AIF-C01 Multiple Select — 20 Questions

Question 1

A company uses Amazon Macie to discover sensitive data in an S3 bucket containing training datasets. The bucket policy currently prohibits access from external accounts. Which TWO steps are necessary to allow a cross-account SageMaker training job to access this bucket while maintaining security?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Add a bucket policy that grants the SageMaker execution role from the other account s3:GetObject and s3:ListBucket permissions. For cross-account access, the bucket policy must grant the required permissions to the SageMaker execution role (from the other account), and the SageMaker execution role must have an IAM policy that allows it to access the S3 bucket. Macie doesn't control access. VPC endpoints are optional.

Answer

Configure Macie to automatically grant access to the SageMaker execution role

Answer

Create a VPC endpoint for S3 and associate it with the SageMaker VPC

Answer

Remove the bucket policy that prohibits external access

Question 2

A company is building a chatbot using Amazon Bedrock. They want to provide up-to-date information from a continuously changing database. Which TWO services can be used as a data source for a Bedrock knowledge base? (Select TWO.)

Accepted Answer

Amazon Kendra. Amazon Bedrock knowledge bases can directly ingest data from Amazon S3, which is a supported data source for indexing documents. Amazon Kendra is also a supported data source, allowing Bedrock to leverage existing Kendra indexes for retrieval-augmented generation (RAG). Both services integrate natively with Bedrock knowledge bases to provide up-to-date information from continuously changing data.

Answer

Amazon RDS for MySQL

Answer

Amazon DynamoDB

Answer

AWS Glue

Question 3

A data science team is using Amazon SageMaker to build a model. They want to ensure that only authorized users can deploy models to production. Which TWO methods can they use to enforce this?

Accepted Answer

Use SageMaker Model Registry to require approval before deployment.. SageMaker Model Registry allows you to set up an approval workflow for model versions. By requiring explicit approval before a model can be deployed to production, you enforce a governance gate that prevents unauthorized or unverified models from being used in production endpoints.

Answer

Enable multi-factor authentication (MFA) for all AWS accounts.

Answer

Use AWS CloudTrail to audit deployment actions.

Answer

Use Amazon GuardDuty to monitor for unauthorized deployment.

Question 4

A company is using Amazon Bedrock to generate content for a marketing application. The company wants to ensure that the model does not generate content that violates the company's brand guidelines, which prohibit certain keywords and tones. Which TWO features should the company use to enforce these guidelines? (Choose two.)

Accepted Answer

Create a prompt template that instructs the model to adhere to brand guidelines and avoid prohibited keywords.. Prompt engineering allows the company to embed brand guidelines directly into the instruction given to the model, effectively steering the output away from prohibited keywords and tones. Option C is correct because Amazon Bedrock Guardrails provides a managed, policy-based mechanism to define custom deny topics and content filters that can block or mask unwanted content at inference time, enforcing brand guidelines without manual intervention.

Answer

Enable Amazon CloudWatch Logs to capture model output and manually review.

Answer

Use AWS IAM policies to restrict the model's output to only approved words.

Answer

Encrypt the model responses using AWS KMS to prevent unauthorized viewing.

Question 5

A company needs to govern the lifecycle of ML models, including versioning, monitoring for drift, and decommissioning outdated models. Which TWO services should they use? (Choose 2)

Accepted Answer

Amazon SageMaker Model Registry. SageMaker Model Registry handles versioning and model approval; SageMaker Model Monitor tracks drift and performance.

Answer

AWS CloudTrail

Answer

Amazon S3

Answer

AWS CodePipeline

Question 6

A company is using Amazon Bedrock to deploy a chatbot. They want to ensure that the chatbot does not produce harmful or biased content. Which TWO AWS services or features can be used together to implement content moderation and monitoring?

Accepted Answer

Amazon Bedrock Guardrails for content filtering. Amazon Bedrock Guardrails (Option D) is correct because it provides built-in content filtering capabilities specifically designed for foundation models, allowing you to define denied topics, filter harmful content, and enforce safety policies directly within the Bedrock chatbot workflow. Amazon CloudWatch Logs (Option E) is correct because it enables you to log model inputs and outputs, which can be monitored for compliance, audited for bias, and used to trigger alerts when harmful content is detected. Together, they form a comprehensive content moderation and monitoring solution that addresses both proactive filtering and reactive analysis.

Answer

Amazon SageMaker Model Monitor for drift detection

Answer

Amazon Rekognition for image moderation

Answer

Amazon Comprehend for sentiment analysis

Question 7

A company is developing a generative AI application using Amazon Bedrock for code generation. They want to reduce costs without sacrificing throughput. Which THREE approaches can help achieve cost optimization?

Accepted Answer

Right-size model selection by choosing the smallest model that meets accuracy requirements. Batch inference processes multiple requests together at a lower cost. Model caching stores previous responses to avoid recomputation. Right-sizing model selection means picking the smallest capable model. Fine-tuning increases cost for custom models, and using larger models increases cost.

Answer

Always use the largest available model for best results

Answer

Fine-tune a large foundation model on the company's codebase

Question 8

A company is deploying an AI-based customer service chatbot using Amazon Lex and AWS Lambda. The company must ensure compliance with GDPR by allowing users to request deletion of their personal data collected during conversations. Which TWO actions should the company take? (Choose two.)

Accepted Answer

Use the Amazon Lex DeleteTranscript API to delete user conversation transcripts.. Amazon Lex provides the DeleteTranscript API, which allows the deletion of user conversation transcripts stored by Lex. This directly supports GDPR compliance by enabling the removal of personal data from conversation logs. The API targets the specific transcripts associated with a user, ensuring that their data is permanently deleted.

Answer

Apply an IAM policy that denies access to the conversation logs for the user who requested deletion.

Answer

Disable encryption of conversation logs to allow manual deletion.

Answer

Modify the Lex bot's conversation log settings to stop collecting personal data.

Question 9

Which TWO of the following are examples of supervised learning tasks that can be performed using Amazon SageMaker built-in algorithms?

Accepted Answer

XGBoost. XGBoost is a supervised learning algorithm that uses gradient-boosted decision trees for regression, classification, and ranking tasks. Amazon SageMaker's built-in XGBoost algorithm is optimized for distributed training and directly supports labeled training data, making it a correct example of a supervised learning task.

Answer

Principal Component Analysis (PCA)

Answer

Latent Dirichlet Allocation (LDA)

Answer

K-Means

Question 10

Which THREE statements about Amazon SageMaker Ground Truth are correct? (Choose three.)

Accepted Answer

It provides built-in workflows for image classification and object detection.. Amazon SageMaker Ground Truth provides built-in workflows for common tasks like image classification and object detection, which simplifies the setup of labeling jobs. These pre-built templates handle the UI and data formatting, allowing users to focus on the labeling instructions rather than building the labeling interface from scratch.

Answer

It can only be used for text data.

Answer

It can only use a public workforce from Amazon Mechanical Turk.

Question 11

A data scientist is preparing data for a classification model. The dataset contains missing values in several features. Which TWO approaches are appropriate for handling missing data? (Select TWO.)

Accepted Answer

Remove rows with any missing values. Imputation fills missing values with estimated values (e.g., mean, median, mode), allowing the model to use all samples. Removing rows with missing values is a simple deletion approach.

Answer

Set missing values to zero

Answer

Ignore missing values during training

Answer

Replace missing values with -1

Question 12

A data scientist is fine-tuning a foundation model on SageMaker. They want to prevent overfitting. Which THREE actions can help? (Select THREE.)

Accepted Answer

Apply dropout. Dropout is a regularization technique that randomly drops a fraction of neurons during training, which prevents the model from relying too heavily on specific features and reduces overfitting. In SageMaker, dropout can be applied via framework-specific APIs (e.g., `tf.keras.layers.Dropout` in TensorFlow) or by configuring the model architecture in the training script.

Answer

Increase the number of epochs

Answer

Use a smaller learning rate

Question 13

Which TWO practices help ensure transparency in AI systems? (Choose 2)

Accepted Answer

Use model-agnostic explainability tools like SHAP. Model-agnostic explainability tools like SHAP (SHapley Additive exPlanations) provide post-hoc explanations for any machine learning model by computing feature contributions based on cooperative game theory. This allows stakeholders to understand how each input feature influences a prediction, directly supporting transparency without requiring access to the model's internal structure.

Answer

Combine multiple models to obscure decision logic

Answer

Remove all features except the most predictive ones

Answer

Use black-box models to protect proprietary algorithms

Question 14

A company needs to select a vector store for their Amazon Bedrock Knowledge Base. Which TWO options are supported as vector stores? (Choose TWO.)

Accepted Answer

Amazon Aurora pgvector. Amazon Bedrock Knowledge Bases support Amazon OpenSearch Serverless, Aurora pgvector, Pinecone, and MongoDB Atlas. DynamoDB and Redshift are not vector stores.

Answer

Amazon Redshift

Answer

Amazon RDS for MySQL

Answer

Amazon DynamoDB

Question 15

A company is building a generative AI application to answer questions from a large set of technical manuals. Which TWO services or features can be used together in a RAG architecture on AWS? (Choose TWO.)

Accepted Answer

Amazon OpenSearch Serverless. A RAG architecture requires a knowledge base for indexing documents and a vector store for storing embeddings. Bedrock Knowledge Bases can use OpenSearch Serverless as a vector store. SageMaker is for training, not retrieval. Guardrails are safety layers. Lambda is for action groups, not core RAG components.

Answer

Amazon SageMaker

Answer

AWS Lambda

Answer

Amazon Bedrock Guardrails

Question 16

A company uses Amazon Bedrock Agents to automate a multi-step customer support workflow. The agent needs to query a customer database and update a ticket system. Which TWO components are required to enable the agent to interact with these external systems?

Accepted Answer

Lambda functions that implement the business logic for each action. Action groups define the functions the agent can call, and Lambda functions implement the business logic to interact with databases and APIs. Knowledge Bases provide static information, no tool use. Guardrails filter content, not execute actions. Vector stores store embeddings.

Answer

A vector store like Amazon OpenSearch Serverless

Answer

Bedrock Guardrails

Answer

Bedrock Knowledge Bases

Question 17

A developer is building an agent using Amazon Bedrock Agents to handle customer support inquiries. The agent needs to look up order status from a database and escalate complex issues to a human. Which THREE components are essential for this agent?

Accepted Answer

A Lambda function that connects to the database and returns results. An action group to query the database, a Lambda function to execute the query, and a knowledge base are essential. IAM roles are needed but not listed here. The other options are not required: fine-tuning is not needed, and custom models are optional.

Answer

A fine-tuned foundation model specific to the support domain

Answer

A custom model trained on historical support tickets

Question 18

A company uses an LLM to generate medical advice. They are concerned about hallucinations and want to implement safeguards. Which TWO techniques should they prioritize?

Accepted Answer

Implement Retrieval-Augmented Generation (RAG) using a verified medical knowledge base. RAG grounds the model in verified medical documents, and human-in-the-loop (A2I) provides oversight for high-risk outputs. Fine-tuning on general data is not sufficient to prevent hallucinations on specific medical topics. Temperature adjustment is a weak control. Stricter content filtering may help but is not specifically designed to address factual accuracy.

Answer

Reduce the temperature parameter to 0

Answer

Fine-tune the LLM on a general dataset of medical texts

Answer

Use Bedrock Guardrails with a content filter for medical topics

Question 19

A company wants to document their machine learning model's intended use, limitations, and ethical considerations. Which TWO practices should they adopt? (Choose two.)

Accepted Answer

Create a model card that describes the model's purpose, performance, and fairness metrics. Model cards provide structured documentation of model details, including intended use and limitations. SageMaker Model Cards support this. Data sheets document datasets. The other options are not documentation practices.

Answer

Automatically retrain the model weekly

Answer

Set up Amazon CloudWatch alarms to monitor model accuracy

Answer

Conduct A/B testing between different model versions

Question 20

A data science team is developing a credit scoring model and wants to ensure it meets fairness requirements. They measure the model's disparate impact and find it exceeds the 80% rule (adverse impact ratio >0.8). Which THREE actions should they consider to mitigate this? (Choose three.)

Accepted Answer

Apply a reweighing technique to assign higher weights to underrepresented groups in training. Reweighing, bias mitigation algorithms, and collecting more diverse data are standard techniques to address disparate impact. Removing protected attributes may not eliminate proxy variables, and only adjusting thresholds does not address root causes.

Answer

Remove protected attributes (e.g., gender, race) from the dataset

Answer

Adjust the decision threshold to increase approval rates for the disadvantaged group