HOTSPOT
-
A company wants to improve multiple ML models.
Select the correct technique from the following list of use cases. Each technique should be selected one time or not at all.
Show Answer
Correct Answer: Enhancing the capabilities of an LLM using external sources:
Retrieval Augmented Generation (RAG)
Generalizing and making predictions on unseen tasks:
Zero-shot learning
Limited data for new tasks:
Few-shot learning
Explanation: RAG augments an LLM with external knowledge at inference time. Zero-shot learning handles tasks without task-specific examples. Few-shot learning adapts to new tasks using a small number of examples in the prompt.
Question 46
Which task describes a use case for intelligent document processing (IDP)?
A. Predict fraudulent transactions
B. Personalize product offerings
C. Analyze user feedback and perform sentiment analysis
D. Automatically extract and format data from scanned files
Show Answer
Correct Answer: D
Explanation: Intelligent Document Processing focuses on ingesting unstructured or semi-structured documents such as scanned images, PDFs, invoices, or forms and converting them into structured, usable data using OCR, NLP, and machine learning. Automatically extracting and formatting data from scanned files is a core IDP use case, whereas the other options relate to predictive analytics, personalization, or text analytics outside document-centric processing.
Question 47
A company is using AI to improve its services. The company needs to ensure that the AI system is fair and explainable. The company wants to require training for members of the AI system development team.
Which training will meet these requirements?
A. Training on advanced coding skills
B. Training on data privacy and encryption protocols
C. Training on bias awareness and responsible AI
D. Training on advanced ML algorithms
Show Answer
Correct Answer: C
Explanation: Ensuring fairness and explainability requires the development team to understand and mitigate bias and to follow responsible AI practices. Training on bias awareness and responsible AI directly addresses ethical design, transparency, and accountability, whereas coding skills, encryption, or advanced algorithms do not specifically ensure fair and explainable outcomes.
Question 47
A company is using Amazon Q Business to create an AI assistant. The company needs to restrict user interactions with the AI assistant to company-approved topics.
Which feature will meet these requirements?
A. Amazon Q Business Enterprise index
B. Amazon Q Business Starter index
C. Amazon Q Business application guardrails
D. Amazon Q index cross-account access
Show Answer
Correct Answer: C
Explanation: Amazon Q Business application guardrails are designed to control and restrict the AI assistant’s behavior and topics it can engage with, ensuring interactions stay within company-approved subject areas. The index options relate to data scope and deployment, not topic restrictions, and cross-account access controls access, not conversational boundaries.
Question 48
Which option is an example of unsupervised learning?
A. A model that groups customers based on their purchase history
B. A model that classifies images as dogs or cats
C. A model that predicts a house’s price based on various features
D. A model that learns to play chess by using trial and error
Show Answer
Correct Answer: A
Explanation: Unsupervised learning works with unlabeled data to discover underlying structure or patterns. Grouping customers based on their purchase history is a clustering task, which is a classic example of unsupervised learning. The other options involve supervised learning (classification or regression) or reinforcement learning.
Question 48
HOTSPOT
-
A company wants to build a new ML solution. The company already has data. The company needs to understand the ML lifecycle before building the solution.
Select and order the steps from the following list to correctly describe the ML lifecycle. Select each step one time.
Show Answer
Correct Answer: Step 1: Prepare the data for training.
Step 2: Train the model.
Step 3: Test the model.
Step 4: Deploy the model.
Explanation: The ML lifecycle starts by preparing and cleaning data, then training a model on that data, evaluating its performance through testing, and finally deploying the validated model to production.
Question 49
A bank is building a chatbot to answer customer questions about opening a bank account. The chatbot will use public bank documents to generate responses. The company will use Amazon Bedrock and prompt engineering to improve the chatbot’s responses.
Which prompt engineering technique meets these requirements?
A. Complexity-based prompting
B. Zero-shot prompting
C. Few-shot prompting
D. Directional stimulus prompting
Show Answer
Correct Answer: D
Explanation: The chatbot must generate answers grounded in public bank documents, and the company plans to improve responses using prompt engineering (not retraining). Directional stimulus prompting works by injecting external context—such as documents, policies, or reference text—directly into the prompt to steer and ground the model’s responses. This technique is commonly used in document-based Q&A scenarios with Amazon Bedrock. Few-shot prompting focuses on examples, not on providing source documents as context.
Question 49
HOTSPOT
-
A company wants to use ML to increase customer engagement and sales. The company has collected a large dataset that includes customer demographics, purchase history, browsing patterns, and product ratings.
Select the correct ML approach from the following list for each use case. Select each ML approach one time.
Show Answer
Correct Answer: Predict customer lifetime value (CLV): Regression
Identify likelihood of customer churn: Classification
Group customers by similar patterns: Clustering
Explanation: CLV is a continuous numeric prediction, which fits regression. Churn likelihood maps to churn vs. non-churn labels, which fits classification. Customer grouping without predefined labels is an unsupervised task, which fits clustering.
Question 50
A company is building a generative AI application on AWS. The application will help improve reading comprehension for students. The application must give students the ability to add illustrations to stories.
Which solution will meet this requirement?
A. Use Amazon Bedrock Stable Diffusion 3.5 Large to generate images based on text inputs.
B. Use Amazon Polly to create an audiobook based on story texts.
C. Use Amazon Rekognition to analyze image contents and detect text attributes.
D. Create a standard prompt template. Use Amazon Q Business to illustrate stories.
Show Answer
Correct Answer: A
Explanation: The requirement is to let students add illustrations to stories, which requires text-to-image generation. Amazon Bedrock Stable Diffusion 3.5 Large is a generative model designed to create images from text prompts. Amazon Polly generates audio, Amazon Rekognition analyzes existing images, and Amazon Q Business is not intended for image generation.
Question 50
An AI practitioner is developing a prompt for large language models (LLMs) in Amazon Bedrock. The AI practitioner must ensure that the prompt works across all Amazon Bedrock LLMs.
Which characteristic can differ across the LLMs?
A. Maximum token count
B. On-demand inference parameter support
C. The ability to control model output randomness
D. Compatibility with Amazon Bedrock Guardrails
Show Answer
Correct Answer: A
Explanation: Different foundation models available through Amazon Bedrock are built by different providers and have different architectures and context window sizes. As a result, the maximum token count (input plus output) that a model supports can vary across LLMs. Other aspects such as guardrails compatibility, randomness control, and on-demand inference are designed to be consistently supported through Bedrock’s unified API.
$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.
