A company has a generative AI application that uses a pre-trained foundation model (FM) on Amazon Bedrock. The company wants the FM to include more context by using company information.
Which solution meets these requirements MOST cost-effectively?
A. Use Amazon Bedrock Knowledge Bases.
B. Choose a different FM on Amazon Bedrock.
C. Use Amazon Bedrock Agents.
D. Deploy a custom model on Amazon Bedrock.
Show Answer
Correct Answer: A
Explanation: Using Amazon Bedrock Knowledge Bases is the most cost-effective way to add company-specific context to a pre-trained foundation model. It implements retrieval-augmented generation (RAG), allowing the model to pull relevant information from company data sources (such as Amazon S3) at inference time without retraining or fine-tuning, avoiding the higher cost and complexity of custom models, different FMs, or agents.
Question 101
A financial company has deployed an ML model to predict customer churn. The model has been running in production for 1 week. The company wants to evaluate how accurately the model predicts churn compared to actual customer behavior.
Which metric meets these requirements?
A. Root mean squared error (RMSE)
B. Return on investment (ROI)
C. F1 score
D. Bilingual Evaluation Understudy (BLEU) score
Show Answer
Correct Answer: C
Explanation: Customer churn prediction is a binary classification problem. To evaluate how well the model’s predictions match actual churn behavior, a classification metric is required. The F1 score is appropriate because it combines precision and recall, providing a balanced measure of performance, especially in churn scenarios where classes are often imbalanced. RMSE is for regression, ROI is a business metric rather than a model accuracy metric, and BLEU is used for evaluating text generation.
Question 102
A company is integrating AI into its employee recruitment and hiring solution. The company wants to mitigate bias risks and ensure responsible AI practices while prioritizing equitable hiring decisions.
Which core dimensions of responsible AI should the company consider? (Choose two.)
A. Fairness
B. Tolerance
C. Flexibility
D. Open source
E. Transparency
Show Answer
Correct Answer: A, E
Explanation: In AI-driven recruitment, Fairness is a core responsible AI dimension because it focuses on preventing discriminatory outcomes and ensuring equitable treatment across protected groups. Transparency is also fundamental, as it enables understanding and explainability of how hiring decisions are made, supports accountability, and helps identify and correct bias. The other options are not recognized core dimensions of responsible AI in this context.
Question 103
A company has developed custom computer vision models. The company needs a user-friendly interface for data labeling to minimize model mistakes on new real-world data.
Which AWS service, feature, or tool meets these requirements?
A. Amazon SageMaker Ground Truth
B. Amazon SageMaker Canvas
C. Amazon Bedrock playground
D. Amazon Bedrock Agents
Show Answer
Correct Answer: A
Explanation: The requirement is a user-friendly interface for labeling data to improve custom computer vision models. Amazon SageMaker Ground Truth is purpose-built for data labeling, offering web-based annotation UIs, support for image and video labeling tasks, human-in-the-loop workflows, and active learning to reduce errors and cost. The other options focus on no-code modeling (Canvas) or generative AI experimentation and orchestration (Bedrock playground and Agents), not data labeling.
Question 104
A company has set up a translation tool to help its customer service team handle issues from customers around the world. The company wants to evaluate the performance of the translation tool. The company sets up a parallel data process that compares the responses from the tool to responses from actual humans. Both sets of responses are generated on the same set of documents.
Which strategy should the company use to evaluate the translation tool?
A. Use the Bilingual Evaluation Understudy (BLEU) score to estimate the absolute translation quality of the two methods.
B. Use the Bilingual Evaluation Understudy (BLEU) score to estimate the relative translation quality of the two methods.
C. Use the BERTScore to estimate the absolute translation quality of the two methods.
D. Use the BERTScore to estimate the relative translation quality of the two methods.
Show Answer
Correct Answer: B
Explanation: The setup compares outputs from the translation tool against human translations on the same documents, which is a relative evaluation between two methods. BLEU is a standard metric designed to compare machine translation outputs to reference (human) translations and is commonly used to assess relative performance rather than absolute quality.
Question 105
An AI practitioner wants to generate more diverse and more creative outputs from a large language model (LLM).
How should the AI practitioner adjust the inference parameter?
A. Increase the temperature value.
B. Decrease the Top K value.
C. Increase the response length.
D. Decrease the prompt length.
Show Answer
Correct Answer: A
Explanation: Increasing the temperature increases randomness in token selection, encouraging the model to sample less probable tokens and thus produce more diverse and creative outputs. Other options do not directly increase creative variability.
Question 106
A company wants to control employee access to publicly available foundation models (FMs).
Which solution meets these requirements?
A. Analyze cost and usage reports in AWS Cost Explorer.
B. Download AWS security and compliance documents from AWS Artifact.
C. Configure Amazon SageMaker JumpStart to restrict discoverable FMs.
D. Build a hybrid search solution by using Amazon OpenSearch Service.
Show Answer
Correct Answer: C
Explanation: The requirement is to control employee access to publicly available foundation models. Amazon SageMaker JumpStart is the AWS service that exposes and manages access to foundation models, and it supports restricting which models are discoverable and usable through configuration and IAM permissions. The other options do not control model access: Cost Explorer is for billing analysis, AWS Artifact provides compliance documents, and OpenSearch is for search solutions.
Question 107
An ecommerce company wants to group customers based on their purchase history and preferences to personalize the user experience of the company's application.
Which ML technique should the company use?
A. Classification
B. Clustering
C. Regression
D. Content generation
Show Answer
Correct Answer: B
Explanation: The goal is to group customers based on similarities in purchase history and preferences without predefined labels. Clustering is an unsupervised machine learning technique designed for this purpose and is commonly used for customer segmentation and personalization. Classification requires labeled classes, regression predicts continuous values, and content generation is unrelated.
Question 108
An animation company wants to provide subtitles for its content.
Which AWS service meets this requirement?
A. Amazon Comprehend
B. Amazon Polly
C. Amazon Transcribe
D. Amazon Translate
Show Answer
Correct Answer: C
Explanation: Subtitles require converting spoken audio into text. Amazon Transcribe is AWS’s speech-to-text service designed to generate transcripts, captions, and subtitles from audio or video content. The other services focus on NLP (Comprehend), text-to-speech (Polly), or language translation (Translate).
Question 109
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.
Show Answer
Correct Answer: B
Explanation: Amazon Bedrock is designed so that customer prompts and model responses remain within the customer’s AWS environment. Inputs and outputs are not shared with third-party model providers and are not used to train or improve the underlying foundation models unless the customer explicitly opts in. This ensures confidentiality when analyzing sensitive or confidential data.
$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.