Which AWS service or feature stores embeddings in a vector database for use with foundation models (FMs) and Retrieval Augmented Generation (RAG)?
A. Amazon SageMaker Ground Truth
B. Amazon OpenSearch Service
C. Amazon Transcribe
D. Amazon Textract
Show Answer
Correct Answer: B
Explanation: Amazon OpenSearch Service supports vector search and storage of high‑dimensional embeddings, enabling similarity search for Retrieval Augmented Generation (RAG) with foundation models. The other options focus on labeling (Ground Truth) or text extraction/transcription, not vector databases.
Question 71
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 help explain ML model predictions by providing feature attribution, bias detection, and model explainability reports that can be shared with customers and stakeholders. The other options do not provide model prediction explainability.
Question 72
HOTSPOT
-
An AI practitioner is determining the appropriate data type for various use cases.
Select the correct data type from the following list for each use case. Select each data type one time.
Show Answer
Correct Answer: Sentiment analysis for social media posts:
Text data
Traffic sign recognition for self-driving cars:
Image data
Optimize ad campaigns with demographics and purchase history:
Tabular data
Forecast stock prices from historical prices:
Time series data
Explanation: Sentiment analysis processes written language.
Traffic sign recognition relies on visual inputs.
Demographics and purchases are structured in rows and columns.
Stock prices are ordered over time and used for forecasting.
Question 73
An online media streaming company wants to give its customers the ability to perform natural language-based image search and filtering. The company needs a vector database that can help with similarity searches and nearest neighbor queries.
Which AWS service meets these requirements?
A. Amazon Comprehend
B. Amazon Personalize
C. Amazon Polly
D. Amazon OpenSearch Service
Show Answer
Correct Answer: D
Explanation: The requirement is a vector database that supports similarity search and nearest‑neighbor queries for natural‑language–based image search. Amazon OpenSearch Service provides built‑in k‑NN and vector search capabilities, allowing storage and querying of vector embeddings for images and text. The other options focus on NLP analysis, recommendations, or text‑to‑speech and do not function as vector databases.
Question 74
HOTSPOT
-
A company uses ML techniques to build applications.
Select the correct ML technique from the following list for each task. Select each ML technique one time.
Explanation: Checking whether an answer is correct is a yes/no decision. Predicting the number of species is predicting a numeric quantity. Determining a car model involves choosing among multiple possible categories.
Question 75
An AI practitioner who has minimal ML knowledge wants to predict employee attrition without writing code.
Which Amazon SageMaker feature meets this requirement?
A. SageMaker Canvas
B. SageMaker Clarify
C. SageMaker Model Monitor
D. SageMaker Data Wrangler
Show Answer
Correct Answer: A
Explanation: The requirement is to predict employee attrition without writing code and with minimal ML knowledge. Amazon SageMaker Canvas is a no-code/low-code ML service designed for business users to build models and generate predictions via a visual interface. The other options focus on bias detection (Clarify), monitoring deployed models (Model Monitor), or data preparation (Data Wrangler), not end-to-end no-code prediction.
Question 76
A company wants to learn about generative AI applications in an experimental environment.
Which solution will meet this requirement MOST cost-effectively?
A. Amazon Q Developer
B. Amazon SageMaker JumpStart
C. Amazon Bedrock PartyRock
D. Amazon Q Business
Show Answer
Correct Answer: C
Explanation: The requirement is to learn and experiment with generative AI in a low-risk, low-cost environment. Amazon Bedrock PartyRock is a free, no-code playground specifically designed for experimenting with generative AI applications powered by Bedrock foundation models. It is more cost-effective and purpose-built for learning than production-oriented services like Amazon Q Business, Amazon Q Developer, or SageMaker JumpStart.
Question 77
A company wants to create a chatbot to answer employee questions about company policies. Company policies are updated frequently. The chatbot must reflect the changes in near real time. The company wants to choose a large language model (LLM).
Which solution meets these requirements?
A. Fine-tune an LLM on the company policy text by using Amazon SageMaker.
B. Select a foundation model (FM) from Amazon Bedrock to build an application.
C. Create a Retrieval Augmented Generation (RAG) workflow by using Amazon Bedrock Knowledge Bases.
D. Use Amazon Q Business to build a custom Q App.
Show Answer
Correct Answer: C
Explanation: Company policies change frequently, so retraining or fine-tuning is inefficient. A Retrieval Augmented Generation (RAG) approach retrieves the latest policy documents at query time, ensuring near real-time accuracy. Amazon Bedrock Knowledge Bases manage ingestion, embedding, and synchronization of updated documents, making it the best fit.
Question 78
A company wants to create an AI solution to generate images and descriptions for a product catalog. The company needs to select a foundation model (FM) for this solution.
The company must consider the output types of each FM.
Which FM characteristic is the company evaluating?
A. Latency
B. Model size
C. Model customization
D. Modality
Show Answer
Correct Answer: D
Explanation: The company is evaluating what types of outputs the foundation model can produce (images and text descriptions). This characteristic is the model’s modality, which defines whether a model handles text, images, audio, or multiple output types.
Question 79
A financial services company must ensure that its generative AI-powered chatbot provides factual responses for regulatory compliance.
Which solution prevents the underlying foundation model (FM) from hallucinating?
A. Use AWS Config to query compliance metadata by using natural language.
B. Configure Amazon Bedrock Guardrails to evaluate user inputs and model responses.
C. Use Amazon Fraud Detector to detect potentially fraudulent online activities.
D. Use AWS Audit Manager to prepare IT audit and compliance reports.
Show Answer
Correct Answer: B
Explanation: Amazon Bedrock Guardrails are designed to enforce safety, compliance, and factuality controls on generative AI models. Guardrails can evaluate both user inputs and model outputs, apply content filters, grounding checks, and automated reasoning to reduce hallucinations and ensure responses are factual and compliant. The other options relate to compliance auditing, fraud detection, or configuration management and do not directly prevent LLM hallucinations.
$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.
