The correct answer is C – Amazon Kendra, AWS’s enterprise search service designed for organizations with large, diverse document repositories. Kendra uses machine learning and natural language understanding (NLU) to provide semantic search, meaning it retrieves results based on meaning rather than keyword matching. According to AWS documentation, Kendra is ideal for educational, enterprise, and knowledge-management scenarios where users need fast, accurate retrieval across PDFs, HTML, Office documents, FAQs, and multimedia transcripts. Kendra connectors can index content from S3, SharePoint, LMS platforms, and internal databases, making it perfect for large volumes of training materials. Amazon Comprehend (A) is for NLP tasks like entity extraction, not enterprise search. Amazon Textract (B) extracts text from PDFs and scanned materials but does not provide search capabilities. Amazon Personalize (D) is for personalized recommendations, not document retrieval. Kendra is purpose-built for enterprise search and aligns directly with the company ' s needs.

Referenced AWS Documentation:

Amazon Kendra Developer Guide – Enterprise Search

AWS ML Specialty Guide – Intelligent Search Systems

AWS Glue is the correct service for transforming petabytes of unstructured data into a structured format suitable for machine learning tasks.

AWS Glue:

A fully managed extract, transform, and load (ETL) service that makes it easy to prepare and transform unstructured data into a structured format.

Provides a range of tools for cleaning, enriching, and cataloging data, making it ready for data scientists to use in ML models.

Why Option D is Correct:

Data Transformation: AWS Glue can handle large volumes of data and transform unstructured data into structured formats efficiently.

Integrated ML Support: Glue integrates with other AWS services to support ML workflows.

Why Other Options are Incorrect:

A. Amazon Lex: Used for building chatbots, not for data transformation.

B. Amazon Rekognition: Used for image and video analysis, not for data transformation.

C. Amazon Kinesis Data Streams: Handles real-time data streaming, not suitable for batch transformation of large volumes of unstructured data.

To achieve the lowest latency possible for inference on edge devices, deploying optimized small language models (SLMs) is the most effective solution. SLMs require fewer resources and havefaster inference times, making them ideal for deployment on edge devices where processing power and memory are limited.

Option A (Correct): " Deploy optimized small language models (SLMs) on edge devices " : This is the correct answer because SLMs provide fast inference with low latency, which is crucial for edge deployments.

Option B: " Deploy optimized large language models (LLMs) on edge devices " is incorrect because LLMs are resource-intensive and may not perform well on edge devices due to their size and computational demands.

Option C: " Incorporate a centralized small language model (SLM) API for asynchronous communication with edge devices " is incorrect because it introduces network latency due to the need for communication with a centralized server.

Option D: " Incorporate a centralized large language model (LLM) API for asynchronous communication with edge devices " is incorrect for the same reason, with even greater latency due to the larger model size.

AWS AI Practitioner References:

Optimizing AI Models for Edge Devices on AWS: AWS recommends using small, optimized models for edge deployments to ensure minimal latency and efficient performance.

Comprehensive and Detailed Explanation From Exact AWS AI documents:

Data retention policies define:

How long data is stored

When data must be deleted

How data lifecycle requirements are enforced

AWS data governance guidance identifies data retention as a core compliance and governance strategy.

Why the other options are incorrect:

De-identification (A) removes personal identifiers.

Data quality (B) focuses on accuracy and completeness.

Log storage (D) is a technical logging mechanism.

AWS AI document references:

AWS Data Governance Best Practices

Managing Data Lifecycles

Compliance and Retention Policies

AWS documentation for Amazon Bedrock explains that prompt engineering is a primary mechanism for controlling the behavior, tone, and style of foundation model outputs. Providing a persona and tone within the prompt allows organizations to align model responses with brand voice, customer expectations, and business values.

In this use case, the AI assistant’s responses risk damaging customer perception, which indicates a mismatch in tone, style, or personality, rather than a lack of knowledge. AWS explicitly states that prompts can include role definitions, communication style, formality level, and behavioral constraints to guide the model’s outputs. By defining a persona—such as “a professional, friendly company representative”—the model consistently generates responses that better represent the company.

Other options are less appropriate. Zero-shot prompting provides no additional guidance beyond the task itself and does not influence tone. Chain-of-thought prompting is designed to improve reasoning transparency, not brand alignment. Retrieval Augmented Generation (RAG) enhances factual accuracy by injecting external knowledge sources, but it does not inherently control tone or personality.

AWS highlights persona-based prompting as a best practice when building customer-facing generative AI applications, particularly chatbots and assistants. This approach improves consistency, reduces reputational risk, and ensures outputs align with organizational communication standards. Therefore, providing a persona and tone in the prompt is the most effective solution.

AWS documentation identifies hallucinations as a known limitation of generative AI models, particularly when used in business and production environments. Hallucinations occur when a model generates outputs that are unrelated, incorrect, fabricated, or unsupported by the input data or provided context. These outputs often appear confident and fluent, which can make them difficult to detect without additional validation.

Generative AI models, including large language models, operate using probabilistic token prediction based on patterns learned during training. AWS explains that these models do not have true reasoning or factual grounding unless explicitly provided with context or external knowledge. As a result, when prompts are ambiguous, incomplete, or outside the model’s training distribution, the model may produce responses that are irrelevant or misleading.

This behavior presents a risk for business use cases such as customer support, reporting, or decision-making systems. AWS highlights hallucinations as a key challenge that must be mitigated through techniques such as Retrieval Augmented Generation (RAG), prompt engineering, human review, and output validation.

The other options are not correct. Interpretability refers to the ability to understand model decisions, not incorrect outputs. Data bias relates to skewed or unfair training data. Nondeterminism refers to variability in outputs, not relevance or correctness.

AWS consistently categorizes hallucinations as a primary disadvantage of generative AI, making this the correct answer.

The scenario involves analyzing customer feedback and automatically classifying it into categories such as product quality, customer service, and delivery experience. This task requires processing and understanding textual data, which is a core application of natural language processing (NLP). NLP encompasses techniques for analyzing, interpreting, and generating human language, including tasks like text classification, sentiment analysis, and topic modeling, all of which are relevant to this use case.

Exact Extract from AWS AI Documents:

From the AWS AI Practitioner Learning Path:

" Natural Language Processing (NLP) enables machines to understand and process human language. Common NLP tasks include text classification, sentiment analysis, named entity recognition, and topic modeling. Services like Amazon Comprehend can be used to classify text into predefined categories based on content. "

(Source: AWS AI Practitioner Learning Path, Module on AI and ML Concepts)

Detailed Explanation:

Option A: Computer visionComputer vision involves processing and analyzing visual data, such as images or videos. Since the scenario deals with textual customer feedback, computer vision is not applicable.

Option B: Natural language processing (NLP)This is the correct answer. The task of classifying customer feedback into categories requires understanding and processing text, which is an NLP task. AWS services like Amazon Comprehend are specifically designed for such text classification tasks.

Option C: Recommendation systemsRecommendation systems suggest items or content based on user preferences or behavior. The scenario does not involve recommending products or services but rather classifying feedback, so this option is incorrect.

Option D: Fraud detectionFraud detection involves identifying anomalous or fraudulent activities, typically in financial or transactional data. The scenario focuses on text classification, not anomaly detection, making this option irrelevant.

Comprehensive and Detailed Explanation From Exact AWS AI documents:

To assess compliance, governance, and regulatory adherence throughout the ML application lifecycle, AWS recommends using services that provide audit evidence, configuration tracking, and activity logging.

AWS Audit Manager continuously evaluates AWS resource usage against predefined regulatory frameworks and internal controls, helping organizations demonstrate compliance.

AWS Config enables continuous monitoring and recording of AWS resource configurations, allowing organizations to assess whether resources comply with company policies.

AWS CloudTrail provides a complete audit trail of API calls and user actions, supporting traceability and regulatory investigations.

Together, these services provide end-to-end compliance assessment and monitoring across development and operational phases.

Why the other options are incorrect:

Amazon Inspector (C) focuses on vulnerability scanning, not governance or regulatory compliance.

Amazon CloudWatch (D) is primarily used for performance monitoring and logging, not compliance assessment.

AWS AI document references (for exact extracts):

AWS Governance, Risk, and Compliance (GRC) Overview

Auditing AI and ML Workloads on AWS

Security, Compliance, and Monitoring in AWS AI Systems

AWS PrivateLink enables private connectivity between your VPC and supported AWS services (like Amazon Bedrock) without sending traffic over the public internet.

CloudFront (A) is for CDN and content delivery, not private service connections.

AWS Glue (B) is for ETL/data catalog, not networking.

Lake Formation (C) provides governance for data lakes, not API network isolation.

???? Reference:

AWS Documentation – Access Amazon Bedrock with PrivateLink

The verified answer is D. Model deployment and inference. The question describes a trained model being made available to production applications through an API endpoint. That is deployment, and the runtime use of the model to answer queries is inference. AWS SageMaker documentation states that after training, you can get predictions, or inferences, from trained machine learning models, and SageMaker provides model deployment options to support ML inference needs. This directly matches the phrase “available to production applications through an API endpoint for runtime queries.”

Data preparation is incorrect because that phase happens before training. It includes collecting, cleaning, transforming, labeling, and preparing datasets so the model can learn from them. The question already says the model is trained, so the workflow has moved beyond data preparation.

Model training and tuning is incorrect because training and tuning are where the model learns patterns from data and hyperparameters may be adjusted to improve performance. The question is not describing learning, optimization, or retraining. It describes exposing the trained model to applications.

Model evaluation and validation is incorrect because evaluation checks whether the model meets quality, accuracy, fairness, safety, or business criteria before or during production use. The scenario does not describe testing the model; it describes making the model callable by production applications.

In the ML lifecycle, deploying a model means placing it into an environment where applications can send requests and receive predictions. Inference is the process of using the deployed model to generate outputs from new inputs. Because the company is exposing the trained model through an API endpoint for runtime queries, the activity is model deployment and inference.