QUESTION 101
A company uses Amazon Bedrock to implement a generative AI assistant on a website. The AI assistant helps customers with product recommendations and purchasing decisions. The company wants to measure the direct impact of the AI assistant on sales performance. Which metric will meet these requirements?

A. The conversion rate of customers who purchase products after AI assistant interactions
B. The number of customer interactions with the AI assistant
C. Sentiment analysis scores from customer feedback after AI assistant interactions
D. Natural language understanding accuracy rates

Correct Answer: A

QUESTION 102
A financial institution is using Amazon Bedrock to develop an AI application. The application is hosted in a VPC. To meet regulatory compliance standards, the VPC is not allowed access to any internet traffic. Which AWS service or feature will meet these requirements?

A. AWS PrivateLink
B. Amazon Macie
C. Amazon CloudFront
D. Internet gateway

Correct Answer: A

QUESTION 103
A company wants to use Amazon Bedrock to build a generative AI application for product advertising. The company wants to customize a foundation model (FM) by using unlabeled data to make the model more specialized. Which model customization technique meets these requirements?

A. Fine-tuning
B. Retrieval Augmented Generation (RAG)
C. Continued pre-training
D. Prompt engineering

Correct Answer: C

QUESTION 104
A startup company is using AWS services for its software development lifecycle. The company wants to use generative AI services to optimize programming productivity and to decrease time to market for the company’s applications. Which combination of steps meets these requirements? (Select TWO.)

A. Use Amazon Comprehend notebooks to process data.
B. Use Amazon Q Developer for real-time code suggestions.
C. Use Amazon Fraud Detector for built-in security scans.
D. Use Amazon Q Developer for built-in security scans.
E. Use Amazon Rekognition for real-time code suggestions.

Correct Answer: ACE

QUESTION 105
A company is building a solution to predict risk by using generative AI. The company needs to understand and trust the automated solution before replacing previous manual processes. Which solution meets these requirements?

A. Model monitoring
B. Model training
C. Model explainability
D. Model inference evaluation

Correct Answer: C

QUESTION 106
A global company has built a generative AI application by using Amazon Bedrock foundation models (FMs). The company’s highest priority is cloud security. According to the AWS shared responsibility model, which option is the customer’s responsibility?

A. Access permissions and data encryption
B. Physical networking setup and configuration
C. Host operating system and virtualization
D. Security and compliance certifications

Correct Answer: A

QUESTION 107
A company is using a generative AI model that creates images based on multiple text prompts and image examples that users provide. The company wants the AI-generated images to closely match the image examples that users provide. Which prompt engineering technique meets these requirements?

A. Zero-shot prompting
B. Few-shot prompting
C. One-shot prompting
D. Tree-of-thought prompting

Correct Answer: B

QUESTION 108
A company is building a chatbot by using generative AI. The company wants to ensure that the chatbot is inclusive. Which solution will meet these requirements?

A. Use unbiased training data for fine-tuning.
B. Use Amazon Fraud Detector.
C. Use prompt templates to set up the prompt guidelines.
D. Set up agents and use Retrieval Augmented Generation (RAG).

Correct Answer: A

QUESTION 109
A company wants to deploy a generative Al application to help employees create images from text inputs. Which type of generative AI model meets this requirement?

A. Transformer-based model
B. Multi-class classification model
C. Regression model
D. Diffusion model

Correct Answer: D

QUESTION 110
A financial institution is using Amazon Bedrock to develop an AI application. The application is hosted in a VPC. To meet regulatory compliance standards, the VPC is not allowed access to any internet traffic. Which AWS service or feature will meet these requirements?

A. AWS PrivateLink
B. Amazon Macie
C. Amazon CloudFront
D. Internet gateway

Correct Answer: A

QUESTION 111
A company wants to use Amazon Bedrock to build a generative AI application for product advertising. The company wants to customize a foundation model (FM) by using unlabeled data to make the model more specialized. Which model customization technique meets these requirements?

A. Fine-tuning
B. Retrieval Augmented Generation (RAG)
C. Continued pre-training
D. Prompt engineering

Correct Answer: C

QUESTION 112
A startup company is using AWS services for its software development lifecycle. The company wants to use generative AI services to optimize programming productivity and to decrease time to market for the company’s applications. Which combination of steps meets these requirements? (Select TWO.)

A. Use Amazon Comprehend notebooks to process data.
B. Use Amazon Q Developer for real-time code suggestions.
C. Use Amazon Fraud Detector for built-in security scans.
D. Use Amazon Q Developer for built-in security scans.
E. Use Amazon Rekognition for real-time code suggestions.

Correct Answer: ACE

QUESTION 113
A company is building a solution to predict risk by using generative AI. The company needs to understand and trust the automated solution before replacing previous manual processes. Which solution meets these requirements?

A. Model monitoring
B. Model training
C. Model explainability
D. Model inference evaluation

Correct Answer: C

QUESTION 114
A global company has built a generative AI application by using Amazon Bedrock foundation models (FMs). The company’s highest priority is cloud security. According to the AWS shared responsibility model, which option is the customer’s responsibility?

A. Access permissions and data encryption
B. Physical networking setup and configuration
C. Host operating system and virtualization
D. Security and compliance certifications

Correct Answer: A

QUESTION 115
A company is using a generative AI model that creates images based on multiple text prompts and image examples that users provide. The company wants the AI-generated images to closely match the image examples that users provide. Which prompt engineering technique meets these requirements?

A. Zero-shot prompting
B. Few-shot prompting
C. One-shot prompting
D. Tree-of-thought prompting

Correct Answer: B

QUESTION 116
A company is developing an ML model to predict customer churn. Which evaluation metric will assess the model’s performance on a binary classification task such as predicting churn?

A. F1 score
B. Mean squared error (MSE)
C. R-squared
D. Time used to train the model

Correct Answer: A

QUESTION 117
A company is using prompt engineering to provide customized outputs for text generation. The company needs the model to generate responses that use industry-specific jargon and technical terms. The company has a small amount of unlabeled data and must use this data to customize the model. The solution must use minimal computational resources. Which solution will meet these requirements?

A. Pre-train a new LLM based on the unlabeled data.
B. Perform domain adaptation fine-tuning on the existing model.
C. Perform instruction-based fine-tuning based on the unlabeled data.
D. Fine-tune prompt templates.

Correct Answer: B

QUESTION 118
A company’s large language model (LLM) is experiencing hallucinations. How can the company decrease hallucinations?

A. Set up Agents for Amazon Bedrock to supervise the model training.
B. Use data pre-processing and remove any data that causes hallucinations.
C. Decrease the temperature inference parameter for the model.
D. Use a foundation model (FM) that is trained to not hallucinate.

Correct Answer: C

QUESTION 119
An AI practitioner has a database of animal photos. The Al practitioner wants to automatically identify and categorize the animals in the photos without manual human effort. Which strategy meets these requirements?

A. Object detection
B. Anomaly detection
C. Named entity recognition
D. Inpainting

Correct Answer: A

QUESTION 120
A company is implementing intelligent agents to provide conversational search experiences for its customers. The company needs a database service that will support storage and queries of embeddings from a generative AI model as vectors in the database. Which AWS service will meet these requirements?

A. Amazon Athena
B. Amazon Aurora PostgreSQL
C. Amazon Redshift
D. Amazon EMR

Correct Answer: B