Free AWS Certified Generative AI Developer - Professional Practice Questions

Question # 31

A pharmaceutical company is developing a Retrieval Augmented Generation application that uses an Amazon Bedrock knowledge base. The knowledge base uses Amazon OpenSearch Service as a data source for more than 25 million scientific papers. Users report that the application produces inconsistent answers that cite irrelevant sections of papers when queries span methodology, results, and discussion sections of the papers.

The company needs to improve the knowledge base to preserve semantic context across related paragraphs on the scale of the entire corpus of data.

Which solution will meet these requirements?

Options:

Configure the knowledge base to use fixed-size chunking. Set a 300-token maximum chunk size and a 10% overlap between chunks. Use an appropriate Amazon Bedrock embedding model.

Configure the knowledge base to use hierarchical chunking. Use parent chunks that contain 1,000 tokens and child chunks that contain 200 tokens. Set a 50-token overlap between chunks.

Configure the knowledge base to use semantic chunking. Use a buffer size of 1 and a breakpoint percentile threshold of 85% to determine chunk boundaries based on content meaning.

Configure the knowledge base not to use chunking. Manually split each document into separate files before ingestion. Apply post-processing reranking during retrieval.

Discussion 0

Question # 32

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:

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.

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.

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

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

Question # 33

A company wants to implement an Amazon Bedrock application that helps lawyers search thousands of legal documents. The solution must give lawyers the ability to query based on the type of legal case, jurisdiction, and case outcome. Queries must return information about document authors and versions. The solution must integrate with the company ' s existing tools and support future growth in volume and query complexity.

Which solution will meet these requirements?

Options:

Use Amazon Bedrock Knowledge Bases with a flat text embedding store. Include search context in user queries.

Use Amazon Bedrock Knowledge Bases with a vector store that supports metadata filtering. Configure metadata attributes for case type, jurisdiction, and case outcome to enable structured retrieval. Store authorship and version information in metadata fields.

Use Amazon Comprehend to extract metadata attributes such as case type, jurisdiction, and case outcome from legal documents. Use Amazon Bedrock Knowledge Bases with a flat embedding store.

Use Amazon Bedrock Knowledge Bases with documents that include metadata attributes such as case type, jurisdiction, and case outcome embedded inside the text rather than defined as structured fields. Use Amazon Bedrock AgentCore with the RetrieveAndGenerate API to extract metadata from embedded documents during queries.

Discussion 0

Question # 34

A healthcare company uses a multi-agent system on Amazon Bedrock AgentCore. The system uses multiple FMs to process 2,000 medical report documents daily. The documents range from 5 to 50 pages each.

The company discovers that the system is not performing complete analysis on documents that exceed 30 pages. Documents over 30 pages miss critical information from later sections. The results are truncated, but there are no explicit errors.

The company must resolve this issue while maintaining response times under 10 seconds. The company must keep processing costs low.

Which solution will meet these requirements?

Options:

Use Amazon CloudWatch Logs Insights queries to analyze Amazon Bedrock agent processing times. Increase the timeout settings for the Lambda functions that host the agents. Implement pagination for larger documents to process in sequential batches.

Implement document chunking with semantic overlap between chunks where content from the end of one chunk appears at the beginning of the next chunk. Configure Amazon CloudWatch metrics to monitor InputTokenCount. Set up a CloudWatch dashboard for context utilization percentage. Configure diagnostic logging that identifies truncation points in the processing flow.

Configure agent action groups to process documents sequentially by automatically creating separate tasks for each document section. Set up an AWS Step Functions workflow to coordinate processing. Combine the results from individual sections.

Deploy the system in a higher memory configuration with a larger compute instance size to accommodate complete documents in memory. Add Amazon Comprehend Medical to identify and prioritize critical medical entities for improved context management.

Discussion 0

Question # 35

A company is using Amazon Bedrock to develop an AI-powered application that uses a foundation model that supports cross-Region inference and provisioned throughput. The application must serve users in Europe and North America with consistently low latency. The application must comply with data residency regulations that require European user data to remain within Europe-based AWS Regions.

During testing, the application experiences service degradation when Regional traffic spikes reach service quotas. The company needs a solution that maintains application resilience and minimizes operational complexity.

Which solution will meet these requirements?

Options:

Deploy separate Amazon Bedrock instances in North American and European Regions. Use a custom routing layer that directs traffic based on user location. Configure Amazon CloudWatch alarms to monitor Regional service usage. Use Amazon SNS to send email alerts to the company when usage approaches specified thresholds.

Use Amazon Bedrock cross-Region inference profiles by specifying geographical codes in profile IDs when the application calls the InvokeModel API. Configure separate Amazon API Gateway HTTP APIs to direct European and North American users to the appropriate Regional endpoints.

Deploy a multi-Region Amazon API Gateway HTTP API and AWS Lambda functions that implement retry logic to handle throttling. Configure the Lambda functions to call the foundation model in the nearest secondary Region when the application reaches service quotas in the primary Region. Use intelligent routing to ensure compliance with data residency requirements.

Configure provisioned throughput for Amazon Bedrock in multiple Regions. Implement failover logic in the application code to switch between Regions when throttling occurs. Use AWS Global Accelerator to route traffic to the appropriate endpoints based on user location.

Discussion 0

Question # 36

A company is using Amazon Bedrock and Anthropic Claude 3 Haiku to develop an AI assistant. The AI assistant normally processes 10,000 requests each hour but experiences surges of up to 30,000 requests each hour during peak usage periods. The AI assistant must respond within 2 seconds while operating across multiple AWS Regions.

The company observes that during peak usage periods, the AI assistant experiences throughput bottlenecks that cause increased latency and occasional request timeouts. The company must resolve the performance issues.

Which solution will meet this requirement?

Options:

Purchase provisioned throughput and sufficient model units (MUs) in a single Region. Configure the application to retry failed requests with exponential backoff.

Implement token batching to reduce API overhead. Use cross-Region inference profiles to automatically distribute traffic across available Regions.

Set up auto scaling AWS Lambda functions in each Region. Implement client-side round-robin request distribution. Purchase one model unit (MU) of provisioned throughput as a backup.

Implement batch inference for all requests by using Amazon S3 buckets across multiple Regions. Use Amazon SQS to set up an asynchronous retrieval process.

Discussion 0

Question # 37

A company has deployed an AI assistant as a React application that uses AWS Amplify, an AWS AppSync GraphQL API, and Amazon Bedrock Knowledge Bases. The application uses the GraphQL API to call the Amazon Bedrock RetrieveAndGenerate API for knowledge base interactions. The company configures an AWS Lambda resolver to use the RequestResponse invocation type.

Application users report frequent timeouts and slow response times. Users report these problems more frequently for complex questions that require longer processing.

The company needs a solution to fix these performance issues and enhance the user experience.

Which solution will meet these requirements?

Options:

Use AWS Amplify AI Kit to implement streaming responses from the GraphQL API and to optimize client-side rendering.

Increase the timeout value of the Lambda resolver. Implement retry logic with exponential backoff.

Update the application to send an API request to an Amazon SQS queue. Update the AWS AppSync resolver to poll and process the queue.

Change the RetrieveAndGenerate API to the InvokeModelWithResponseStream API. Update the application to use an Amazon API Gateway WebSocket API to support the streaming response.

Discussion 0

Question # 38

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:

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.

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.

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.

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

Question # 39

A healthcare company is using Amazon Bedrock to develop a real-time patient care AI assistant to respond to queries for separate departments that handle clinical inquiries, insurance verification, appointment scheduling, and insurance claims. The company wants to use a multi-agent architecture.

The company must ensure that the AI assistant is scalable and can onboard new features for patients. The AI assistant must be able to handle thousands of parallel patient interactions. The company must ensure that patients receive appropriate domain-specific responses to queries.

Which solution will meet these requirements?

Options:

Isolate data for each agent by using separate knowledge bases. Use IAM filtering to control access to each knowledge base. Deploy a supervisor agent to perform natural language intent classification on patient inquiries. Configure the supervisor agent to route queries to specialized collaborator agents to respond to department-specific queries. Configure each specialized collaborator agent to use Retrieval Augmented Generation (RAG) with th

Create a separate supervisor agent for each department. Configure individual collaborator agents to perform natural language intent classification for each specialty domain within each department. Integrate each collaborator agent with department-specific knowledge bases only. Implement manual handoff processes between the supervisor agents.

Isolate data for each department in separate knowledge bases. Use IAM filtering to control access to each knowledge base. Deploy a single general-purpose agent. Configure multiple action groups within the general-purpose agent to perform specific department functions. Implement rule-based routing logic within the general-purpose agent instructions.

Implement multiple independent supervisor agents that run in parallel to respond to patient inquiries for each department. Configure multiple collaborator agents for each supervisor agent. Integrate all agents with the same knowledge base. Use external routing logic to merge responses from multiple supervisor agents.

Discussion 0

Question # 40

A software company is using Amazon Q Business to build an AI assistant that allows employees to access company information and personal information by using natural language prompts. The company stores this information in an Amazon S3 bucket.

Each department in the company has a dedicated prefix in the S3 bucket. Each object name includes the S3 prefix of the department that it belongs to. Each department can belong to only a single group in AWS IAM Identity Center. Each employee belongs to a single department.

The company configures Amazon Q Business to access data stored in an S3 bucket as a data source. The company needs to ensure that the AI assistant respects access controls based on the user ' s IAM Identity Center group membership.

Which solution will meet this requirement with the LEAST operational overhead?

Options:

Create a JSON file named acl.json in each department folder. In each file, create access control entries that specify the IAM Identity Center group that should have access to that department ' s data. Indicate the location of the JSON file in the Access Control section of the data source settings.

Create a single JSON file named acl.json at the top level of the S3 bucket. Add access control entries that map each department ' s S3 prefix to its corresponding IAM Identity Center group. Indicate the location of the JSON file in the Access Control section of the data source settings.

For each IAM Identity Center group, create a separate permissions set that denies access to all prefixes in the S3 bucket. Add a StringNotEquals condition key to the permissions set for each group that specifies the department each group is associated with. Attach the permissions sets to the Identity Center groups.

Create a metadata file named metadata.json at the top level of the S3 bucket. Add an AccessControlList object to the file that specifies the S3 path of each department ' s prefix. Specify the IAM Identity Center group that should have access to each department ' s prefix. Reference the file location in the data source metadata settings.

Discussion 0