Domain adaptation fine-tuning involves training a foundation model (FM) further using a specific dataset that includes domain-specific terminology and content, such as scientific terms in research papers. This process allows the model to better understand and handle complex terminology, improving its performance on specialized tasks.
* Option B (Correct): "Use domain adaptation fine-tuning to adapt the FM to complex scientific terms": This is the correct answer because fine-tuning the model on domain-specific data helps it learn and adapt to the specific language and terms used in the research papers, resulting in better performance.
* Option A: "Use few-shot prompting to define how the FM can answer the questions" is incorrect because while few-shot prompting can help in certain scenarios, it is less effective than fine-tuning for handling complex domain-specific terms.
* Option C: "Change the FM inference parameters" is incorrect because adjusting inference parameters will not resolve the issue of the model's lack of understanding of complex scientific terminology.
* Option D: "Clean the research paper data to remove complex scientific terms" is incorrect because removing the complex terms would result in the loss of important information and context, which is not a viable solution.
AWS AI Practitioner References:
* Domain Adaptation in Amazon Bedrock: AWS recommends fine-tuning models with domain- specific data to improve their performance on specialized tasks involving unique terminology.

The verified answer is C. Memory. In Amazon Bedrock AgentCore, Memory is the feature designed to preserve conversational context and make an assistant remember relevant information across interactions.
AWS documentation states that AgentCore Memory supports both short-term and long-term memory. Short- term memory stores raw interactions that help the agent maintain context within a single session, while long- term memory automatically extracts and stores key insights from conversations across multiple sessions, including user preferences, important facts, and session summaries. This directly matches the requirement because the assistant must maintain context across multiple user interactions without the company building and operating its own memory infrastructure.
Option A. Gateway is incorrect because AgentCore Gateway is used to connect agents securely to tools, APIs, and enterprise services. It helps expose external capabilities to agents, but it does not provide persistent conversational context. Option B. Browser Tool is incorrect because the Browser Tool enables an agent to interact with websites or web-based workflows. It is useful for browser automation and web interaction, not memory retention. Option D. Code Interpreter is incorrect because Code Interpreter allows the agent to execute code for tasks such as calculations, file analysis, and data manipulation. It does not solve the requirement of remembering prior conversation details.
The key phrase in the question is "maintain context across multiple user interactions." That is exactly the purpose of AgentCore Memory. AWS also explains that long-term memory provides persistent storage for session-specific context, enabling agents to maintain continuity and personalization across interactions.
Therefore, when a conversational assistant needs continuity, personalization, and context retention without custom infrastructure management, the correct AgentCore feature is Memory.

Comprehensive and Detailed Explanation From Exact AWS AI documents:
Amazon Neptune is a fully managed graph database service optimized for storing and querying highly connected data.
AWS guidance highlights that graph databases are ideal for:
Fraud detection
Relationship analysis
Pattern discovery across entities such as users, transactions, and accounts Amazon Neptune supports popular graph models and enables ML-driven investigations by efficiently traversing relationships, which is critical for fraud pattern analysis.
Why the other options are incorrect:
OpenSearch (A) is optimized for search and log analytics.
Aurora (B) is a relational database, not graph-based.
MemoryDB (D) is an in-memory data store for low-latency workloads.
AWS AI document references:
Amazon Neptune Overview
Graph-Based Fraud Detection on AWS
Using Graph Databases for Investigations

AWS Glue is a serverless data integration service that enables users to extract, transform, and load (ETL) data. For a company with minimal programming experience, Amazon Q Developer provides an AI-powered assistant that can generate code, explain AWS services, and guide users through tasks like creating AWS Glue jobs. This makes it an ideal tool to help the company use AWS Glue effectively.
Exact Extract from AWS AI Documents:
From the AWS Documentation on Amazon Q Developer:
"Amazon Q Developer is an AI-powered assistant that helps developers by generating code, answering questions about AWS services, and providing step-by-step guidance for tasks such as building ETL pipelines with AWS Glue. It is designed to assist users with varying levels of expertise, including those with minimal programming experience." (Source: AWS Documentation, Amazon Q Developer Overview) Detailed Explanation:
Option A: Amazon Q Developer
This is the correct answer. Amazon Q Developer can assist the company by generating AWS Glue scripts, explaining Glue concepts, and providing guidance on setting up ETL jobs, which is particularly helpful for users with limited programming experience.
Option B: AWS Config
AWS Config is used for tracking and managing resource configurations and compliance, not for assisting with coding or using services like AWS Glue. This option is incorrect.
Option C: Amazon Personalize
Amazon Personalize is a machine learning service for building recommendation systems, not for assisting with data integration or AWS Glue. This option is irrelevant.
Option D: Amazon Comprehend
Amazon Comprehend is an NLP service for analyzing text, not for helping users write code or use AWS Glue.
This option does not meet the requirements.
References:
AWS Documentation: Amazon Q Developer Overview (https://aws.amazon.com/q/developer/) AWS Glue Developer Guide: Introduction to AWS Glue (https://docs.aws.amazon.com/glue/latest/dg/what-is- glue.html) AWS AI Practitioner Learning Path: Module on AWS Developer Tools and Services

Explanation:
SageMaker Model Registry, SageMaker Serverless interference
This question requires selecting the appropriate Amazon SageMaker feature for two distinct steps in the AI model lifecycle. Let's break down each step and evaluate the options:
Step 1: Managing different versions of the model
The goal here is to identify a SageMaker feature that supports version control and management of machine learning models. Let's analyze the options:
SageMaker Clarify: This feature is used to detect bias in models and explain model predictions, helping with fairness and interpretability. It does not provide functionality for managing model versions.
SageMaker Model Registry: This is a centralized repository in Amazon SageMaker that allows users to catalog, manage, and track different versions of machine learning models. It supports model versioning, approval workflows, and deployment tracking, making it ideal for managing different versions of a model.
SageMaker Serverless Inference: This feature enables users to deploy models for inference without managing servers, automatically scaling based on demand. It is focused on inference (predictions), not on managing model versions.
Conclusion for Step 1: The SageMaker Model Registry is the correct choice for managing different versions of the model.
Exact Extract Reference: According to the AWS SageMaker documentation, "The SageMaker Model Registry allows you to catalog models for production, manage model versions, associate metadata, and manage approval status for deployment." (Source: AWS SageMaker Documentation - Model Registry,
https://docs.aws.amazon.com/sagemaker/latest/dg/model-registry.html).
Step 2: Using the current model to make predictions
The goal here is to identify a SageMaker feature that facilitates making predictions (inference) with a deployed model. Let's evaluate the options:
SageMaker Clarify: As mentioned, this feature focuses on bias detection and explainability, not on performing inference or making predictions.
SageMaker Model Registry: While the Model Registry helps manage and catalog models, it is not used directly for making predictions. It can store models, but the actual inference process requires a deployment mechanism.
SageMaker Serverless Inference: This feature allows users to deploy models for inference without managing infrastructure. It automatically scales based on traffic and is specifically designed for making predictions in a cost-efficient, serverless manner.
Conclusion for Step 2: SageMaker Serverless Inference is the correct choice for using the current model to make predictions.
Exact Extract Reference: The AWS documentation states, "SageMaker Serverless Inference is a deployment option that allows you to deploy machine learning models for inference without configuring or managing servers. It automatically scales to handle inference requests, making it ideal for workloads with intermittent or unpredictable traffic." (Source: AWS SageMaker Documentation - Serverless Inference, https://docs.aws.
amazon.com/sagemaker/latest/dg/serverless-inference.html).
Why Not Use the Same Feature Twice?
The question specifies that each SageMaker feature or resource should be selected one time or not at all. Since SageMaker Model Registry is used for version management and SageMaker Serverless Inference is used for predictions, each feature is selected exactly once. SageMaker Clarify is not applicable to either step, so it is not selected at all, fulfilling the question's requirements.
References:
AWS SageMaker Documentation: Model Registry (https://docs.aws.amazon.com/sagemaker/latest/dg/model- registry.html) AWS SageMaker Documentation: Serverless Inference (https://docs.aws.amazon.com/sagemaker/latest/dg
/serverless-inference.html)
AWS AI Practitioner Study Guide (conceptual alignment with SageMaker features for model lifecycle management and inference) Let's format this question according to the specified structure and provide a detailed, verified answer based on AWS AI Practitioner knowledge and official AWS documentation. The question focuses on selecting an AWS database service that supports storage and queries of embeddings as vectors, which is relevant to generative AI applications.