An online learning company with large volumes of education materials wants to use enterprise search.
Which AWS service meets these requirements?
A. Amazon Comprehend
B. Amazon Textract
C. Amazon Kendra
D. Amazon Personalize
Show Answer
Correct Answer: C
Explanation: Enterprise search over large volumes of documents is best handled by Amazon Kendra, a fully managed AWS service designed to index and search enterprise content. The other options focus on NLP analysis (Comprehend), document text extraction (Textract), or recommendations (Personalize), not search.
Question 16
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 video.
Show Answer
Correct Answer: D
Explanation: Multimodal generative AI models are designed to handle and generate across multiple data modalities, such as images, audio, text, and video. Processing different data types is the defining use case of multimodal models, whereas the other options describe scalability, training logistics, or general coding abilities.
Question 17
A company wants to use an ML model to analyze customer reviews on social media. The model must determine if each review has a neutral, positive, or negative sentiment.
Which model evaluation strategy will meet these requirements?
A. Open-ended generation
B. Text summarization
C. Machine translation
D. Classification
Show Answer
Correct Answer: D
Explanation: The task requires assigning each customer review to one of three predefined labels (positive, neutral, or negative). This is a sentiment analysis problem, which is a form of multiclass classification. Therefore, classification is the correct model evaluation strategy.
Question 17
What is continues pre-training?
A. The process of fine-tuning a pre-trained language model on labeled data for a specific task
B. The process of providing unlabeled data to a pre-trained language model to improve the model’s domain knowledge
C. The process of training a language model from the beginning on a specific dataset
D. The process of evaluating the performance of a pre-trained language model on a test set
Show Answer
Correct Answer: B
Explanation: Continuous pre-training (also called continued or domain-adaptive pre-training) refers to further training an already pre-trained language model on additional unlabeled text, often from a specific domain, to improve its domain knowledge and representations. It is not task-specific fine-tuning, training from scratch, or evaluation.
Question 18
Sentiment analysis is a subset of which broader field of AI?
A. Computer vision
B. Robotics
C. Natural language processing (NLP)
D. Time series forecasting
Show Answer
Correct Answer: C
Explanation: Sentiment analysis focuses on understanding and classifying opinions or emotions expressed in text, which requires processing and interpreting human language. This places it squarely within the field of Natural Language Processing (NLP).
Question 18
Which type of ML technique provides the MOST explainability?
A. Linear regression
B. Support vector machines
C. Random cut forest (RCF)
D. Neural network
Show Answer
Correct Answer: A
Explanation: Linear regression is generally the most explainable ML technique because its parameters (coefficients) have a direct, interpretable relationship with the input features and the output. Each coefficient quantifies the effect of a feature while holding others constant, making the model transparent and easy to reason about. In contrast, SVMs, random cut forests, and neural networks involve more complex, less interpretable decision mechanisms.
Question 19
HOTSPOT
-
A company is building an AI solution by using Amazon SageMaker AI. The company wants to use SageMaker AI features to facilitate application development.
Select the correct SageMaker AI feature from the following list for each use case. Select each feature one time.
Show Answer
Correct Answer: Determine the most suitable model to use for a business case:
Model Cards
Prepare data through a low-code or no-code interface:
Data Wrangler
Identify biases or imbalances in the data:
Clarify
Explanation: Model Cards document model intent, performance, and limitations to support model selection. Data Wrangler provides a low-code/no-code interface for data preparation. Clarify analyzes datasets and models to detect bias and class imbalance.
Question 19
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
Show Answer
Correct Answer: A
Explanation: The issue described is that the AI-generated budget contains incorrect numbers. Producing fabricated or incorrect outputs despite a clear task is characteristic of hallucinations, not safety, interpretability, or cost concerns.
Question 20
An AI practitioner is writing software code. The AI practitioner wants to quickly develop a test case and create documentation for the code.
Which solution will meet these requirements with the LEAST effort?
A. Upload the code to an online coding assistant.
B. Develop an application to use foundation models (FMs).
C. Use Amazon Q Developer in an integrated development environment (IDE).
D. Research and write test cases. Then, create test cases and add documentation.
Show Answer
Correct Answer: C
Explanation: Amazon Q Developer integrates directly into popular IDEs and can automatically generate test cases, explain code, and create documentation with minimal setup. This meets the requirement of quickly developing tests and documentation with the least effort compared to building custom solutions or doing the work manually.
Question 20
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
Show Answer
Correct Answer: A
Explanation: Amazon Bedrock provides fully managed access to multiple foundational models via APIs, enabling rapid development and deployment with minimal setup. It eliminates the need to build, train, or manage infrastructure compared to SageMaker, while PartyRock is a demo/prototyping tool and Amazon Q Developer targets developer productivity rather than custom AI model deployment.
$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.
