A documentary filmmaker wants to reach more viewers. The filmmaker wants to automatically add subtitles and voice-overs in multiple languages to their films.
Which combination of steps will meet these requirements? (Choose two.)
A. Use Amazon Transcribe and Amazon Translate to generate subtitles in other languages.
B. Use Amazon Textract and Amazon Translate to generate subtitles in other languages.
C. Use Amazon Polly to generate voice-overs in other languages.
D. Use Amazon Translate to generate voice-overs in other languages.
E. Use Amazon Textract to generate voice-overs in other languages.
Show Answer
Correct Answer: A, C
Explanation: To add multilingual subtitles, the filmmaker must first convert spoken audio into text and then translate it. Amazon Transcribe converts the film’s audio to text, and Amazon Translate translates that text into other languages. To add multilingual voice-overs, text must be converted into spoken audio, which is done by Amazon Polly. Amazon Translate does not generate audio, and Amazon Textract is for extracting text from documents and images, not media.
Question 81
A company wants to fine-tune an ML model that is hosted on Amazon Bedrock. The company wants to use its own sensitive data that is stored in private databases in a VPC. The data needs to stay within the company’s private network.
Which solution will meet these requirements?
A. Restrict access to Amazon Bedrock by using an AWS Identity and Access Management (IAM) service role.
B. Restrict access to Amazon Bedrock by using an AWS Identity and Access Management (IAM) resource policy.
C. Use AWS PrivateLink to connect the VPC and Amazon Bedrock.
D. Use AWS Key Management Service (AWS KMS) keys to encrypt the data.
Show Answer
Correct Answer: C
Explanation: The requirement is to keep sensitive data within the company’s private network while fine-tuning a model hosted on Amazon Bedrock. AWS PrivateLink provides private connectivity between a VPC and supported AWS services, including Bedrock, without traversing the public internet. IAM roles or resource policies control authorization but do not ensure network-level data isolation, and AWS KMS only encrypts data without addressing network exposure. Therefore, using AWS PrivateLink meets the requirement.
Question 82
Which option is an example of unsupervised learning?
A. Clustering data points into groups based on their similarity
B. Training a model to recognize images of animals
C. Predicting the price of a house based on the house’s features
D. Generating human-like text based on a given prompt
Show Answer
Correct Answer: A
Explanation: Unsupervised learning works with unlabeled data to discover patterns or structure. Clustering groups data points based on similarity without predefined labels, making it a classic unsupervised learning task. The other options involve supervised learning or generative modeling.
Question 83
A company is monitoring a predictive model by using Amazon SageMaker Model Monitor. The company notices data drift beyond a defined threshold. The company wants to mitigate a potentially adverse impact on the predictive model.
Which solution will meet these requirements?
A. Restart the SageMaker AI endpoint.
B. Adjust the monitoring sensitivity.
C. Re-train the model with fresh data.
D. Set up experiments tracking.
Show Answer
Correct Answer: C
Explanation: Data drift indicates the production input distribution no longer matches the training data, which can degrade model performance. The appropriate mitigation is to retrain the model using fresh, representative data to realign it with current patterns. Restarting endpoints, adjusting sensitivity, or tracking experiments do not address the root cause.
Question 84
A company has developed an ML model to approve or reject loan applications. The model’s decision-making process must be transparent and explainable to comply with regulatory requirements. The company must document the decision-making process for audit purposes.
Which solution will meet these requirements?
A. Amazon Textract
B. Amazon SageMaker Model Card
C. AWS Cloud Formation
D. Amazon Comprehend
Show Answer
Correct Answer: B
Explanation: Amazon SageMaker Model Cards are designed to document ML models for transparency and compliance. They capture model purpose, training data, evaluation metrics, explainability, bias and fairness considerations, and limitations, providing auditable documentation required for regulated use cases like loan approval decisions.
Question 85
HOTSPOT
-
Select the correct AI term from the following list for each statement. Each AI term should be selected one time.
Show Answer
Correct Answer: Simulates human problem-solving capabilities: AI
Applies data-driven learning techniques to make predictions: ML
Focuses on processing data through intricate neural networks: Deep learning
Explanation: AI is the broad field that mimics human intelligence.
ML is a subset of AI that learns from data to make predictions.
Deep learning is a subset of ML that uses multi-layer neural networks.
Question 86
A company deployed a model to production. After 4 months, the model inference quality degraded. The company wants to receive a notification if the model inference quality degrades. The company also wants to ensure that the problem does not happen again.
Which solution will meet these requirements?
A. Retrain the model. Monitor model drift by using Amazon SageMaker Clarify.
B. Retrain the model. Monitor model drift by using Amazon SageMaker Model Monitor.
C. Build a new model. Monitor model drift by using Amazon SageMaker Feature Store.
D. Build a new model. Monitor model drift by using Amazon SageMaker JumpStart.
Show Answer
Correct Answer: B
Explanation: The requirements are to detect and be notified of inference quality degradation and to prevent recurrence. Amazon SageMaker Model Monitor is designed to continuously monitor deployed models for data drift, concept drift, and quality issues, and can trigger alerts via CloudWatch/SNS when thresholds are breached. Retraining the model addresses the degradation and helps prevent future issues once drift is detected. Other options do not provide the appropriate production monitoring and alerting capabilities for inference quality drift.
Question 87
An ecommerce company is deploying a chatbot. The chatbot will give users the ability to ask questions about the company’s products and receive details on users’ orders. The company must implement safeguards for the chatbot to filter harmful content from the input prompts and chatbot responses.
Which AWS feature or resource meets these requirements?
A. Amazon Bedrock Guardrails
B. Amazon Bedrock Agents
C. Amazon Bedrock inference APIs
D. Amazon Bedrock custom models
Show Answer
Correct Answer: A
Explanation: Amazon Bedrock Guardrails are designed to apply safety controls to both user prompts and model responses, including filtering harmful or unsafe content, enforcing topic restrictions, and blocking specific words or phrases. This directly meets the requirement to safeguard chatbot inputs and outputs.
Question 88
A financial company has offices in different countries worldwide. The company requires that all API calls between generative AI applications and foundation models (FM) must not travel across the public internet.
Which AWS service should the company use?
A. AWS PrivateLink
B. Amazon Q
C. Amazon CloudFront
D. AWS CloudTrail
Show Answer
Correct Answer: A
Explanation: AWS PrivateLink provides private connectivity between VPCs and AWS services, ensuring that API calls between generative AI applications and foundation models stay on the AWS internal network and do not traverse the public internet. The other options do not provide private service-to-service network isolation.
Question 89
A design company is using a foundation model (FM) on Amazon Bedrock to generate images for various projects. The company wants to have control over how detailed or abstract each generated image appears
Which model parameter should the company modify?
A. Model checkpoint
B. Batch size
C. Generation step
D. Token length
Show Answer
Correct Answer: C
Explanation: In image generation models (such as diffusion-based FMs on Amazon Bedrock), the generation step or number of inference steps controls how many refinement iterations are applied. More steps produce more detailed, polished images, while fewer steps result in more abstract or rough outputs. The other options do not directly affect image detail.
$19
Get all 397 questions with detailed answers and explanations
Instant download HTML + PDF delivered the moment payment clears.
Secure Stripe checkout we never see or store your card details.
7-day refund if files are defective see our refund policy.
