An ecommerce company is developing a generative AI (GenAI) solution that uses Amazon Bedrock with Anthropic Claude to recommend products to customers. Customers report that some recommended products are not available for sale or are not relevant. Customers also report long response times for some recommendations.
The company confirms that most customer interactions are unique and that the solution recommends products not present in the product catalog.
Which solution will meet this requirement?

1. A. Increase grounding within Amazon Bedrock Guardrail
2. B. Enable automated reasoning check
3. C. Set up provisioned throughput.
4. D. Use prompt engineering to restrict model responses to relevant product
5. E. Use streaming inference to reduce perceived latency.
6. F. Create an Amazon Bedrock Knowledge Bases and implement Retrieval Augmented Generation (RAG). Set the PerformanceConfigLatency parameter to optimized.
7. G. Store product catalog data in Amazon OpenSearch Servic
8. H. Validate model recommendations against the catalo
9. I. Use Amazon DynamoDB for response caching.

Correct Answer: C

A company is designing an API for a generative AI (GenAI) application that uses a foundation model (FM) that is hosted on a managed model service. The API must stream responses to reduce latency, enforce token limits to manage compute resource usage, and implement retry logic to handle model timeouts and partial responses.
Which solution will meet these requirements with the LEAST operational overhead?

1. A. Integrate an Amazon API Gateway HTTP API with an AWS Lambda function to invoke Amazon Bedroc
2. B. Use Lambda response streaming to stream response
3. C. Enforce token limits within the Lambda functio
4. D. Implement retry logic for model timeouts by using Lambda and API Gateway timeout configurations.
5. E. Connect an Amazon API Gateway HTTP API directly to Amazon Bedroc
6. F. Simulate streaming by using client-side pollin
7. G. Enforce token limits on the fronten
8. H. Configure retry behavior by using API Gateway integration settings.
9. I. Connect an Amazon API Gateway WebSocket API to an Amazon ECS service that hosts a containerized inference serve
10. J. Stream responses by using the WebSocket protoco
11. K. Enforce token limits within Amazon EC
12. L. Handle model timeouts by using ECS task lifecycle hooks and restart policies.
13. M. Integrate an Amazon API Gateway REST API with an AWS Lambda function that invokes Amazon Bedroc
14. N. Use Lambda response streaming to stream response
15. O. Enforce token limits within the Lambda functio
16. P. Implement retry logic by using Lambda and API Gateway timeout configurations.

Correct Answer: A

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?

1. A. Use AWS Glue Data Catalog to register all data sources and track lineag
2. B. Use Amazon Bedrock Guardrails PII filter
3. C. Enable AWS CloudTrail logging for all Amazon Bedrock API calls with Amazon S3 integratio
4. D. Use Amazon Macie to scan stored data for sensitive information and publish findings to Amazon CloudWatch Log
5. E. Create CloudWatch dashboards to visualize the findings and generate automated compliance reports.
6. F. Use AWS Config to track data source configurations and change
7. G. Use AWS WAF with custom rules to filter PII at the application layer before Amazon Bedrock processes the dat
8. H. 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.
9. I. Use AWS DataSync to replicate data sources to track lineag
10. J. Configure Amazon Macie to scan Amazon Bedrock outputs for sensitive informatio
11. K. Use AWS Systems Manager Session Manager to log user interaction
12. L. Deploy Amazon Textract with AWS Step Functions workflows to identify and redact PII from generated reports.
13. M. Configure Amazon Athena to query data sources to analyze and report on data lineag
14. N. Use Amazon CloudWatch custom metrics to monitor PII exposure in Amazon Bedrock responses and establish AWS X-Ray tracing to generate an audit trai
15. O. Use an Amazon Rekognition Custom Labels model to detect sensitive information in the data that Amazon Bedrock processes.

Correct Answer: A

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?

1. A. Deploy Amazon Bedrock with provisioned throughput to stabilize inference latenc
2. B. Apply Amazon Bedrock guardrails with semantic denial rules to block unsafe output
3. C. Use Amazon Bedrock Prompt Management to manage prompts by using approval workflows.
4. D. Use Amazon Bedrock Agents to manage chainin
5. E. Log model inputs and outputs to Amazon CloudWatch Log
6. F. Use logs from CloudWatch to perform A/B testing for prompt versions.
7. G. Cache prompt results in Amazon ElastiCach
8. H. Use AWS Lambda functions to pre- process metadata and to trace end-to-end latenc
9. I. Use AWS X-Ray to identify and remediate performance bottlenecks.
10. J. Use Amazon Kendra to improve roast log retrieval accurac
11. K. Store normalized prompt metadata within Amazon DynamoD
12. L. Use AWS Step Functions to orchestrate multi-step prompts.

Correct Answer: A

A company is designing a canary deployment strategy for a payment processing API. The system must support automated gradual traffic shifting between multiple Amazon Bedrock models based on real-time inference metrics, historical traffic patterns, and service health. The solution must be able to gradually increase traffic to new model versions. The system must increase traffic if metrics remain healthy and decrease traffic if the performance degrades below acceptable thresholds.
The company needs to comprehensively monitor inference latency and error rates during the deployment phase. The company must also be able to halt deployments and revert to a previous model version without any manual intervention.
Which solution will meet these requirements?

1. A. Use Amazon Bedrock with provisioned throughput to host model version
2. B. Configure an Amazon EventBridge rule to invoke an AWS Step Functions workflow when a new model version is release
3. C. Configure the workflow to shift traffic in stages, wait for a specified time period, and invoke an AWS Lambda function to check Amazon CloudWatch performance metric
4. D. Configure the workflow to increase traffic if metrics meet thresholds and to trigger a traffic rollback if performance metrics fall below thresholds.
5. E. Use AWS Lambda functions to invoke various Amazon Bedrock model version
6. F. Use an Amazon API Gateway HTTP API with stage variables and weighted routing to shift traffic graduall
7. G. Use Amazon CloudWatch to monitor performanc
8. H. Use external logic to adjust traffic and roll back if performance falls below thresholds.
9. I. Use Amazon SageMaker AI endpoint variants to represent multiple Amazon Bedrock model version
10. J. Use variant weights to shift traffi
11. K. Use Amazon CloudWatch and SageMaker Model Monitor to trigger rollback
12. L. Use EventBridge to roll back deployments if an anomaly is detected.
13. M. Use Amazon OpenSearch Service to track inference log
14. N. Configure OpenSearch Service to invoke an AWS Systems Manager Automation runbook to update Amazon Bedrock model endpoints to shift traffic based on inference logs.

Correct Answer: A