AIF-C01 Practice Test 20 — 15 Questions

Question 1

A company uses Amazon Rekognition to analyze images stored in an S3 bucket. The security team requires that all image analysis be logged to AWS CloudTrail for auditing. What is the minimum configuration needed to meet this requirement?

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

Accepted Answer

Enable CloudTrail data events for the S3 bucket to capture GetObject API calls. CloudTrail data events capture S3 object-level API operations such as GetObject, which is the API call made by Amazon Rekognition when it retrieves images from the S3 bucket for analysis. By enabling data events for the S3 bucket, every GetObject request is logged to CloudTrail, providing the audit trail the security team requires. Management events alone do not capture object-level operations, and S3 server access logs are not integrated with CloudTrail for auditing.

Answer

Enable Rekognition logging in the AWS Management Console

Answer

Enable CloudTrail management events for the S3 bucket

Answer

Enable S3 server access logs on the bucket

Question 2

A company wants to build a chatbot that responds to customer queries using a foundation model. They need low latency and want to avoid managing infrastructure. Which AWS service should they use?

Accepted Answer

Amazon Bedrock. Amazon Bedrock is a fully managed service that provides access to foundation models (FMs) from leading AI providers via a simple API, eliminating the need to manage underlying infrastructure. It is designed for building generative AI applications like chatbots with low latency, as it handles model hosting, scaling, and inference optimization automatically. This makes it the ideal choice for the company's requirement of low-latency responses without infrastructure management.

Answer

Amazon EC2

Answer

AWS Lambda

Answer

Amazon SageMaker

Question 3

Which THREE are SageMaker built-in algorithms suitable for regression tasks?

Accepted Answer

Linear Learner. Linear Learner (A) is a SageMaker built-in algorithm that supports both classification and regression; in regression mode it learns a linear function minimizing a chosen loss (e.g., squared error) on continuous targets. DeepAR (D) is a built-in supervised time-series forecasting algorithm that predicts continuous numeric values, so it is used for regression-style forecasting tasks. XGBoost (E) is a built-in gradient-boosted trees algorithm whose objective can be set to reg:squarederror or reg:logistic, making it suitable for regression on tabular data. K-Means (B) is an unsupervised clustering algorithm that groups data points and does not predict a continuous target, and PCA (C) is an unsupervised dimensionality-reduction algorithm, so neither belongs to regression tasks.

Answer

K-Means

Answer

PCA

Question 4

Which TWO of the following are types of feature scaling?

Accepted Answer

Standardization. Standardization (C) is a feature-scaling technique that transforms each feature to have a mean of 0 and a standard deviation of 1 (z-score, (x − μ)/σ), which is exactly what the question asks for. Normalization (Min-Max) (E) is also a feature-scaling method that rescales values into a fixed range, typically [0, 1], via (x − min)/(max − min). One-hot encoding (A) is a categorical-encoding technique that creates binary columns, not a scaling method. Principal Component Analysis (B) is a dimensionality-reduction technique that projects data onto principal components, not a scaling method. Binning (D) is a discretization technique that groups continuous values into bins, not a scaling method.

Answer

One-hot encoding

Answer

Principal Component Analysis (PCA)

Answer

Binning

Question 5

A healthcare company needs to use a foundation model for analyzing medical records while complying with HIPAA. They plan to use Amazon Bedrock. What should they do to meet HIPAA requirements?

Accepted Answer

All of the above. HIPAA compliance in Amazon Bedrock requires a combination of controls: using a HIPAA-eligible model in a region where AWS offers a Business Associate Addendum (BAA), enabling access logging for auditability, and encrypting data at rest and in transit. None of the individual options alone satisfy all HIPAA requirements; only the full set of controls ensures compliance.

Answer

Use a model that is HIPAA eligible in a region that supports BAA

Answer

Implement access logging for all API calls

Answer

Encrypt data at rest and in transit

Question 6

A machine learning team is fine-tuning a foundation model using Amazon SageMaker. They need to optimize training time and cost. Which approach should they take?

Accepted Answer

Use Parameter-Efficient Fine-Tuning (PEFT) techniques like LoRA. Parameter-Efficient Fine-Tuning (PEFT) techniques like LoRA (Low-Rank Adaptation) significantly reduce the number of trainable parameters by injecting low-rank matrices into the model layers, while keeping the original weights frozen. This drastically lowers memory usage and computational cost, enabling faster training and reduced GPU hours on SageMaker without sacrificing model quality.

Answer

Use a larger instance type with more vCPUs

Answer

Increase the batch size to the maximum possible

Answer

Use the full model weights and train on a single GPU

Question 7

A law firm uses a foundation model to draft legal briefs. To ensure accuracy, they want to ground the model's outputs in authoritative legal sources. They have a large database of prior case law and statutes stored in Amazon S3. The firm's IT team must implement a solution that reduces hallucinations while being cost-effective. The solution should allow the model to retrieve relevant documents and generate responses based on them. Which approach should they take?

Accepted Answer

Use Amazon Bedrock Agents to create a RAG application.. Amazon Bedrock Agents with a knowledge base can implement Retrieval-Augmented Generation (RAG): the agent retrieves relevant documents from S3 and uses them as context for the model, grounding responses and reducing hallucinations. Option A (fine-tuning) is expensive and does not guarantee grounding for all queries. Option B (manually attaching documents) is not scalable. Option C (using a larger model) increases cost without solving hallucination.

Answer

Fine-tune the model on the legal database.

Answer

Manually attach relevant documents to each prompt.

Answer

Use a larger foundation model with more parameters.

Question 8

A data science team is using SHAP values to explain a complex model. They notice that for a particular prediction, the SHAP value for feature 'age' is +0.3. What does this indicate?

Accepted Answer

The age feature increased the prediction by 0.3 units from the baseline. A SHAP value of +0.3 for the 'age' feature on a specific prediction means that, relative to the model's baseline (expected) output, the age feature pushed the prediction upward by 0.3 units. SHAP values are additive and local: they decompose a single prediction into per-feature contributions that sum to the difference between the prediction and the base value. The sign indicates direction, and the magnitude indicates the size of that feature's contribution for that instance.

Answer

The age feature is the most important feature globally

Answer

The age feature has a negative impact on the prediction

Answer

The age feature is causing bias in the model

Question 9

A team is using a prompt engineering technique where they provide a few examples of desired input-output pairs in the prompt to guide the model's response. Which technique are they using?

Accepted Answer

Few-shot prompting. Few-shot prompting (Option C) is the correct technique because it involves providing a small number of input-output examples within the prompt to condition the model on the desired task format and pattern. This approach helps the model generalize from the examples to produce accurate responses for new inputs, without requiring fine-tuning.

Answer

System prompting

Answer

Zero-shot prompting

Answer

Chain-of-thought prompting

Question 10

A company is using Amazon Bedrock to generate marketing copy. They want to ensure the model's responses are factually accurate and grounded in their proprietary knowledge base. Which feature should they use?

Accepted Answer

Retrieval Augmented Generation (RAG). Retrieval Augmented Generation (RAG) is the correct choice because it retrieves relevant documents from the company's proprietary knowledge base and provides them as context to the foundation model at inference time. This grounds the model's responses in factual, up-to-date information without modifying the underlying model weights, ensuring accuracy and reducing hallucinations.

Answer

Model customization

Answer

Fine-tuning

Answer

Prompt engineering

Question 11

A company wants to use Amazon SageMaker to train a model using a custom Docker container that has specific dependencies. The training code is stored in an S3 bucket. Which steps must be taken to run the training job?

Accepted Answer

Push the custom container to Amazon ECR and create a training job with the container URI. Amazon SageMaker requires custom Docker containers to be stored in Amazon Elastic Container Registry (ECR) to run training jobs. The container URI from ECR is specified in the `AlgorithmSpecification` parameter of the `CreateTrainingJob` API call, allowing SageMaker to pull and execute the container with the training code from S3. Option B correctly describes this mandatory workflow.

Answer

Install dependencies via SageMaker's lifecycle configuration instead of a custom container

Answer

Use SageMaker's built-in framework container and override the entry point

Answer

Upload the container to S3 and reference it in the training job

Question 12

A company is using Amazon SageMaker to train machine learning models on sensitive customer data. Which AWS service can be used to encrypt the data at rest in the S3 bucket used by SageMaker?

Accepted Answer

AWS Key Management Service (KMS). AWS Key Management Service (KMS) is the correct service because it provides managed encryption keys that can be used to enable server-side encryption (SSE-KMS) for Amazon S3 buckets. When SageMaker accesses training data from S3, it can use a customer-managed KMS key to encrypt data at rest, ensuring sensitive customer data remains protected. KMS integrates directly with S3 and SageMaker, allowing you to specify a KMS key in the SageMaker training job configuration.

Answer

AWS CloudHSM

Answer

AWS Secrets Manager

Answer

AWS Certificate Manager (ACM)

Question 13

A data scientist is evaluating different AWS services for building a machine learning pipeline. Which THREE components are part of Amazon SageMaker? (Select THREE.)

Accepted Answer

Notebook instances. Amazon SageMaker is a fully managed ML platform, and three of the listed items are native SageMaker capabilities. B (Notebook instances) is correct because SageMaker provides managed Jupyter notebook instances for data exploration, preprocessing, and model development. C (Ground Truth) is correct because SageMaker Ground Truth is the built-in data labeling service used to create high-quality training datasets, including with automated labeling and human review workflows. D (Model registry) is correct because SageMaker includes a model registry for cataloging, versioning, and managing trained models through approval and deployment stages. A (AWS Glue) is a separate ETL and data catalog service, and E (Amazon Athena) is a separate serverless query service for S3 data, so neither is a component of SageMaker.

Answer

AWS Glue

Answer

Amazon Athena

Question 14

A company uses Amazon Bedrock to generate marketing copy. They want to measure the quality of generated text compared to reference text. Which metric is most appropriate?

Accepted Answer

BLEU. BLEU (Bilingual Evaluation Understudy) is the most appropriate metric for evaluating the quality of generated text against reference text in tasks like machine translation and text generation. It measures n-gram precision between the generated and reference texts, making it ideal for assessing marketing copy generated by Amazon Bedrock.

Answer

F1 score

Answer

RMSE

Answer

Accuracy

Question 15

A team is evaluating a classification model. The confusion matrix shows: TP=80, FN=20, FP=10, TN=90. What is the precision?

Accepted Answer

0.89. Precision is calculated as TP / (TP + FP). Here, TP=80 and FP=10, so precision = 80 / (80 + 10) = 80 / 90 = 0.888..., which rounds to 0.89. This metric measures the proportion of positive identifications that were actually correct.

Answer

0.75

Answer

0.80

Answer

0.90