A company is using Amazon SageMaker to deploy a model that identifies if social media posts contain certain topics. The company needs to show how different input features influence model behavior.
Which SageMaker feature meets these requirements?
A. SageMaker Canvas
B. SageMaker Clarify
C. SageMaker Feature Store
D. SageMaker Ground Truth
Show Answer
Correct Answer: B
Explanation: Amazon SageMaker Clarify is designed for model explainability and bias detection. It provides feature attribution (such as SHAP-based explanations) to show how input features influence individual predictions and overall model behavior. Canvas is a no-code ML tool, Feature Store manages ML features, and Ground Truth is for data labeling.
Question 165
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.
Explanation: RAG enhances an LLM using external knowledge sources. Zero-shot learning performs unseen tasks without examples. Few-shot learning uses a small number of examples for new tasks.
Question 166
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: Training on bias awareness and responsible AI directly addresses fairness by helping teams identify and mitigate bias, and supports explainability through responsible AI practices that emphasize transparency and interpretable AI systems. The other options focus on coding, security, or algorithmic depth rather than these governance and ethics requirements.
Question 167
An AI practitioner wants to evaluate ML models. The AI practitioner wants to provide explanations of model predictions to customers and stakeholders.
Which AWS service or feature will meet these requirements?
A. Amazon QuickSight
B. Amazon Comprehend
C. AWS Trusted Advisor
D. Amazon SageMaker Clarify
Show Answer
Correct Answer: D
Explanation: Amazon SageMaker Clarify is designed to evaluate machine learning models for bias and explainability. It provides feature attribution and explanations for model predictions, helping practitioners communicate model behavior to customers and stakeholders.
Question 168
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 finds patterns or structure in unlabeled data. Grouping customers based on purchase history is a clustering task, which is a classic unsupervised learning application. Classifying dogs vs. cats and predicting house prices are supervised learning tasks, while learning chess through trial and error is reinforcement learning.
Question 169
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: Directional stimulus prompting steers the model by providing guiding context or cues. For a chatbot that answers questions using public bank documents in Amazon Bedrock, supplying document-derived context in the prompt to ground responses aligns with directional stimulus prompting. Few-shot prompting is primarily for teaching a pattern via examples rather than grounding answers in provided documents.
Question 170
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: Amazon Bedrock offers Stable Diffusion 3.5 Large for text-to-image generation, making it suitable for creating illustrations from story text. Amazon Polly generates speech, Amazon Rekognition analyzes existing images rather than generating them, and Amazon Q Business is an enterprise assistant, not a text-to-image illustration service.
Question 171
A company wants to develop an AI assistant for employees to query internal data.
Which AWS service will meet this requirement?
A. Amazon Rekognition
B. Amazon Textract
C. Amazon Lex
D. Amazon Q Business
Show Answer
Correct Answer: D
Explanation: Amazon Q Business is purpose-built to provide a generative AI assistant for employees that can securely connect to internal enterprise data sources and answer natural language queries. Amazon Lex builds conversational interfaces but does not by itself provide enterprise knowledge retrieval across internal data. Rekognition is for image/video analysis, and Textract extracts text from documents.
Question 172
HOTSPOT
-
Select and order the steps from the following list to correctly describe the ML lifecycle for a new custom model. Select each step one time.
Show Answer
Correct Answer: Step 1: Define the business objective.
Step 2: Process the data.
Step 3: Develop and train the model.
Step 4: Deploy the model.
Explanation: A standard ML lifecycle starts by defining the business problem, then collecting/preparing data, followed by model development and training, and finally deployment.
Question 173
A company wants to build an AI assistant to provide responses to user queries. The AI assistant must evaluate specific data sources, query external APIs, generate response options, and compare and prioritize response options.
Which Amazon Bedrock feature or resource will meet these requirements?
A. Prompt Management
B. Response streaming
C. Knowledge Bases
D. Agents
Show Answer
Correct Answer: D
Explanation: Amazon Bedrock Agents are designed to orchestrate multi-step tasks for AI assistants. They can evaluate information from data sources, invoke external APIs through action groups, perform reasoning across steps, and generate, compare, and prioritize responses before returning an answer. Prompt Management only manages prompts, Response streaming only streams model output, and Knowledge Bases provide retrieval over data but do not orchestrate API calls and multi-step decision workflows.
$19
Get all 443 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.
