QUESTION 61
Which option is a disadvantage of using generative AI models in production systems?

A. Possible high accuracy and reliability
B. Deterministic and consistent behavior
C. Negligible computational resource requirements
D. Hallucinations and inaccuracies

Correct Answer: D

QUESTION 62
A company has developed a generative AI application by using Amazon Bedrock. The application produces catalogs that are updated weekly. The company needs to select a pricing model for weekly catalog updates. Which Amazon Bedrock pricing model meets these requirements MOST cost-effectively?

A. On-Demand
B. Provisioned Throughput
C. Batch
D. Model evaluation

Correct Answer: C

QUESTION 63
A company is using large language models (LLMs) to develop online tutoring applications. The company needs to apply configurable safeguards to the LIMs. These safeguards must ensure that the LLMs follow standard safety rules when creating applications. Which solution will meet these requirements with the LEAST effort?

A. Amazon Bedrock playgrounds
B. Amazon SageMaker Clarify
C. Amazon Bedrock Guardrails
D. Amazon SageMaker JumpStart

Correct Answer: C

QUESTION 64
A company needs to log all requests made to its Amazon Bedrock API. The company must retain the logs securely for 5 years at the lowest possible cost. Which combination of AWS service and storage class meets these requirements? (Select TWO.)

A. AWS CloudTrail
B. Amazon CloudWatch
C. AWS Audit Manager
D. Amazon S3 Intelligent-Tiering
E. Amazon S3 Standard

Correct Answer: AD

QUESTION 65
A financial company wants to flag all credit card activity as possibly fraudulent or non-fraudulent based on transaction data. Which type of ML model meets these requirements?

A. Regression
B. Diffusion
C. Binary classification
D. Multi-class classification

Correct Answer: C

QUESTION 66
A company built an AI chatbot. The chatbot uses large language models (LLMs) to answer user questions. The company wants to keep the chatbots LLM instructions private. Which security risk should the company consider?

A. Data poisoning
B. Prompt leakage
C. LLM hallucinations
D. Output ungroundedness

Correct Answer: B

QUESTION 67
A financial company is training a generative Al model to predict outcomes of loan applications. The training dataset is small. The dataset categorizes loan applicants as “younger-aged,” “middle-aged,” or “older-aged.” Most individuals in the dataset are characterized as “middle-aged. “The company removes the age range feature from the training dataset. Which model behavior will likely happen as a result of this change to the dataset?

A. The model will inaccurately predict outcomes for younger and older age groups.
B. The model will require less training data.
C. The model will predict accurate outcomes for only younger age groups.
D. The model will accurately predict outcomes for all ages.

Correct Answer: A

QUESTION 68
A company uses a third-party model on Amazon Bedrock to analyze confidential documents. The company is concerned about data privacy. Which statement describes how Amazon Bedrock protects data privacy?

A. User inputs and model outputs are anonymized and shared with third-party model providers.
B. User inputs and model outputs are not shared with any third-party model providers.
C. User inputs are kept confidential, but model outputs are shared with third-party model providers.
D. User inputs and model outputs are redacted before the inputs and outputs are shared with third-party model providers.

Correct Answer: B

QUESTION 69
What is an example of structured data?

A. A file of text comments from an online forum
B. A compilation of video files that contains news broadcasts
C. A CSV file that consists of measurement data
D. Transcribed conversations between call center agents and customers

Correct Answer: C

QUESTION 70
Which statement describes a generative AI use case for multimodal models?

A. Deploy multiple scalable and cost-effective versions of a model.
B. Process large amounts of data to train multiple models.
C. Write code in multiple programming languages.
D. Process different data types, such as images, audio, and videos.

Correct Answer: D

QUESTION 71
A company wants to use foundational models (FMs) to develop and deploy an AI model. Which AWS service or resource will meet these requirements with the LEAST development effort?

A. Amazon Bedrock
B. Amazon SageMaker AI
C. Amazon Bedrock PartyRock
D. Amazon Q Developer

Correct Answer: A

QUESTION 72
A company builds applications on AWS. The company wants to use a foundation model (FM) to improve developer productivity by reducing the amount of time to write application code. Which solution will meet these requirements?

A. Use Amazon Q Developer to generate real-time inline code suggestions.
B. Create an Amazon Bedrock knowledge base to generate real-time inline code suggestions.
C. Use Amazon CodeGuru to generate real-time inline code suggestions.
D. Use Amazon Personalize to generate real-time inline code suggestions.

Correct Answer: A

QUESTION 73
An AI practitioner is developing a new ML model. After training the model, the AI practitioner evaluates the accuracy of the model’s predictions. The model’s accuracy is low when the model uses both the training dataset and test dataset. Which scenario is the MOST likely cause of this problem?

A. Overfitting
B. Hallucination
C. Underfitting
D. Cross-validation

Correct Answer: C

QUESTION 74
A company wants to generate synthetic data responses for multiple prompts from a large volume of data. The company wants to use an API method to generate the responses. The company does not need to generate the responses immediately. Which solution meets these requirements with the LEAST development effort?

A. Input the prompts into the model. Generate responses by using real-time inference.
B. Use Amazon Bedrock batch inference. Generate responses asynchronously.
C. Use Amazon Bedrock agents. Build an agent system to process the prompts recursively.
D. Use AWS Lambda functions to automate the task. Submit one prompt after another and store each response.

Correct Answer: B

QUESTION 75
A company has developed a neural network model to replace an existing decision tree model. The neural network model has a higher prediction accuracy compared to the decision tree model. However, the neural network model’s decision process is not as explainable as the decision tree model’s decision process. Which tradeoff is the company making by adopting the neural network model?

A. Higher compliance for lower interpretability
B. Higher performance for lower portability
C. Higher performance for lower interpretability
D. Higher portability for lower interpretability

Correct Answer: C

QUESTION 76
A company is building a chatbot. The chatbot uses a large language model (LLM) and answers customer questions about products. The company wants the chatbot to answer only product questions. The company does not want the chatbot to answer questions about other topics. Which solution will meet these requirements with the LEAST operational overhead?

A. Set guardrails on the LLM prompt template.
B. Write custom application logic to identify questions about other topics.
C. Reduce the information the LLM can access.
D. Set the temperature parameter value to a lower number.

Correct Answer: A

QUESTION 77
A software company has deployed an AI model to translate paragraphs of text into a user’s chosen language. The model can produce a confidence score for the translations. The company wants to incorporate its employees into a review process to validate and improve the model’s translations. Which AWS solution will meet these requirements?

A. Amazon SageMaker Clarify
B. Amazon Augmented AI (Amazon A2I)
C. Amazon SageMaker Model Monitor
D. Amazon Bedrock Agents

Correct Answer: B

QUESTION 78
A company is integrating AI into its employee recruitment and hiring solution. The company wants to mitigate bias risks and ensure responsible Al practices while prioritizing equitable hiring decisions. Which core dimensions of responsible Al should the company consider? (Select TWO.)

A. Fairness
B. Tolerance
C. Flexibility
D. Open source
E. Transparency

Correct Answer: AE

QUESTION 79
A company is using Amazon Bedrock to build an assistant for its online store. The company wants to ensure that the assistant does not generate harmful responses based on hate speech, insults, sexual content, or violence. Which strategy will prevent harmful responses in Amazon Bedrock?

A. Use Amazon SageMaker built-in algorithms to filter harmful content.
B. Use Amazon Comprehend toxicity detection to identify harmful content.
C. Configure Guardrails for Amazon Bedrock to filter harmful content.
D. Train a custom model according to the company’s responsible AI policies.

Correct Answer: C

QUESTION 80
A company wants to use AI for budgeting. The company made one budget manually and one budget by using an AI model. The company compared the budgets to evaluate the performance of the AI model. The AI model budget produced incorrect numbers. Which option represents the AI model’s problem?

A. Hallucinations
B. Safety
C. Interpretability
D. Cost

Correct Answer: A