in the regulated Region. Configure Amazon Bedrock to directly access the documents through a VPC endpoint. Perform all RAG retrieval on AWS.

B.  

Store critical customer data locally by using AWS Outposts in the regulated Region. Create embeddings locally in a secure vector store. Use Amazon Bedrock to orchestrate LLMs on AWS by using only retrieved context.

C.  

Store critical customer data in a private Amazon OpenSearch Service cluster in a Region that is close to the regulated Region. Configure end-to-end encryption. Use an LLM on AWS to retrieve and summarize the data dynamically without storing embeddings locally.

D.  

Containerize FMs on Amazon ECS in the regulated Region. Ingest critical customer data into the containerized FMs. Perform RAG queries entirely inside the container.

Discussion 0
Questions 3

A global healthcare company is deploying a GenAI application on Amazon Bedrock to produce treatment recommendations. Regulations vary for each country where the company operates. Some countries require the company to retain all model inputs and outputs for 2 years. Other countries require the company to submit data for local audits only. Medical providers require consistent medical terminology across all locations. However, the treatment recommendations that the model produces must adapt to local patient demographics. The solution must also integrate with existing electronic health record (EHR) systems. The application must support up to 10,000 healthcare provider queries every day with sub-second response times. The company must be able to review the application before deployments and approve of prompt changes. The application must produce comprehensive logs for prompts, responses, and user context. Which solution will meet these requirements?

Options:

A.  

Use AWS CloudTrail to log API calls. Create standard prompts in Amazon Bedrock Prompt Management that include variables for patient demographics. Implement IAM policies to ensure that only approves users can access prompts.

B.  

Use Amazon CloudWatch Logs to collect detailed model invocation logs. Store the logs in Amazon S3. Create parameterized prompts in Amazon Bedrock Prompt Management that include variables for treatment options. Enable prompt versioning and set up an approval workflow.

C.  

Create AWS Lambda functions to dynamically generate prompts that enforce clinical language requirements. Use Amazon CloudWatch Logs to track model invocations. Use Amazon SQS queues to implement a prompt approval workflow.

D.  

Store prompt templates in Amazon S3. Use S3 Object Lock to implement version control. Use Amazon EventBridge to track model invocations. Use AWS Config to monitor changes to prompt templates.

Discussion 0
Questions 4

A GenAI developer is evaluating Amazon Bedrock foundation models (FMs) to enhance a Europe-based company ' s internal business application. The company has a multi-account landing zone in AWS Control Tower. The company uses Service Control Policies (SCPs) to allow its accounts to use only the eu-north-1 and eu-west-1 Regions. All customer data must remain in private networks within the approved AWS Regions.

The GenAI developer selects an FM based on analysis and testing and hosts the model in the eu-central-1 Region and the eu-west-3 Region. The GenAI developer must enable access to the FM for the company ' s employees. The GenAI developer must ensure that requests to the FM are private and remain within the same Regions as the FM.

Which solution will meet these requirements?

Options:

A.  

Deploy an AWS Lambda function that is exposed by a private Amazon API Gateway REST API to a VPC in eu-north-1. Create a VPC endpoint for the selected FM in eu-central-1 and eu-west-3. Extend existing SCPs to allow employees to use the FM. Integrate the REST API with the business application.

B.  

Deploy the FM on Amazon EC2 instances in eu-north-1. Deploy a private Amazon API Gateway REST API in front of the EC2 instances. Configure an Amazon Bedrock VPC endpoint. Integrate the REST API with the business application.

C.  

Configure the FM to use cross-Region inference through a Europe-scoped endpoint. Configure an Amazon Bedrock VPC endpoint. Extend existing SCPs to allow employees to use the FM through inference profiles in Europe-based Regions where the FM is available. Use an inference profile to integrate Amazon Bedrock with the business application.

D.  

Deploy the FM in Amazon SageMaker in eu-north-1. Configure a SageMaker VPC endpoint. Extend existing SCPs to allow employees to use the SageMaker endpoint. Integrate the FM in SageMaker with the business application.

Discussion 0
Questions 5

A retail company is using Amazon Bedrock to develop a customer service AI assistant. Analysis shows that 70% of customer inquiries are simple product questions that a smaller model can effectively handle. However, 30% of inquiries are complex return policy questions that require advanced reasoning.

The company wants to implement a cost-effective model selection framework to automatically route customer inquiries to appropriate models based on inquiry complexity. The framework must maintain high customer satisfaction and minimize response latency.

Which solution will meet these requirements with the LEAST implementation effort?

Options:

A.  

Create a multi-stage architecture that uses a small foundation model (FM) to classify the complexity of each inquiry. Route simple inquiries to a smaller, more cost-effective model. Route complex inquiries to a larger, more capable model. Use AWS Lambda functions to handle routing logic.

B.  

Use Amazon Bedrock intelligent prompt routing to automatically analyze inquiries. Route simple product inquiries to smaller models and route complex return policy inquiries to more capable larger models.

C.  

Implement a single-model solution that uses an Amazon Bedrock mid-sized foundation model (FM) with on-demand pricing. Include special instructions in model prompts to handle both simple and complex inquiries by using the same model.

D.  

Create separate Amazon Bedrock endpoints for simple and complex inquiries. Implement a rule-based routing system based on keyword detection. Use on-demand pricing for the smaller model and provisioned throughput for the larger model.

Discussion 0
Questions 6

Company configures a landing zone in AWS Control Tower. The company handles sensitive data that must remain within the European Union. The company must use only the eu-central-1 Region. The company uses Service Control Policies (SCPs) to enforce data residency policies. GenAI developers at the company are assigned IAM roles that have full permissions for Amazon Bedrock.

The company must ensure that GenAI developers can use the Amazon Nova Pro model through Amazon Bedrock only by using cross-Region inference (CRI) and only in eu-central-1. The company enables model access for the GenAI developer IAM roles in Amazon Bedrock. However, when a GenAI developer attempts to invoke the model through the Amazon Bedrock Chat/Text playground, the GenAI developer receives the following error:

User arn:aws:sts:123456789012:assumed-role/AssumedDevRole/DevUserName

Action: bedrock:InvokeModelWithResponseStream

On resource(s): arn:aws:bedrock:eu-west-3::foundation-model/amazon.nova-pro-v1:0

Context: a service control policy explicitly denies the action

The company needs a solution to resolve the error. The solution must retain the company ' s existing governance controls and must provide precise access control. The solution must comply with the company ' s existing data residency policies.

Which combination of solutions will meet these requirements? (Select TWO.)

Options:

A.  

Add an AdministratorAccess policy to the GenAI developer IAM role

B.  

Extend the existing SCPs to enable CRI for the eu.amazon.nova-pro-v1:0 inference profile

C.  

Enable Amazon Bedrock model access for Amazon Nova Pro in the eu-west-3 Region

D.  

Validate that the GenAI developer IAM roles have permissions to invoke Amazon Nova Pro through the eu.amazon.nova-pro-v1:0 inference profile on all European Union AWS Regions that can serve the model

E.  

Extend the existing SCP to enable CRI for the eu-* inference profile

Discussion 0
Questions 7

A financial technology company is using Amazon Bedrock to build an assessment system for the company’s customer service AI assistant. The AI assistant must provide financial recommendations that are factually accurate, compliant with financial regulations, and conversationally appropriate. The company needs to combine automated quality evaluations at scale with targeted human reviews of critical interactions.

What solution will meet these requirements?

Options:

A.  

Configure a pipeline in which financial experts manually score all responses for accuracy, compliance, and conversational quality. Use Amazon SageMaker notebooks to analyze results to identify improvement areas.

B.  

Configure Amazon Bedrock evaluations that use Anthropic Claude Sonnet as a judge model to assess response accuracy and appropriateness. Configure custom Amazon Bedrock guardrails to check responses for compliance with financial policies. Add Amazon Augmented AI (Amazon A2I) human reviews for flagged critical interactions.

C.  

Create an Amazon Lex bot to manage customer service interactions. Configure AWS Lambda functions to check responses against a static compliance database. Configure intents that call the Lambda functions. Add an additional intent to collect end-user reviews.

D.  

Configure Amazon CloudWatch to monitor response patterns from the AI assistant. Configure CloudWatch alerts for potential compliance violations. Establish a team of human evaluators to review flagged interactions.

Discussion 0
Questions 8

A company runs a generative AI (GenAI)-powered summarization application in an application AWS account that uses Amazon Bedrock. The application architecture includes an Amazon API Gateway REST API that forwards requests to AWS Lambda functions that are attached to private VPC subnets. The application summarizes sensitive customer records that the company stores in a governed data lake in a centralized data storage account. The company has enabled Amazon S3, Amazon Athena, and AWS Glue in the data storage account.

The company must ensure that calls that the application makes to Amazon Bedrock use only private connectivity between the company ' s application VPC and Amazon Bedrock. The company ' s data lake must provide fine-grained column-level access across the company ' s AWS accounts.

Which solution will meet these requirements?

Options:

A.  

In the application account, create interface VPC endpoints for Amazon Bedrock runtimes. Run Lambda functions in private subnets. Use IAM conditions on inference and data-plane policies to allow calls only to approved endpoints and roles. In the data storage account, use AWS Lake Formation LF-tag-based access control to create table-level and column-level cross-account grants.

B.  

Run Lambda functions in private subnets. Configure a NAT gateway to provide access to Amazon Bedrock and the data lake. Use S3 bucket policies and ACLs to manage permissions. Export AWS CloudTrail logs to Amazon S3 to perform weekly reviews.

C.  

Create a gateway endpoint only for Amazon S3 in the application account. Invoke Amazon Bedrock through public endpoints. Use database-level grants in AWS Lake Formation to manage data access. Stream AWS CloudTrail logs to Amazon CloudWatch Logs. Do not set up metric filters or alarms.

D.  

Use VPC endpoints to provide access to Amazon Bedrock and Amazon S3 in the application account. Use only IAM path-based policies to manage data lake access. Send AWS CloudTrail logs to Amazon CloudWatch Logs. Periodically create dashboards and allow public fallback for cross-Region reads to reduce setup time.

Discussion 0
Questions 9

A medical device company wants to feed reports of medical procedures that used the company’s devices into an AI assistant. To protect patient privacy, the AI assistant must expose patient personally identifiable information (PII) only to surgeons. The AI assistant must redact PII for engineers. The AI assistant must reference only medical reports that are less than 3 years old.

The company stores reports in an Amazon S3 bucket as soon as each report is published. The company has already set up an Amazon Bedrock Knowledge Bases. The AI assistant uses Amazon Cognito to authenticate users.

Which solution will meet these requirements?

Options:

A.  

Enable Amazon Macie PII detection on the S3 bucket. Use an S3 trigger to invoke an AWS Lambda function that redacts PII from the reports. Configure the Lambda function to delete outdated documents and invoke knowledge base syncing.

B.  

Invoke an AWS Lambda function to sync the S3 bucket and the knowledge base when a new report is uploaded. Use a second Lambda function with Amazon Comprehend to redact PII for engineers. Use S3 Lifecycle rules to remove reports older than 3 years.

C.  

Set up an S3 Lifecycle configuration to remove reports that are older than 3 years. Schedule an AWS Lambda function to run daily syncs between the bucket and the knowledge base. When users interact with the AI assistant, apply a guardrail configuration selected based on the user’s Cognito user group to redact PII from responses when required.

D.  

Create a second knowledge base. Use Lambda and Amazon Comprehend to redact PII before syncing to the second knowledge base. Route users to the appropriate knowledge base based on Cognito group membership.

Discussion 0
Questions 10

A company uses an organization in AWS Organizations with all features enabled to manage multiple AWS accounts. Employees use Amazon Bedrock across multiple accounts. The company must prevent specific topics and proprietary information from being included in prompts to Amazon Bedrock models. The company must ensure that employees can use only approved Amazon Bedrock models. The company wants to manage these controls centrally.

Which combination of solutions will meet these requirements? (Select TWO.)

Options:

A.  

Create an IAM permissions boundary for each employee ' s IAM role. Configure the permissions boundary to require an approved Amazon Bedrock guardrail identifier to invoke Amazon Bedrock models. Create an SCP that allows employees to use only approved models.

B.  

Create an SCP that allows employees to use only approved models. Configure the SCP to require employees to specify a guardrail identifier in calls to invoke an approved model.

C.  

Create an SCP that prevents an employee from invoking a model if a centrally deployed guardrail identifier is not specified in a call to the model. Create a permissions boundary on each employee ' s IAM role that allows each employee to invoke only approved models.

D.  

Use AWS CloudFormation to create a custom Amazon Bedrock guardrail that has a block filtering policy. Use stack sets to deploy the guardrail to each account in the organization.

E.  

Use AWS CloudFormation to create a custom Amazon Bedrock guardrail that has a mask filtering policy. Use stack sets to deploy the guardrail to each account in the organization.

Discussion 0
Questions 11

A financial services company uses multiple foundation models (FMs) through Amazon Bedrock for its generative AI (GenAI) applications. To comply with a new regulation for GenAI use with sensitive financial data, the company needs a token management solution.

The token management solution must proactively alert when applications approach model-specific token limits. The solution must also process more than 5,000 requests each minute and maintain token usage metrics to allocate costs across business units.

Which solution will meet these requirements?

Options:

A.  

Develop model-specific tokenizers in an AWS Lambda function. Configure the Lambda function to estimate token usage before sending requests to Amazon Bedrock. Configure the Lambda function to publish metrics to Amazon CloudWatch and trigger alarms when requests approach thresholds. Store detailed token usage in Amazon DynamoDB to report costs.

B.  

Implement Amazon Bedrock Guardrails with token quota policies. Capture metrics on rejected requests. Configure Amazon EventBridge rules to trigger notifications based on Amazon Bedrock Guardrails metrics. Use Amazon CloudWatch dashboards to visualize token usage trends across models.

C.  

Deploy an Amazon SQS dead-letter queue for failed requests. Configure an AWS Lambda function to analyze token-related failures. Use Amazon CloudWatch Logs Insights to generate reports on token usage patterns based on error logs from Amazon Bedrock API responses.

D.  

Use Amazon API Gateway to create a proxy for all Amazon Bedrock API calls. Configure request throttling based on custom usage plans with predefined token quotas. Configure API Gateway to reject requests that will exceed token limits.

Discussion 0
Questions 12

A company is using Amazon Bedrock to design an application to help researchers apply for grants. The application is based on an Amazon Nova Pro foundation model (FM). The application contains four required inputs and must provide responses in a consistent text format. The company wants to receive a notification in Amazon Bedrock if a response contains bullying language. However, the company does not want to block all flagged responses.

The company creates an Amazon Bedrock flow that takes an input prompt and sends it to the Amazon Nova Pro FM. The Amazon Nova Pro FM provides a response.

Which additional steps must the company take to meet these requirements? (Select TWO.)

Options:

A.  

Use Amazon Bedrock Prompt Management to specify the required inputs as variables. Select an Amazon Nova Pro FM. Specify the output format for the response. Add the prompt to the prompts node of the flow.

B.  

Create an Amazon Bedrock guardrail that applies the hate content filter. Set the filter response to block. Add the guardrail to the prompts node of the flow.

C.  

Create an Amazon Bedrock prompt router. Specify an Amazon Nova Pro FM. Add the required inputs as variables to the input node of the flow. Add the prompt router to the prompts node. Add the output format to the output node.

D.  

Create an Amazon Bedrock guardrail that applies the insults content filter. Set the filter response to detect. Add the guardrail to the prompts node of the flow.

E.  

Create an Amazon Bedrock application inference profile that specifies an Amazon Nova Pro FM. Specify the output format for the response in the description. Include a tag for each of the input variables. Add the profile to the prompts node of the flow.

Discussion 0
Questions 13

A company is developing a customer support application that uses Amazon Bedrock foundation models (FMs) to provide real-time AI assistance to the company’s employees. The application must display AI-generated responses character by character as the responses are generated. The application needs to support thousands of concurrent users with minimal latency. The responses typically take 15 to 45 seconds to finish.

Which solution will meet these requirements?

Options:

A.  

Configure an Amazon API Gateway WebSocket API with an AWS Lambda integration. Configure the WebSocket API to invoke the Amazon Bedrock InvokeModelWithResponseStream API and stream partial responses through WebSocket connections.

B.  

Configure an Amazon API Gateway REST API with an AWS Lambda integration. Configure the REST API to invoke the Amazon Bedrock standard InvokeModel API and implement frontend client-side polling every 100 ms for complete response chunks.

C.  

Implement direct frontend client connections to Amazon Bedrock by using IAM user credentials and the InvokeModelWithResponseStream API without any intermediate gateway or proxy layer.

D.  

Configure an Amazon API Gateway HTTP API with an AWS Lambda integration. Configure the HTTP API to cache complete responses in an Amazon DynamoDB table and serve the responses through multiple paginated GET requests to frontend clients.

Discussion 0
Questions 14

A healthcare company is developing an Amazon Bedrock-based AI clinical assistant. The company needs a solution to track model inputs and outputs so the company can perform offline quality evaluation and regression analysis. The solution must provide centralized, immutable audit records of all model inference and decision events. The company needs a solution that requires minimal runtime overhead so interactive latency remains stable during evaluation and auditing.

Which solution will meet these requirements?

Options:

A.  

Use Amazon SageMaker Model Registry to track model versions. Use Amazon Macie to classify artifacts. Write inference outputs to Amazon CloudWatch Logs. Manually perform monthly quality reviews.

B.  

Use AWS CloudTrail to record API calls. Store logs of API calls in an Amazon S3 bucket that has versioning enabled. Use AWS AppConfig feature flags to perform simple online splits without offline evaluation.

C.  

Send logs for Amazon Bedrock model invocations to Amazon CloudWatch Logs and Amazon S3. Enable AWS CloudTrail for Amazon Bedrock and Amazon S3 data events. Store logs in an S3 bucket that has Object Lock enabled. Run Amazon Bedrock model evaluations offline.

D.  

Capture dataset lineage in AWS Glue Data Catalog. Store inference payloads in standard Amazon S3 buckets. Use a judge large language model (LLM) to score responses in production for each request.

Discussion 0
Questions 15

A company is building a generative AI (GenAI) application that produces content based on a variety of internal and external data sources. The company wants to ensure that the generated output is fully traceable. The application must support data source registration and enable metadata tagging to attribute content to its original source. The application must also maintain audit logs of data access and usage throughout the pipeline.

Which solution will meet these requirements?

Options:

A.  

Use AWS Lake Formation to catalog data sources and control access. Apply metadata tags directly in Amazon S3. Use AWS CloudTrail to monitor API activity.

B.  

Use AWS Glue Data Catalog to register and tag data sources. Use Amazon CloudWatch Logs to monitor access patterns and application behavior.

C.  

Store data in Amazon S3 and use object tagging for attribution. Use AWS Glue Data Catalog to manage schema information. Use AWS CloudTrail to log access to S3 buckets.

D.  

Use AWS Glue Data Catalog to register all data sources. Apply metadata tags to attribute data sources. Use AWS CloudTrail to log access and activity across services.

Discussion 0
Questions 16

A retail company runs an application that makes product recommendations to customers on the company’s website. The application uses Amazon Bedrock to generate recommendations by dynamically constructing prompts and sending them to foundation models (FMs). A GenAI developer has deployed an update to the application that instructs the FM to include a specific promotional message when the FM generates a response to prompts. When the developer tests the application, the promotional message does not always appear in the responses. When the promotional message does appear in the responses, it does not always flow with the rest of the text. The GenAI developer must ensure that the promotional message always appears in the FM responses. Which solution will meet this requirement?

Options:

A.  

Use an Amazon Bedrock Guardrails filter on the prompt. Set the input filter strength to HIGH.

B.  

Generate multiple response variants that include the promotional message in different ways. Use a reranker model to select the most coherent version based on relevance to the original prompt.

C.  

Run the prompt through Amazon Bedrock. Process the response through Amazon Bedrock AgentCore to add the promotional message. Rerank the results by using the original prompt and the desired message as context.

D.  

Reinforce the requirement to include the new promotional message within product recommendations by using an output indicator in prompts to the FM.

Discussion 0
Questions 17

A financial services company is deploying a GenAI assistant that uses Amazon Bedrock to answer customer questions about account activity and company policies. The company must comply with responsible AI principles and governance requirements.

The solution must meet the following requirements:

• Prevent harmful, biased, or non-compliant responses.

• Ensure consistent policy enforcement across all model invocations.

• Provide traceability and auditability for AI-generated outputs.

• Maintain developer productivity without embedding complex safety logic in application code.

Which solution will meet these requirements?

Options:

A.  

Use Amazon Bedrock Guardrails to enforce content policies. Configure response filtering and topic restrictions. Configure logging for model interactions.

B.  

Use prompt engineering techniques and system prompts to guide the model ' s behavior.

C.  

Implement post-processing checks in AWS Lambda functions to manually review and redact model outputs before returning responses to users.

D.  

Log all prompts and responses to Amazon S3. Conduct periodic human reviews to identify violations of responsible AI principles.

Discussion 0
Questions 18

A financial services company uses an AI application to process financial documents by using Amazon Bedrock. During business hours, the application handles approximately 10,000 requests each hour, which requires consistent throughput.

The company uses the CreateProvisionedModelThroughput API to purchase provisioned throughput. Amazon CloudWatch metrics show that the provisioned capacity is unused while on-demand requests are being throttled. The company finds the following code in the application:

response = bedrock_runtime.invoke_model(

modelId= " anthropic.claude-v2 " ,

body=json.dumps(payload)

)

The company needs the application to use the provisioned throughput and to resolve the throttling issues.

Which solution will meet these requirements?

Options:

A.  

Increase the number of model units (MUs) in the provisioned throughput configuration.

B.  

Replace the model ID parameter with the ARN of the provisioned model that the CreateProvisionedModelThroughput API returns.

C.  

Add exponential backoff retry logic to handle throttling exceptions during peak hours.

D.  

Modify the application to use the invokeModelWithResponseStream API instead of the invokeModel API.

Discussion 0
Questions 19

A healthcare company is using Amazon Bedrock to build a Retrieval Augmented Generation (RAG) application that helps practitioners make clinical decisions. The application must achieve high accuracy for patient information retrievals, identify hallucinations in generated content, and reduce human review costs.

Which solution will meet these requirements?

Options:

A.  

Use Amazon Comprehend to analyze and classify RAG responses and to extract medical entities and relationships. Use AWS Step Functions to orchestrate automated evaluations. Configure Amazon CloudWatch metrics to track entity recognition confidence scores. Configure CloudWatch to send an alert when accuracy falls below specified thresholds.

B.  

Implement automated large language model (LLM)-based evaluations that use a specialized model that is fine-tuned for medical content to assess all responses. Deploy AWS Lambda functions to parallelize evaluations. Publish results to Amazon CloudWatch metrics that track relevance and factual accuracy.

C.  

Configure Amazon CloudWatch Synthetics to generate test queries that have known answers on a regular schedule, and track model success rates. Set up dashboards that compare synthetic test results against expected outcomes.

D.  

Deploy a hybrid evaluation system that uses an automated LLM-as-a-judge evaluation to initially screen responses and targeted human reviews for edge cases. Use a built-in Amazon Bedrock evaluation to track retrieval precision and hallucination rates.

Discussion 0
Questions 20

A medical company uses Amazon Bedrock to power a clinical documentation summarization system. The system produces inconsistent summaries when handling complex clinical documents. The system performed well on simple clinical documents.

The company needs a solution that diagnoses inconsistencies, compares prompt performance against established metrics, and maintains historical records of prompt versions.

Which solution will meet these requirements?

Options:

A.  

Create multiple prompt variants by using Prompt management in Amazon Bedrock. Manually test the prompts with simple clinical documents. Deploy the highest performing version by using the Amazon Bedrock console.

B.  

Implement version control for prompts in a code repository with a test suite that contains complex clinical documents and quantifiable evaluation metrics. Use an automated testing framework to compare prompt versions and document performance patterns.

C.  

Deploy each new prompt version to separate Amazon Bedrock API endpoints. Split production traffic between the endpoints. Configure Amazon CloudWatch to capture response metrics and user feedback for automatic version selection.

D.  

Create a custom prompt evaluation flow in Amazon Bedrock Flows that applies the same clinical document inputs to different prompt variants. Use Amazon Comprehend Medical to analyze and score the factual accuracy of each version.

Discussion 0
Questions 21

A company is using Amazon Bedrock to build a GenAI assistant that answers employee questions based on internal documentation. The company stores documents in Amazon S3, Atlassian Confluence, and an internal wiki system. The GenAI assistant must retrieve relevant content and provide grounded responses.

The solution must meet the following requirements:

• Integrate multiple document sources into a single retrieval layer.

• Support semantic search rather than keyword-only queries.

• Minimize custom ingestion and synchronization logic.

• Ensure that retrieved content can be directly used to augment the GenAI assistant ' s foundation model (FM).

Which solution will meet these requirements?

Options:

A.  

Use Amazon Bedrock Knowledge Bases and managed data connectors to ingest content from the source documents. Enable semantic retrieval to augment the FM.

B.  

Index documents from the source documents into Amazon OpenSearch Service by using keyword mappings. Invoke the FM and manually select search results.

C.  

Store the source documents in Amazon S3. Use AWS Lambda functions to generate embeddings. Implement custom retrieval logic in the GenAI assistant application layer.

D.  

Store the source documents in Amazon DynamoDB. Query the DynamoDB table directly to provide contextual input to the FM.

Discussion 0
Questions 22

A specialty coffee company has a mobile app that generates personalized coffee roast profiles by using Amazon Bedrock with a three-stage prompt chain. The prompt chain converts user inputs into structured metadata, retrieves relevant logs for coffee roasts, and generates a personalized roast recommendation for each customer.

Users in multiple AWS Regions report inconsistent roast recommendations for identical inputs, slow inference during the retrieval step, and unsafe recommendations such as brewing at excessively high temperatures. The company must improve the stability of outputs for repeated inputs. The company must also improve app performance and the safety of the app’s outputs. The updated solution must ensure 99.5% output consistency for identical inputs and achieve inference latency of less than 1 second. The solution must also block unsafe or hallucinated recommendations by using validated safety controls.

Which solution will meet these requirements?

Options:

A.  

Deploy Amazon Bedrock with provisioned throughput to stabilize inference latency. Apply Amazon Bedrock guardrails with semantic denial rules to block unsafe outputs. Use Amazon Bedrock Prompt Management to manage prompts by using approval workflows.

B.  

Use Amazon Bedrock Agents to manage chaining. Log model inputs and outputs to Amazon CloudWatch Logs . Use logs from CloudWatch to perform A/B testing for prompt versions.

C.  

Cache prompt results in Amazon ElastiCache . Use AWS Lambda functions to pre-process metadata and to trace end-to-end latency. Use AWS X-Ray to identify and remediate performance bottlenecks.

D.  

Use Amazon Kendra to improve roast log retrieval accuracy. Store normalized prompt metadata within Amazon DynamoDB. Use AWS Step Functions to orchestrate multi-step prompts.

Discussion 0
Questions 23

A company is designing a solution that uses foundation models (FMs) to support multiple AI workloads. Some FMs must be invoked on demand and in real time. Other FMs require consistent high-throughput access for batch processing.

The solution must support hybrid deployment patterns and run workloads across cloud infrastructure and on-premises infrastructure to comply with data residency and compliance requirements.

Which combination of steps will meet these requirements? (Select TWO.)

Options:

A.  

Use AWS Lambda to orchestrate low-latency FM inference by invoking FMs hosted on Amazon SageMaker AI asynchronous endpoints.

B.  

Configure provisioned throughput in Amazon Bedrock to ensure consistent performance for high-volume workloads.

C.  

Deploy FMs to Amazon SageMaker AI endpoints with support for edge deployment by using Amazon SageMaker Neo. Orchestrate the FMs by using AWS Lambda to support hybrid deployment.

D.  

Use Amazon Bedrock with auto-scaling to handle unpredictable traffic surges.

E.  

Use Amazon SageMaker JumpStart to host and invoke the FMs.

Discussion 0
Questions 24

A logistics company is using Amazon Bedrock to build an autonomous routing agent that coordinates with APIs that support warehouse, shipping, and international customs operations. The agent must meet the following requirements:

• Break requests into reasoning steps.

• Retry failed tool calls with backoff.

• Stop retrying after three consecutive failures.

• Require human approval for shipments that are valued over $100,000.

• Use MCP to provide access to tools and new integrations without requiring code changes.

Which combination of solutions will meet these requirements? (Select THREE.)

Options:

A.  

Use Amazon Bedrock AgentCore Gateway to convert the warehouse, shipping, and customs APIs into MCP-compatible tools.

B.  

Use Task states in AWS Step Functions to orchestrate each reasoning step. Use retry configurations with exponential backoff to handle tool failures.

C.  

Use a Choice state to route high-value shipments to a human approval workflow.

D.  

Use Amazon Bedrock AgentCore with action groups for each API. Configure the agent ' s orchestration prompt to implement retry logic and human approval conditions.

E.  

Use AWS Lambda functions that use MCP client libraries to invoke tools. Implement custom retry logic and circuit breaker patterns in Lambda function code.

F.  

Use Amazon Bedrock Guardrails to block tool invocations for shipments that exceed the $100,000 threshold until a human approves the shipment through a separate workflow.

G.  

Use Amazon API Gateway with AWS Lambda authorizers to validate tool requests and implement rate limiting. Implement custom retry logic with exponential backoff and a circuit breaker that halts retries after three consecutive failures.

Discussion 0
Questions 25

A medical company is building a generative AI (GenAI) application that uses Retrieval Augmented Generation (RAG) to provide evidence-based medical information. The application uses Amazon OpenSearch Service to retrieve vector embeddings. Users report that searches frequently miss results that contain exact medical terms and acronyms and return too many semantically similar but irrelevant documents. The company needs to improve retrieval quality and maintain low end-user latency, even as the document collection grows to millions of documents.

Which solution will meet these requirements with the LEAST operational overhead?

Options:

A.  

Configure hybrid search by combining vector similarity with keyword matching to improve semantic understanding and exact term and acronym matching.

B.  

Increase the dimensions of the vector embeddings from 384 to 1536. Use a post-processing AWS Lambda function to filter out irrelevant results after retrieval.

C.  

Replace OpenSearch Service with Amazon Kendra. Use query expansion to handle medical acronyms and terminology variants during pre-processing.

D.  

Implement a two-stage retrieval architecture in which initial vector search results are re-ranked by an ML model hosted on Amazon SageMaker.

Discussion 0
Questions 26

A financial services company is developing a customer service AI assistant by using Amazon Bedrock. The AI assistant must not discuss investment advice with users. The AI assistant must block harmful content, mask personally identifiable information (PII), and maintain audit trails for compliance reporting. The AI assistant must apply content filtering to both user inputs and model responses based on content sensitivity.

The company requires an Amazon Bedrock guardrail configuration that will effectively enforce policies with minimal false positives. The solution must provide multiple handling strategies for multiple types of sensitive content.

Which solution will meet these requirements?

Options:

A.  

Configure a single guardrail and set content filters to high for all categories. Set up denied topics for investment advice and include sample phrases to block. Set up sensitive information filters that apply the block action for all PII entities. Apply the guardrail to all model inference calls.

B.  

Configure multiple guardrails by using tiered policies. Create one guardrail and set content filters to high. Configure the guardrail to block PII for public interactions. Configure a second guardrail and set content filters to medium. Configure the second guardrail to mask PII for internal use. Configure multiple topic-specific guardrails to block investment advice and set up contextual grounding checks.

C.  

Configure a guardrail and set content filters to medium for harmful content. Set up denied topics for investment advice and include clear definitions and sample phrases to block. Configure sensitive information filters to mask PII in responses and to block financial information in inputs. Enable both input and output evaluations that use custom blocked messages for audits.

D.  

Create a separate guardrail for each use case. Create one guardrail that applies a harmful content filter. Create a guardrail to apply topic filters for investment advice. Create a guardrail to apply sensitive information filters to block PII. Use AWS Step Functions to chain the guardrails sequentially.

Discussion 0
Questions 27

A wildlife conservation agency operates zoos globally. The agency uses various sensors, trackers, and audiovisual recorders to monitor animal behavior. The agency wants to launch a generative AI (GenAI) assistant that can ingest multimodal data to study animal behavior.

The GenAI assistant must support natural language queries, avoid speculative behavioral interpretations, and maintain audit logs for ethical research audits.

Which solution will meet these requirements?

Options:

A.  

Ingest raw videos into Amazon Rekognition to detect animal postures and expressions. Use Amazon Data Firehose to stream sensor and GPS data into Amazon S3. Prompt an Amazon Bedrock FM using basic templates stored in AWS Systems Manager Parameter Store. Use IAM for access control. Use AWS CloudTrail for audit logging.

B.  

Use Amazon SageMaker Processing and Amazon Transcribe to pre-process multimodal data. Ingest curated summaries into an Amazon Bedrock Knowledge Bases. Apply Amazon Bedrock guardrails to restrict speculative outputs. Use AWS AppConfig to manage prompt templates. Use AWS CloudTrail to log research activity for audits.

C.  

Use Amazon OpenSearch Serverless to index behavioral logs and telemetry. Use Amazon Comprehend to extract entities. Use Amazon Bedrock to answer questions over indexed data. Use IAM for access control and CloudTrail for audit logging.

D.  

Configure Amazon O Business to federate data across Amazon S3, Amazon Kinesis, and Amazon SageMaker Feature Store. Use EventBridge for ingestion orchestration. Use custom AWS Lambda functions to filter LLM outputs for ethical compliance.

Discussion 0
Questions 28

A company uses AWS Lake Formation to set up a data lake that contains databases and tables for multiple business units across multiple AWS Regions. The company wants to use a foundation model (FM) through Amazon Bedrock to perform fraud detection. The FM must ingest sensitive financial data from the data lake. The data includes some customer personally identifiable information (PII).

The company must design an access control solution that prevents PII from appearing in a production environment. The FM must access only authorized data subsets that have PII redacted from specific data columns. The company must capture audit trails for all data access.

Which solution will meet these requirements?

Options:

A.  

Create a separate dataset in a separate Amazon S3 bucket for each business unit and Region combination. Configure S3 bucket policies to control access based on IAM roles that are assigned to FM training instances. Use S3 access logs to track data access.

B.  

Configure the FM to authenticate by using AWS Identity and Access Management roles and Lake Formation permissions based on LF-Tag expressions. Define business units and Regions as LF-Tags that are assigned to databases and tables. Use AWS CloudTrail to collect comprehensive audit trails of data access.

C.  

Use direct IAM principal grants on specific databases and tables in Lake Formation. Create a custom application layer that logs access requests and further filters sensitive columns before sending data to the FM.

D.  

Configure the FM to request temporary credentials from AWS Security Token Service . Access the data by using presigned S3 URLs that are generated by an API that applies business unit and Regional filters. Use AWS CloudTrail to collect comprehensive audit trails of data access.

Discussion 0
Questions 29

A retail company has a generative AI (GenAI) product recommendation application that uses Amazon Bedrock. The application suggests products to customers based on browsing history and demographics. The company needs to implement fairness evaluation across multiple demographic groups to detect and measure bias in recommendations between two prompt approaches. The company wants to collect and monitor fairness metrics in real time. The company must receive an alert if the fairness metrics show a discrepancy of more than 15% between demographic groups. The company must receive weekly reports that compare the performance of the two prompt approaches.

Which solution will meet these requirements with the LEAST custom development effort?

Options:

A.  

Configure an Amazon CloudWatch dashboard to display default metrics from Amazon Bedrock API calls. Create custom metrics based on model outputs. Set up Amazon EventBridge rules to invoke AWS Lambda functions that perform post-processing analysis on model responses and publish custom fairness metrics.

B.  

Create the two prompt variants in Amazon Bedrock Prompt Management. Use Amazon Bedrock Flows to deploy the prompt variants with defined traffic allocation. Configure Amazon Bedrock guardrails to monitor demographic fairness. Set up Amazon CloudWatch alarms on the GuardrailContentSource dimension by using InvocationsIntervened metrics to detect recommendation discrepancy threshold violations.

C.  

Set up Amazon SageMaker Clarify to analyze model outputs. Publish fairness metrics to Amazon CloudWatch. Create CloudWatch composite alarms that combine SageMaker Clarify bias metrics with Amazon Bedrock latency metrics.

D.  

Create an Amazon Bedrock model evaluation job to compare fairness between the two prompt variants. Enable model invocation logging in Amazon CloudWatch. Set up CloudWatch alarms for InvocationsIntervened metrics with a dimension for each demographic group.

Discussion 0
Questions 30

A company provides a service that helps users from around the world discover new restaurants. The service has 50 million monthly active users. The company wants to implement a semantic search solution across a database that contains 20 million restaurants and 200 million reviews. The company currently stores the data in PostgreSQL.

The solution must support complex natural language queries and return results for at least 95% of queries within 500 ms. The solution must maintain data freshness for restaurant details that update hourly. The solution must also scale cost-effectively during peak usage periods.

Which solution will meet these requirements with the LEAST development effort?

Options:

A.  

Migrate the restaurant data to Amazon OpenSearch Service. Implement keyword-based search rules that use custom analyzers and relevance tuning to find restaurants based on attributes such as cuisine type, features, and location. Create Amazon API Gateway HTTP API endpoints to transform user queries into structured search parameters.

B.  

Migrate the restaurant data to Amazon OpenSearch Service. Use a foundation model (FM) in Amazon Bedrock to generate vector embeddings from restaurant descriptions, reviews, and menu items. When users submit natural language queries, convert the queries to embeddings by using the same FM. Perform k-nearest neighbors (k-NN) searches to find semantically similar results.

C.  

Keep the restaurant data in PostgreSQL and implement a pgvector extension. Use a foundation model (FM) in Amazon Bedrock to generate vector embeddings from restaurant data. Store the vector embeddings directly in PostgreSQL. Create an AWS Lambda function to convert natural language queries to vector representations by using the same FM. Configure the Lambda function to perform similarity searches within the database.

D.  

Migrate restaurant data to an Amazon Bedrock knowledge base by using a custom ingestion pipeline. Configure the knowledge base to automatically generate embeddings from restaurant information. Use the Amazon Bedrock Retrieve API with built-in vector search capabilities to query the knowledge base directly by using natural language input.

Discussion 0
Questions 31

A financial services company is creating a Retrieval Augmented Generation (RAG) application that uses Amazon Bedrock to generate summaries of market activities. The application relies on a vector database that stores a small proprietary dataset with a low index count. The application must perform similarity searches. The Amazon Bedrock model’s responses must maximize accuracy and maintain high performance.

The company needs to configure the vector database and integrate it with the application.

Which solution will meet these requirements?

Options:

A.  

Launch an Amazon MemoryDB cluster and configure the index by using the Flat algorithm. Configure a horizontal scaling policy based on performance metrics.

B.  

Launch an Amazon MemoryDB cluster and configure the index by using the Hierarchical Navigable Small World (HNSW) algorithm. Configure a vertical scaling policy based on performance metrics.

C.  

Launch an Amazon Aurora PostgreSQL cluster and configure the index by using the Inverted File with Flat Compression (IVFFlat) algorithm. Configure the instance class to scale to a larger size when the load increases.

D.  

Launch an Amazon DocumentDB cluster that has an IVFFlat index and a high probe value. Configure connections to the cluster as a replica set. Distribute reads to replica instances.

Discussion 0
Questions 32

A company upgraded its Amazon Bedrock–powered foundation model (FM) that supports a multilingual customer service assistant. After the upgrade, the assistant exhibited inconsistent behavior across languages. The assistant began generating different responses in some languages when presented with identical questions.

The company needs a solution to detect and address similar problems for future updates. The evaluation must be completed within 45 minutes for all supported languages. The evaluation must process at least 15,000 test conversations in parallel. The evaluation process must be fully automated and integrated into the CI/CD pipeline. The solution must block deployment if quality thresholds are not met.

Which solution will meet these requirements?

Options:

A.  

Create a distributed traffic simulation framework that sends translation-heavy workloads to the assistant in multiple languages simultaneously. Use Amazon CloudWatch metrics to monitor latency, concurrency, and throughput. Run simulations before production releases to identify infrastructure bottlenecks.

B.  

Deploy the assistant in multiple AWS Regions with Amazon Route 53 latency-based routing and AWS Global Accelerator to improve global performance. Store multilingual conversation logs in Amazon S3. Perform weekly post-deployment audits to review consistency.

C.  

Create a pre-processing pipeline that normalizes all incoming messages into a consistent format before sending the messages to the assistant. Apply rule-based checks to flag potential hallucinations in the outputs. Focus evaluation on normalized text to simplify testing across languages.

D.  

Set up standardized multilingual test conversations with identical meaning. Run the test conversations in parallel by using Amazon Bedrock model evaluation jobs. Apply similarity and hallucination thresholds. Integrate the process into the CI/CD pipeline to block releases that fail.

Discussion 0
Questions 33

A research company is developing a GenAI system to produce summaries of technical documents. The company must catalog all data sources in a central location. The company needs a solution that can automatically discover and update data sources. The solution must tag each generated summary with citations as metadata that users can query. The solution must retain tamper-evident, immutable audit logs for every model invocation and store I/O records. Which solution will meet these requirements?

Options:

A.  

Use Amazon Comprehend to identify data sources in the documents. Store generated summaries in Amazon S3 and enable S3 Object Lock. Use Amazon CloudWatch metrics to generate reports about application throughput. Do not include logs for each invocation.

B.  

Use AWS Glue Data Catalog with crawlers to maintain data sources. Store generated summaries in Amazon S3. Write object tags that include a source ID. Store Amazon Bedrock model invocation logs in Amazon S3. Enable S3 Object Lock on the S3 bucket that stores invocation logs. Use AWS CloudTrail log file integrity validation to provide tamper-evident immutability.

C.  

Store application outputs in Amazon DynamoDB. Apply item-level tags that include source attribution. Write application events to Amazon CloudWatch Logs. Use IAM roles to provide audit traceability.

D.  

Use AWS AppConfig feature flags to implement data versioning. Restrict access to the model by using IAM condition keys. Maintain a versioned mapping file of source-to-output relationships in Amazon S3.

Discussion 0
Questions 34

A global research company is building a RAG-enabled AI system that uses Amazon Bedrock Knowledge Bases. The company stores documents in Amazon S3 and indexes the documents into an Amazon OpenSearch Serverless vector collection.

When the company evaluates the system, the company identifies three issues. Queries return outdated documents when users request only recent research. Medical research queries return both medical research documents and engineering domain documents. Users can retrieve documents that were authored by researchers who the users should not have access to based on company policies.

The company wants to improve the system so that retrieval becomes more precise and contextually appropriate.

Which solution will meet these requirements?

Options:

A.  

Add custom metadata fields to the documents in Amazon S3 to record timestamp, authorship, and research domain. Index the document embeddings and the custom metadata fields into the OpenSearch Serverless vector collection. At query time, use the knowledge base to run vector similarity search and return the stored metadata with the results to help the model interpret document relevance.

B.  

Use S3 object metadata to store each document ' s timestamp. Use a custom metadata field to record authorship. Use S3 object tags to record the research domain. Propagate the metadata fields into the OpenSearch Serverless vector collection as filterable attributes. Use Knowledge Bases to apply timestamp, author, and domain filters before running vector similarity search.

C.  

Store documents in Amazon S3. Extract timestamp, author metadata, and research-domain tags, and store the data in an Amazon DynamoDB table. During retrieval, apply author, domain, and timestamp filters in DynamoDB to identify candidate document IDs. Use the filtered document IDs to narrow the vector similarity search in the OpenSearch Serverless collection.

D.  

Store documents in Amazon S3 with custom metadata to record authorship. Use Amazon Comprehend to classify each document into a research domain. Store the classification results in Amazon Aurora. Query Aurora during retrieval to identify relevant domains before performing vector similarity search in the OpenSearch Serverless collection.

Discussion 0
Questions 35

A company uses an AI assistant application to summarize the company’s website content and provide information to customers. The company plans to use Amazon Bedrock to give the application access to a foundation model (FM).

The company needs to deploy the AI assistant application to a development environment and a production environment. The solution must integrate the environments with the FM. The company wants to test the effectiveness of various FMs in each environment. The solution must provide product owners with the ability to easily switch between FMs for testing purposes in each environment.

Which solution will meet these requirements?

Options:

A.  

Create one AWS CDK application. Create multiple pipelines in AWS CodePipeline. Configure each pipeline to have its own settings for each FM. Configure the application to invoke the Amazon Bedrock FMs by using the aws_bedrock.ProvisionedModel.fromProvisionedModelArn() method.

B.  

Create a separate AWS CDK application for each environment. Configure the applications to invoke the Amazon Bedrock FMs by using the aws_bedrock.FoundationModel.fromFoundationModelId() method. Create a separate pipeline in AWS CodePipeline for each environment.

C.  

Create one AWS CDK application. Configure the application to invoke the Amazon Bedrock FMs by using the aws_bedrock.FoundationModel.fromFoundationModelId() method. Create a pipeline in AWS CodePipeline that has a deployment stage for each environment that uses AWS CodeBuild deploy actions.

D.  

Create one AWS CDK application for the production environment. Configure the application to invoke the Amazon Bedrock FMs by using the aws_bedrock.ProvisionedModel.fromProvisionedModelArn() method. Create a pipeline in AWS CodePipeline. Configure the pipeline to deploy to the production environment by using an AWS CodeBuild deploy action. For the development environment, manually recreate the resources by referring to the production applica

Discussion 0
Questions 36

A healthcare company is using Amazon Bedrock to build a system to help practitioners make clinical decisions. The system must provide treatment recommendations to physicians based only on approved medical documentation and must cite specific sources. The system must not hallucinate or produce factually incorrect information.

Which solution will meet these requirements with the LEAST operational overhead?

Options:

A.  

Integrate Amazon Bedrock with Amazon Kendra to retrieve approved documents. Implement custom post-processing to compare generated responses against source documents and to include citations.

B.  

Deploy an Amazon Bedrock Knowledge Base and connect it to approved clinical source documents. Use the Amazon Bedrock RetrieveAndGenerate API to return citations from the knowledge base.

C.  

Use Amazon Bedrock and Amazon Comprehend Medical to extract medical entities. Implement verification logic against a medical terminology database.

D.  

Use an Amazon Bedrock knowledge base with Retrieve API calls and InvokeModel API calls to retrieve approved clinical source documents. Implement verification logic to compare against retrieved sources and to cite sources.

Discussion 0
Questions 37

A company is building an AI-powered customer support application that uses Amazon Bedrock FMs. The application must provide users with recommendations based on an internal Amazon Bedrock knowledge base.

Users will query documents that the company stores in Amazon S3 and structured data that is in Amazon RDS. The application must provide citations for the sources it uses to generate recommendations. The application must also provide secure access to sensitive data.

Which solution will meet these requirements?

Options:

A.  

Associate one Amazon Bedrock AgentCore agent with two knowledge bases. Configure one knowledge base to access documents from Amazon S3 and the other to access structured data from Amazon RDS. Configure the agent to preserve attribution metadata in responses. Use IAM roles to control access to sensitive data.

B.  

Create two Amazon Bedrock AgentCore agents. Associate one agent with a knowledge base that is connected to the documents in Amazon S3 and the other agent with a knowledge base that is connected to Amazon RDS. Develop a custom AWS Lambda function to query both agents simultaneously and combine the results.

C.  

Create one Amazon Bedrock AgentCore agent that uses AWS Lambda functions to directly query Amazon S3 for documents and Amazon RDS for structured data. Process the responses and merge the results into a single response.

D.  

Configure one Amazon Bedrock AgentCore agent to use a knowledge base that contains the documents from Amazon S3. Configure AWS Lambda functions to query Amazon RDS directly for structured data and to combine the results before returning responses.

Discussion 0
Questions 38

An elevator service company has developed an AI assistant application by using Amazon Bedrock. The application generates elevator maintenance recommendations to support the company’s elevator technicians. The company uses Amazon Kinesis Data Streams to collect the elevator sensor data.

New regulatory rules require that a human technician must review all AI-generated recommendations. The company needs to establish human oversight workflows to review and approve AI recommendations. The company must store all human technician review decisions for audit purposes.

Which solution will meet these requirements?

Options:

A.  

Create a custom approval workflow by using AWS Lambda functions and Amazon SQS queues for human review of AI recommendations. Store all review decisions in Amazon DynamoDB for audit purposes.

B.  

Create an AWS Step Functions workflow that has a human approval step that uses the waitForTaskToken API to pause execution. After a human technician completes a review, use an AWS Lambda function to call the SendTaskSuccess API with the approval decision. Store all review decisions in Amazon DynamoD

B.  

C.  

Create an AWS Glue workflow that has a human approval step. After the human technician review, integrate the application with an AWS Lambda function that calls the SendTaskSuccess API. Store all human technician review decisions in Amazon DynamoDB.

D.  

Configure Amazon EventBridge rules with custom event patterns to route AI recommendations to human technicians for review. Create AWS Glue jobs to process human technician approval queues. Use Amazon ElastiCache to cache all human technician review decisions.

Discussion 0
Questions 39

A company is using Amazon Bedrock to develop a customer support AI assistant. The AI assistant must respond to customer questions about their accounts. The AI assistant must not expose personal information in responses. The company must comply with data residency policies by ensuring that all processing occurs within the same AWS Region where each customer is located.

The company wants to evaluate how effective the AI assistant is at preventing the exposure of personal information before the company makes the AI assistant available to customers.

Which solution will meet these requirements?

Options:

A.  

Configure a cross-Region Amazon Bedrock guardrail to apply sensitive information filters. Set the guardrail to detect mode during development and testing. Switch to block mode for production deployment.

B.  

Configure an Amazon Bedrock guardrail to apply sensitive information filters. Set the guardrail to mask mode during development and testing. Switch to block mode for production deployment. Deploy a copy of the guardrail to each Region where the company operates.

C.  

Configure an Amazon Bedrock guardrail to apply content and topic filters. Set the guardrail to detect mode during development, testing, and production. Disable invocation logging for the Amazon Bedrock model.

D.  

Configure a cross-Region Amazon Bedrock guardrail to apply a set of content and word filters. Set the guardrail to detect mode during development and testing. Switch to mask mode for production deployment.

Discussion 0
Questions 40

A financial services company is developing a customer service AI assistant application that uses a foundation model (FM) in Amazon Bedrock. The application must provide transparent responses by documenting reasoning and by citing sources that are used for Retrieval Augmented Generation (RAG). The application must capture comprehensive audit trails for all responses to users. The application must be able to serve up to 10,000 concurrent users and must respond to each customer inquiry within 2 seconds.

Which solution will meet these requirements with the LEAST operational overhead?

Options:

A.  

Enable tracing for Amazon Bedrock Agents. Configure structured prompts that direct the FM to provide evidence presentations. Integrate Amazon Bedrock Knowledge Bases with data sources to enable RAG. Configure the application to reference and cite authoritative content. Deploy the application in a Multi-AZ architecture. Use Amazon API Gateway and AWS Lambda functions to scale the application. Use Amazon CloudFront to provide low-latency deli

B.  

Enable tracing for Amazon Bedrock agents. Integrate a custom RAG pipeline with Amazon OpenSearch Service to retrieve and cite sources. Configure structured prompts to present retrieved evidence. Deploy the application behind an Amazon API Gateway REST API. Use AWS Lambda functions and Amazon CloudFront to scale the application and to provide low latency. Store logs in Amazon S3 and use AWS CloudTrail to capture audit trails.

C.  

Use Amazon CloudWatch to monitor latency and error rates. Embed model prompts directly in the application backend to cite sources. Store application interactions with users in Amazon RDS for audits.

D.  

Store generated responses and supporting evidence in an Amazon S3 bucket. Enable versioning on the bucket for audits. Use AWS Glue to catalog retrieved documents. Process the retrieved documents in Amazon Athena to generate periodic compliance reports.

Discussion 0
Questions 41

A company has a recommendation system running on Amazon EC2 instances. The applications make API calls to Amazon Bedrock foundation models (FMs) to analyze customer behavior and generate personalized product recommendations.

The system experiences intermittent issues where some recommendations do not match customer preferences. The company needs an observability solution to monitor operational metrics and detect patterns of performance degradation compared to established baselines. The solution must generate alerts with correlation data within 10 minutes when FM behavior deviates from expected patterns.

Which solution will meet these requirements?

Options:

A.  

Configure Amazon CloudWatch Container Insights. Set up alarms for latency thresholds. Add custom token metrics using the CloudWatch embedded metric format.

B.  

Implement AWS X-Ray. Enable CloudWatch Logs Insights. Set up AWS CloudTrail and create dashboards in Amazon QuickSight.

C.  

Enable Amazon CloudWatch Application Insights. Create custom metrics for recommendation quality, token usage, and response latency using the CloudWatch embedded metric format with dimensions for request types and user segments. Configure CloudWatch anomaly detection on model metrics. Use CloudWatch Logs Insights for pattern analysis.

D.  

Use Amazon OpenSearch Service with the Observability plugin. Ingest metrics and logs through Amazon Kinesis and analyze behavior with custom queries.

Discussion 0
Questions 42

A company is developing a generative AI (GenAI) application by using Amazon Bedrock. The application will analyze patterns and relationships in the company ' s data. The application will process millions of new data points daily across AWS Regions in Europe, North America, and Asia before storing the data in Amazon S3.

The application must comply with local data protection and storage regulations. Data residency and processing must occur within the same continent. The application must also maintain audit trails of the application ' s decision-making processes and provide data classification capabilities.

Which solution will meet these requirements?

Options:

A.  

Deploy the application in each Region with local IAM policies. Use Amazon Bedrock cross-Region inference to distribute the workload. Use Amazon CloudWatch to log AI decision-making processes and data processing activities. Manually track compliance certifications across Regions.

B.  

Use SCPs with AWS Organizations to manage location-specific permissions. Use AWS CloudTrail immutable logs to audit the decision-making processes. Import a custom model into Amazon Bedrock and deploy the model to each Region.

C.  

Use Amazon S3 Object Lock with Region-specific S3 bucket policies. Pre-process the data points within the Region based on geographic origin before sending the data points to Amazon Bedrock. Use Amazon Macie to classify the data. Use AWS CloudTrail immutable logs to audit the decision-making processes.

D.  

Create separate AWS accounts for each Region with individual compliance frameworks. Use Amazon SageMaker AI with custom monitoring to track model performance and compliance with data residency requirements. Create manual reports for each regulatory jurisdiction.

Discussion 0
Questions 43

A medical company is creating a generative AI (GenAI) system by using Amazon Bedrock. The system processes data from various sources and must maintain end-to-end data lineage. The system must also use real-time personally identifiable information (PII) filtering and audit trails to automatically report compliance.

Which solution will meet these requirements?

Options:

A.  

Use AWS Glue Data Catalog to register all data sources and track lineage. Use Amazon Bedrock Guardrails PII filters. Enable AWS CloudTrail logging for all Amazon Bedrock API calls with Amazon S3 integration. Use Amazon Macie to scan stored data for sensitive information and publish findings to Amazon CloudWatch Logs. Create CloudWatch dashboards to visualize the findings and generate automated compliance reports.

B.  

Use AWS Config to track data source configurations and changes. Use AWS WAF with custom rules to filter PII at the application layer before Amazon Bedrock processes the data. Configure Amazon EventBridge to capture and route audit events to Amazon S3. Use Amazon Comprehend Medical with scheduled AWS Lambda functions to analyze stored outputs for compliance violations.

C.  

Use AWS DataSync to replicate data sources to track lineage. Configure Amazon Macie to scan Amazon Bedrock outputs for sensitive information. Use AWS Systems Manager Session Manager to log user interactions. Deploy Amazon Textract with AWS Step Functions workflows to identify and redact PII from generated reports.

D.  

Configure Amazon Athena to query data sources to analyze and report on data lineage. Use Amazon CloudWatch custom metrics to monitor PII exposure in Amazon Bedrock responses and establish AWS X-Ray tracing to generate an audit trail. Use an Amazon Rekognition Custom Labels model to detect sensitive information in the data that Amazon Bedrock processes.

Discussion 0
Questions 44

A company uses Amazon Bedrock to generate technical content for customers. The company has recently experienced a surge in hallucinated outputs when the company’s model generates summaries of long technical documents. The model outputs include inaccurate or fabricated details. The company’s current solution uses a large foundation model (FM) with a basic one-shot prompt that includes the full document in a single input.

The company needs a solution that will reduce hallucinations and meet factual accuracy goals. The solution must process more than 1,000 documents each hour and deliver summaries within 3 seconds for each document.

Which combination of solutions will meet these requirements? (Select TWO.)

Options:

A.  

Implement zero-shot chain-of-thought (CoT) instructions that require step-by-step reasoning with explicit fact verification before the model generates each summary.

B.  

Use Retrieval Augmented Generation (RAG) with an Amazon Bedrock knowledge base. Apply semantic chunking and tuned embeddings to ground summaries in source content.

C.  

Configure Amazon Bedrock guardrails to block any generated output that matches patterns that are associated with hallucinated content.

D.  

Increase the temperature parameter in Amazon Bedrock.

E.  

Prompt the Amazon Bedrock model to summarize each full document in one pass.

Discussion 0
Questions 45

A company is developing three specialized NLP models that support a customer service application. One model categorizes each customer’s specific issue. Another model extracts key information from the customer interactions. The third model generates responses. The company must ensure that the application achieves at least 95% accuracy for all tasks. The application must handle up to 500 concurrent requests and respond in less than 500 ms during daily 2-hour peak usage periods. The company must ensure that the application optimizes resource usage during periods of low demand between usage spikes. Which solution will meet these requirements?

Options:

A.  

Deploy all three models to a single Amazon SageMaker AI multi-model endpoint. Enable dynamic scaling on the endpoint. Use a compute optimized instance type. Configure auto scaling policies that are based on invocation metrics to handle peak loads.

B.  

Deploy each model to a separate Amazon SageMaker Serverless Inference endpoint. Set provisioned concurrency to handle peak loads. Configure maximum concurrency limits and memory sizing based on each model ' s specific requirements.

C.  

Deploy the models by using Amazon Bedrock with provisioned throughput to handle peak loads. Configure the number of model units (MUs) based on expected token throughput needs. Implement request batching for each model.

D.  

Deploy each model to a separate Amazon SageMaker AI endpoint. Use an asynchronous inference configuration. Store model requests and responses in Amazon S3. Use Amazon SNS to send alerts to users when the application finishes processing requests.

Discussion 0
Questions 46

An ecommerce company operates a global product recommendation system that needs to switch between multiple foundation models (FM) in Amazon Bedrock based on regulations, cost optimization, and performance requirements. The company must apply custom controls based on proprietary business logic, including dynamic cost thresholds, AWS Region-specific compliance rules, and real-time A/B testing across multiple FMs.

The system must be able to switch between FMs without deploying new code. The system must route user requests based on complex rules including user tier, transaction value, regulatory zone, and real-time cost metrics that change hourly and require immediate propagation across thousands of concurrent requests.

Which solution will meet these requirements?

Options:

A.  

Deploy an AWS Lambda function that uses environment variables to store routing rules and Amazon Bedrock FM IDs. Use the Lambda console to update the environment variables when business requirements change. Configure an Amazon API Gateway REST API to read request parameters to make routing decisions.

B.  

Deploy Amazon API Gateway REST API request transformation templates to implement routing logic based on request attributes. Store Amazon Bedrock FM endpoints as REST API stage variables. Update the variables when the system switches between models.

C.  

Configure an AWS Lambda function to fetch routing configurations from the AWS AppConfig Agent for each user request. Run business logic in the Lambda function to select the appropriate FM for each request. Expose the FM through a single Amazon API Gateway REST API endpoint.

D.  

Use AWS Lambda authorizers for an Amazon API Gateway REST API to evaluate routing rules that are stored in AWS AppConfig. Return authorization contexts based on business logic. Route requests to model-specific Lambda functions for each Amazon Bedrock FM.

Discussion 0
Questions 47

An ecommerce company is building an internal platform to develop generative AI applications by using Amazon Bedrock foundation models (FMs). Developers need to select models based on evaluations that are aligned to ecommerce use cases. The platform must display accuracy metrics for text generation and summarization in dashboards. The company has custom ecommerce datasets to use as standardized evaluation inputs.

Which combination of steps will meet these requirements with the LEAST operational overhead? (Select TWO.)

Options:

A.  

Import the datasets to an Amazon S3 bucket. Provide appropriate IAM permissions and cross-origin resource sharing (CORS) permissions to give the evaluation jobs access to the datasets.

B.  

Import the datasets to an Amazon S3 bucket. Provide appropriate IAM permissions and a VPC endpoint configuration to give the evaluation jobs access to the datasets.

C.  

Configure an AWS Lambda function to create model evaluation jobs on a schedule in the Amazon Bedrock console. Provide the URI of the S3 bucket that contains the datasets as an input. Configure the evaluation jobs to measure the real world knowledge (RWK) score for text generation and BERTScore for summarization. Configure a second Lambda function to check the status of the jobs and publish custom logs to Amazon CloudWatch. Create a custom A

D.  

Use Amazon SageMaker Clarify on a schedule to create model evaluation jobs. Use open source frameworks to create and run standardized evaluations. Publish results to Amazon CloudWatch namespaces. Use an AWS Lambda function to check the status of the jobs and publish custom logs to Amazon CloudWatch. Create a custom Amazon CloudWatch Logs Insights dashboard.

E.  

Run an Amazon SageMaker AI notebook job on a schedule by using the fmvelos or ragas framework to run evaluations that use the datasets in the S3 bucket. Write Python code in the notebook that makes direct InvokeModel API calls to the FMs and processes their responses for evaluation. Publish job status and results to Amazon CloudWatch Logs to measure the real world knowledge (RWK) score for text generation and toxicity for summarization as

Discussion 0
Questions 48

A company is developing a generative AI (GenAI) application by using Amazon Bedrock. The application will analyze patterns and relationships in the company’s data. The application will process millions of new data points daily across AWS Regions in Europe, North America, and Asia before storing the data in Amazon S3.

The application must comply with local data protection and storage regulations. Data residency and processing must occur within the same continent. The application must also maintain audit trails of the application’s decision-making processes and provide data classification capabilities.

Which solution will meet these requirements?

Options:

A.  

Deploy the application in each Region with local IAM policies. Use Amazon Bedrock cross-Region inference to distribute the workload. Use Amazon CloudWatch to log AI decision-making processes. Manually track compliance certifications across Regions.

B.  

Use SCPs with AWS Organizations to manage location-specific permissions. Use AWS CloudTrail immutable logs to audit decision-making processes. Import a custom model into Amazon Bedrock and deploy the model to each Region.

C.  

Use Amazon S3 Object Lock with Region-specific S3 bucket policies. Pre-process the data points within the Region based on geographic origin before sending the data points to Amazon Bedrock. Use Amazon Macie to classify the data. Use AWS CloudTrail immutable logs to audit the decision-making processes.

D.  

Create separate AWS accounts for each Region with individual compliance frameworks. Use Amazon SageMaker AI with custom monitoring. Create manual compliance reports for each regulatory jurisdiction.

Discussion 0