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?

1. A. Configure hybrid search by combining vector similarity with keyword matching to improve semantic understanding and exact term and acronym matching.
2. 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.
3. C. Replace OpenSearch Service with Amazon Kendr
4. D. Use query expansion to handle medical acronyms and terminology variants during pre-processing.
5. E. Implement a two-stage retrieval architecture in which initial vector search results are re- ranked by an ML model hosted on Amazon SageMaker.

Correct Answer: A

A company is developing a generative AI (GenAI) application that analyzes customer service calls in real time and generates suggested responses for human customer service agents. The application must process 500,000 concurrent calls during peak hours with less than 200 ms end-to-end latency for each suggestion. The company uses existing architecture to transcribe customer call audio streams. The application must not exceed a predefined monthly compute budget and must maintain auto scaling capabilities.
Which solution will meet these requirements?

1. A. Deploy a large, complex reasoning model on Amazon Bedroc
2. B. Purchase provisioned throughput and optimize for batch processing.
3. C. Deploy a low-latency, real-time optimized model on Amazon Bedroc
4. D. Purchase provisioned throughput and set up automatic scaling policies.
5. E. Deploy a large language model (LLM) on an Amazon SageMaker real-time endpoint that uses dedicated GPU instances.
6. F. Deploy a mid-sized language model on an Amazon SageMaker serverless endpoint that is optimized for batch processing.

Correct Answer: B

A company uses AWS Lambda functions to build an AI agent solution. A GenAI developer must set up a Model Context Protocol (MCP) server that accesses user information. The GenAI developer must also configure the AI agent to use the new MCP server. The GenAI developer must ensure that only authorized users can access the MCP server.
Which solution will meet these requirements?

1. A. Use a Lambda function to host the MCP serve
2. B. Grant the AI agent Lambda functions permission to invoke the Lambda function that hosts the MCP serve
3. C. Configure the AI agent??s MCP client to invoke the MCP server asynchronously.
4. D. Use a Lambda function to host the MCP serve
5. E. Grant the AI agent Lambda functions permission to invoke the Lambda function that hosts the MCP serve
6. F. Configure the AI agent to use the STDIO transport with the MCP server.
7. G. Use a Lambda function to host the MCP serve
8. H. Create an Amazon API Gateway HTTP API that proxies requests to the Lambda functio
9. I. Configure the AI agent solution to use the Streamable HTTP transport to make requests through the HTTP AP
10. J. Use Amazon Cognito to enforce OAuth 2.1.
11. K. Use a Lambda layer to host the MCP serve
12. L. Add the Lambda layer to the AI agent Lambda function
13. M. Configure the agentic AI solution to use the STDIO transport to send requests to the MCP serve
14. N. In the AI agent??s MCP configuration, specify the Lambda layer ARN as the comman
15. O. Specify the user credentials as environment variables.

Correct Answer: C

A publishing company is developing a chat assistant that uses a containerized large language model (LLM) that runs on Amazon SageMaker AI. The architecture consists of an Amazon API Gateway REST API that routes user requests to an AWS Lambda function. The Lambda function invokes a SageMaker AI real-time endpoint that hosts the LLM.
Users report uneven response times. Analytics show that a high number of chats are abandoned after 2 seconds of waiting for the first token. The company wants a solution to ensure that p95 latency is under 800 ms for interactive requests to the chat assistant.
Which combination of solutions will meet this requirement? (Select TWO.)

1. A. Enable model preload upon container startu
2. B. Implement dynamic batching to process multiple user requests together in a single inference pass.
3. C. Select a larger GPU instance type for the SageMaker AI endpoin
4. D. Set the minimum number of instances to 0. Continue to perform per-request processin
5. E. Lazily load model weights on the first request.
6. F. Switch to a multi-model endpoin
7. G. Use lazy loading without request batching.
8. H. Set the minimum number of instances to greater than 0. Enable response streaming.
9. I. Switch to Amazon SageMaker Asynchronous Inference for all request
10. J. Store requests in an Amazon S3 bucke
11. K. Set the minimum number of instances to 0.

Correct Answer: AD

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?

1. A. Deploy the application in each Region with local IAM policie
2. B. Use Amazon Bedrock cross-Region inference to distribute the workloa
3. C. Use Amazon CloudWatch to log AI decision-making processe
4. D. Manually track compliance certifications across Regions.
5. E. Use SCPs with AWS Organizations to manage location-specific permission
6. F. Use AWS CloudTrail immutable logs to audit decision-making processe
7. G. Import a custom model into Amazon Bedrock and deploy the model to each Region.
8. H. Use Amazon S3 Object Lock with Region-specific S3 bucket policie
9. I. Pre-process the data points within the Region based on geographic origin before sending the data points to Amazon Bedroc
10. J. Use Amazon Macie to classify the dat
11. K. Use AWS CloudTrail immutable logs to audit the decision-making processes.
12. L. Create separate AWS accounts for each Region with individual compliance framework
13. M. Use Amazon SageMaker AI with custom monitorin
14. N. Create manual compliance reports for each regulatory jurisdiction.

Correct Answer: C