Question 1

A company has set up Amazon Q Developer Pro licenses for all developers at the company. The company maintains a list of approved resources that developers must use when developing applications. The approved resources include internal libraries, proprietary algorithmic techniques, and sample code with approved styling. A new team of developers is using Amazon Q Developer to develop a new Java-based application. The company must ensure that the new developer team uses the company’s approved resources. The company does not want to make project-level modifications. Which solution will meet these requirements? 

A. Create a Git repository that contains all of the approved internal libraries, algorithms, and code samples. Include this Git repository in the application project locally as part of the workspace. Ensure that the developers use the workspace context to retrieve suggestions from the Git repository. 
B. In the project root folder, create a folder named amazonq/rules. Add the approved internal libraries, algorithms, and code samples to the folder. 
C. Create a folder in the application project named rules. Store the guidelines and code in the folder for Amazon Q Developer to reference for code suggestions. 
D. Create an Amazon Q Developer customization that includes the approved data sources. Ensure that the developers use the customization to develop the application. 

Show Answer

Question 2

A large ecommerce company has deployed a foundation model (FM) to generate product descriptions. The company's engineering team monitors technical metrics such as token usage, latency, and error rates by using Amazon CloudWatch. The company's marketing team tracks business metrics such as conversion rates and revenue impact in its own systems. The company needs a unified observability solution that correlates technical performance with business outcomes. The solution must provide automatic alerts to stakeholders when operational metrics indicate degradation. The solution must provide comprehensive visibility across both technical and business metrics. Which solution will meet these requirements? 

A. Create CloudWatch dashboards that include technical metrics and imported business metrics. Configure CloudWatch composite alarms that combine technical data and business data. Use Amazon SNS to set up notifications to stakeholders. 
B. Use Amazon Managed Grafana to visualize technical metrics from CloudWatch with business metrics from external sources. Configure Amazon Managed Grafana alerts to invoke AWS Lambda functions. Configure the Lambda functions to remediate issues automatically when metrics exceed predefined thresholds. 
C. Stream CloudWatch metrics to Amazon S3 by using CloudWatch metric streams. Create Amazon QuickSight dashboards to visualize the combined technical metrics and business metrics. Set up Amazon EventBridge rules to send notifications to stakeholders when metrics exceed predefined thresholds. 
D. Configure CloudWatch custom dashboards that integrate operational metrics with imported business metrics. Set up CloudWatch composite alarms with anomaly detection. Use Amazon SNS to create alarm actions to notify stakeholders when correlated metrics indicate performance issues. 

Show Answer

Question 3

A university is building an AI-powered application that includes several sub-applications. The sub-applications include AI assistants, assignment graders, and internal analytics applications. The university is defining and testing multiple prompts by using various foundation models (FMs). The university wants to compare variants of each prompt and choose the variant that yield outputs that are best-suited for specified use cases. The university requires a version control solution for the prompts. The university must be able to test prompt variations and collect audit trails for prompt changes and usage. The solution must also maintain consistency while allowing the prompts to integrate into the main application. Which combination of solutions will meet these requirements with the LEAST operational overhead? (Select TWO.)

A. Use Amazon Bedrock Prompt Management to create versioned prompts. Include parameterized variables for each use case. 
B. Store prompts in Amazon S3. Use AWS Step Functions to orchestrate the model interactions and service integrations. 
C. Use Amazon Bedrock Flows to create workflows that combine FMs and AWS services. 
D. Configure AWS Config to record prompt changes. Use AWS CloudTrail to track prompt usage. 
E. Configure Amazon Bedrock intelligent prompt routing. 

Show Answer

Question 4

A company purchases Amazon Q Developer Pro subscriptions for 500 developers to improve code quality and productivity. The company needs to create an observability system that tracks adoption metrics across the company. The observability system must be able to identify active subscription users compared to underused subscriptions. The system must give the company the ability to recognize power users every quarter and to identify teams that require additional training. The system must provide visibility into usage patterns such as the number of lines of Amazon Q generated code that each user has accepted. Which solution will meet these requirements?

A. Create a usage dashboard for Amazon Q Developer. Use the usage dashboard to track aggregated usage adoption metrics. 
B. Use the Amazon Q Developer built-in administrator dashboard to track user adoption metrics across the company’s organization in AWS Organizations. 
C. Collect user-level metrics in Amazon Q Developer. Store the metrics in an Amazon S3 bucket. Use Amazon QuickSight to visualize the usage data. Create dashboards to show adoption metrics for users and teams. 
D. Configure AWS CloudTrail to track all Amazon Q Developer API calls in the company’s organization in AWS Organizations. Use an AWS Lambda function to process the logs. Store the processed logs in Amazon DynamoDB. Create custom dashboards in Amazon Managed Grafana to visualize the data. 

Show Answer

Question 5

A company is building a real-time voice assistant system to assist customer service representatives during customer calls. The system must convert audio calls to text with end-to-end latency of less than 500 ms. The system must use generative AI (GenAI) to produce response suggestions. Human supervisors must be able to rate the system's suggestions during a live customer call. The company must store all customer interactions to comply with auditing policies. Which solution will meet these requirements?

A. Use the Amazon Transcribe streaming API with standard settings to convert speech to text. Use Amazon Bedrock batch processing to perform inference. Store call recordings and metadata in Amazon S3. Use S3 Lifecycle policies to manage the storage. 
B. Use the Amazon Transcribe streaming API with 100-ms audio chunks to optimize latency for the voice assistant. Call the Amazon Bedrock InvokeModelWithResponseStream operation to process client inquiries in real time. Store supervisor ratings in an Amazon DynamoDB table. 
C. Use Amazon Transcribe batch processing to perform post-call analysis. Configure AWS Lambda functions to generate responses by using the Amazon Bedrock InvokeModel operation. Use Amazon CloudWatch to log supervisor feedback. 
D. Use Amazon Transcribe to convert speech to text and to perform real-time analytics. Use Amazon Comprehend to perform sentiment analysis. Use Amazon SQS to queue processing tasks. Run the Amazon Bedrock InvokeModel operation to generate responses. 

Show Answer

Question 6

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? 

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. 

Show Answer

Question 7

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?

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. 

Show Answer

Question 8

A healthcare company wants to develop a proof-of-concept application that uses Amazon Bedrock to automatically summarize medical documents. The company has 3 weeks to validate the application's accuracy. The application must comply with the company’s data privacy policies. The application must include metrics to evaluate summarization accuracy and processing time. Which solution will meet these requirements?

A. Create a dataset that includes 50-100 anonymized patient records. Implement Retrieval Augmented Generation (RAG) with a secure knowledge base. Use a judge model to evaluate accuracy metrics across three foundation models (FMs).
B. Fine-tune a single foundation model (FM) on patient records. Deploy the FM on Amazon Bedrock. Use Amazon Bedrock AgentCore to configure the FM as an agent. Conduct user testing on 500 company staff members. 
C. Select the most powerful available AWS foundation model (FM). Create a chat interface by using Converse APIs. Test the application on 50-100 actual patient records by using only qualitative feedback from stakeholders. Use a custom web interface to gather realworld performance metrics. 
D. Use the Strands SDK to deploy multiple agents that connect to multiple knowledge bases that contain specialized medical documents. Compare the responses of the agents. Evaluate the integration of the agents with the company's existing systems. 

Show Answer

Question 9

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? 

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. 

Show Answer

Question 10

A financial services company wants to use Amazon Bedrock foundation models (FMs) to analyze call center recordings. When calls end, the call center stores recordings as MP3 files in an Amazon S3 bucket. The company needs to generate summaries and sentiment analysis for the recordings in a structured format as soon as new files are created. The recordings average 20 MB in size. Which combination of solutions will meet these requirements? (Select TWO.)

A. Use AWS Step Functions to orchestrate a workflow to process the recordings. Configure steps to invoke Amazon Transcribe to convert audio to text, validate job completion, and to invoke an AWS Lambda function to process the text by using Amazon Bedrock FMs to generate structured analysis output. 
B. Use AWS Step Functions to orchestrate a workflow to process the recordings. Configure steps to invoke Amazon Transcribe to convert audio to text, validate job completion, and to directly invoke Amazon Bedrock FMs to generate summaries and sentiment analysis in JSON format. 
C. Use AWS Step Functions to orchestrate a workflow to process the recordings. Configure steps to invoke Amazon Transcribe to convert audio to text, validate job completion, and to invoke an AWS Lambda function to create a prompt to invoke Amazon Bedrock FMs to generate structured analysis output. 
D. Configure the source S3 bucket to send events to Amazon EventBridge. Create an EventBridge rule to invoke the Step Functions workflow when an object is created in the bucket. 
E. Configure the source S3 bucket to send notifications to the Step Functions workflow when an object is created in the bucket. 

Show Answer