Redeem Your Black Friday Code: 75% Off All Exam Bundles! Use coupon code below! - Ends in 0d 00h 00m 00s - Coupon code: discactive

Amazon Web Services AIF-C01 AWS Certified AI Practitioner Exam Exam Practice Test

Page: 1 / 46
Total 455 questions

AWS Certified AI Practitioner Exam Questions and Answers

Question 1

An ML research team develops custom ML models. The model artifacts are shared with other teams for integration into products and services. The ML team retains the model training code and data. The ML team wants to builk a mechanism that the ML team can use to audit models.

Which solution should the ML team use when publishing the custom ML models?

Options:

A.

Create documents with the relevant information. Store the documents in Amazon S3.

B.

Use AWS A] Service Cards for transparency and understanding models.

C.

Create Amazon SageMaker Model Cards with Intended uses and training and inference details.

D.

Create model training scripts. Commit the model training scripts to a Git repository.

Question 2

Which statement describes a generative AI use case for multimodal models?

Options:

A.

Deploy multiple scalable and cost-effective versions of a model.

B.

Process large amounts of data to train multiple models.

C.

Write code in multiple programming languages.

D.

Process different data types, such as images, audio, and videos.

Question 3

An AI practitioner is building a model to generate images of humans in various professions. The AI practitioner discovered that the input data is biased and that specific attributes affect the image generation and create bias in the model.

Which technique will solve the problem?

Options:

A.

Data augmentation for imbalanced classes

B.

Model monitoring for class distribution

C.

Retrieval Augmented Generation (RAG)

D.

Watermark detection for images

Question 4

A retail store wants to predict the demand for a specific product for the next few weeks by using the Amazon SageMaker DeepAR forecasting algorithm.

Which type of data will meet this requirement?

Options:

A.

Text data

B.

Image data

C.

Time series data

D.

Binary data

Question 5

A medical company is customizing a foundation model (FM) for diagnostic purposes. The company needs the model to be transparent and explainable to meet regulatory requirements.

Which solution will meet these requirements?

Options:

A.

Configure security and compliance by using Amazon Inspector.

B.

Generate simple metrics, reports, and examples by using Amazon SageMaker Clarify.

C.

Encrypt and secure training data by using Amazon Macie.

D.

Gather more data. Use Amazon Rekognition to add custom labels to the data.

Question 6

A company has implemented a generative AI solution to create personalized exercise routines for premium subscription users. The company offers free basic subscriptions and paid premium subscriptions. The company wants to evaluate the AI solution ' s return on investment over time.

Options:

A.

The average revenue per user (ARPU) over the past month

B.

The number of daily interactions by basic subscription users

C.

The conversion rate and the customer retention rate

D.

The decrease in the number of premium customer queries and issue volume

Question 7

A company needs to share a dataset with a third-party provider. The provider will use the dataset to create an ML model. Some fields in the dataset contain personally identifiable information (PII). The company needs a solution to share this dataset without exposing PII.

Which solution will meet these requirements?

Options:

A.

Apply data masking to all fields in the dataset.

B.

Apply data masking to the fields that contain PII in the dataset.

C.

Apply data encryption to all fields in the dataset.

D.

Apply data labeling to the fields that contain PII in the dataset.

Question 8

An ecommerce company is using Amazon Bedrock to convert product images into detailed text descriptions for the company ' s catalog.

Which AI model characteristic is required for this task?

Options:

A.

Multilanguage processing

B.

Multimodal capabilities

C.

Retrieval Augmented Generation (RAG)

D.

Sequence-to-sequence (seq2seq) architecture

Question 9

An AI practitioner wants to perform a contextual grounding check in Amazon Bedrock.

Which three components must the AI practitioner use?

Options:

A.

User query, model response, and grounding source

B.

API credentials, grounding source, and model response

C.

Amazon Bedrock console, SDK, and source

D.

Confidence score, user query, and filtering threshold

Question 10

A company evaluates a medical AI model by testing its predictions against a labeled dataset of radiology reports to measure diagnostic accuracy.

Which evaluation method is the company using?

Options:

A.

Cross-domain testing

B.

Domain-specific benchmark testing

C.

User engagement measurement

D.

Random sampling

Question 11

A company needs an automated solution to group its customers into multiple categories. The company does not want to manually define the categories. Which ML technique should the company use?

Options:

A.

Classification

B.

Linear regression

C.

Logistic regression

D.

Clustering

Question 12

Which option is a disadvantage of using generative AI models in production systems?

Options:

A.

Possible high accuracy and reliability

B.

Deterministic and consistent behavior

C.

Negligible computational resource requirements

D.

Hallucinations and inaccuracies

Question 13

Which type of AI model makes numeric predictions?

Options:

A.

Diffusion

B.

Regression

C.

Transformer

D.

Multi-modal

Question 14

A company wants to improve the accuracy of the responses from a generative AI application. The application uses a foundation model (FM) on Amazon Bedrock.

Which solution meets these requirements MOST cost-effectively?

Options:

A.

Fine-tune the FM.

B.

Retrain the FM.

C.

Train a new FM.

D.

Use prompt engineering.

Question 15

An ecommerce company is deploying a chatbot. The chatbot will give users the ability to ask questions about the company ' s products and receive details on users ' orders. The company must implement safeguards for the chatbot to filter harmful content from the input prompts and chatbot responses.

Which AWS feature or resource meets these requirements?

Options:

A.

Amazon Bedrock Guardrails

B.

Amazon Bedrock Agents

C.

Amazon Bedrock inference APIs

D.

Amazon Bedrock custom models

Question 16

A company wants to use language models to create an application for inference on edge devices. The inference must have the lowest latency possible.

Which solution will meet these requirements?

Options:

A.

Deploy optimized small language models (SLMs) on edge devices.

B.

Deploy optimized large language models (LLMs) on edge devices.

C.

Incorporate a centralized small language model (SLM) API for asynchronous communication with edge devices.

D.

Incorporate a centralized large language model (LLM) API for asynchronous communication with edge devices.

Question 17

A company needs to automate recurring compliance assessments for its AI workloads. The assessments must include documented evidence mapped to regulatory frameworks.

Which AWS service meets these requirements?

Options:

A.

AWS Audit Manager

B.

AWS Trusted Advisor

C.

AWS Secrets Manager

D.

Amazon Inspector

Question 18

A food service company wants to collect a dataset to predict customer food preferences. The company wants to ensure that the food preferences of all demographics are included in the data.

Options:

A.

Accuracy

B.

Diversity

C.

Recency bias

D.

Reliability

Question 19

A company wants to use an ML model to analyze customer reviews on social media. The model must determine if each review has a neutral, positive, or negative sentiment.

Options:

A.

Open-ended generation

B.

Text summarization

C.

Machine translation

D.

Classification

Question 20

A company has an ML model. The company wants to know how the model makes predictions. Which term refers to understanding model predictions?

Options:

A.

Model interpretability

B.

Model training

C.

Model interoperability

D.

Model performance

Question 21

A bank has fine-tuned a large language model (LLM) to expedite the loan approval process. During an external audit of the model, the company discovered that the model was approving loans at a faster pace for a specific demographic than for other demographics.

How should the bank fix this issue MOST cost-effectively?

Options:

A.

Include more diverse training data. Fine-tune the model again by using the new data.

B.

Use Retrieval Augmented Generation (RAG) with the fine-tuned model.

C.

Use AWS Trusted Advisor checks to eliminate bias.

D.

Pre-train a new LLM with more diverse training data.

Question 22

An AI practitioner performed continued pre-training on a foundation model (FM). After model deployment, the AI practitioner discovered that the model was exposing sensitive company information that was inadvertently included in the training data.

Which security risk does this scenario represent?

Options:

A.

Jailbreaking

B.

Data leakage

C.

Contextual grounding

D.

Prompt injection

Question 23

A company wants to classify human genes into 20 categories based on gene characteristics. The company needs an ML algorithm to document how the inner mechanism of the model affects the output.

Which ML algorithm meets these requirements?

Options:

A.

Decision trees

B.

Linear regression

C.

Logistic regression

D.

Neural networks

Question 24

An AI practitioner must fine-tune an open source large language model (LLM) for text categorization. The dataset is already prepared.

Which solution will meet these requirements with the LEAST operational effort?

Options:

A.

Create a custom model training job in PartyRock on Amazon Bedrock.

B.

Use Amazon SageMaker JumpStart to create a training job.

C.

Use a custom script to run an Amazon SageMaker AI model training job.

D.

Create a Jupyter notebook on an Amazon EC2 instance. Use the notebook to train the model.

Question 25

A company is building a mobile app for users who have a visual impairment. The app must be able to hear what users say and provide voice responses.

Which solution will meet these requirements?

Options:

A.

Use a deep learning neural network to perform speech recognition.

B.

Build ML models to search for patterns in numeric data.

C.

Use generative AI summarization to generate human-like text.

D.

Build custom models for image classification and recognition.

Question 26

What does an F1 score measure in the context of foundation model (FM) performance?

Options:

A.

Model precision and recall

B.

Model speed in generating responses

C.

Financial cost of operating the model

D.

Energy efficiency of the model ' s computations

Question 27

A company wants to implement a generative AI solution to improve its marketing operations. The company wants to increase its revenue in the next 6 months.

Which approach will meet these requirements?

Options:

A.

Immediately start training a custom FM by using the company’s existing data.

B.

Conduct stakeholder interviews to refine use cases and set measurable goals.

C.

Implement a prebuilt AI assistant solution and measure its impact on customer satisfaction.

D.

Analyze industry AI implementations and replicate the most successful features.

Question 28

An AI company periodically evaluates its systems and processes with the help of independent software vendors (ISVs). The company needs to receive email notifications when an ISV’s compliance reports become available.

Which AWS service can the company use to meet this requirement?

Options:

A.

AWS Audit Manager

B.

AWS Artifact

C.

AWS Trusted Advisor

D.

AWS Data Exchange

Question 29

A company wants to build an ML application.

Select and order the correct steps from the following list to develop a well-architected ML workload. Each step should be selected one time. (Select and order FOUR.)

• Deploy model

• Develop model

• Monitor model

• Define business goal and frame ML problem

Question # 29

Options:

Question 30

A company is deploying AI/ML models by using AWS services. The company wants to offer transparency into the models ' decision-making processes and provide explanations for the model outputs.

Options:

A.

Amazon SageMaker Model Cards

B.

Amazon Rekognition

C.

Amazon Comprehend

D.

Amazon Lex

Question 31

Which AI technique combines large language models (LLMs) with external knowledge bases to improve response accuracy?

Options:

A.

Reinforcement learning (RL)

B.

Natural language processing (NLP)

C.

Retrieval Augmented Generation (RAG)

D.

Transfer learning

Question 32

Which strategy evaluates the accuracy of a foundation model (FM) that is used in image classification tasks?

Options:

A.

Calculate the total cost of resources used by the model.

B.

Measure the model ' s accuracy against a predefined benchmark dataset.

C.

Count the number of layers in the neural network.

D.

Assess the color accuracy of images processed by the model.

Question 33

A company has terabytes of data in a database that the company can use for business analysis. The company wants to build an AI-based application that can build a SQL query from input text that employees provide. The employees have minimal experience with technology.

Which solution meets these requirements?

Options:

A.

Generative pre-trained transformers (GPT)

B.

Residual neural network

C.

Support vector machine

D.

WaveNet

Question 34

A medical company deployed a disease detection model on Amazon Bedrock. To comply with privacy policies, the company wants to prevent the model from including personal patient information in its responses. The company also wants to receive notification when policy violations occur.

Which solution meets these requirements?

Options:

A.

Use Amazon Macie to scan the model ' s output for sensitive data and set up alerts for potential violations.

B.

Configure AWS CloudTrail to monitor the model ' s responses and create alerts for any detected personal information.

C.

Use Guardrails for Amazon Bedrock to filter content. Set up Amazon CloudWatch alarms for notification of policy violations.

D.

Implement Amazon SageMaker Model Monitor to detect data drift and receive alerts when model quality degrades.

Question 35

A company has built a solution by using generative AI. The solution uses large language models (LLMs) to translate training manuals from English into other languages. The company wants to evaluate the accuracy of the solution by examining the text generated for the manuals.

Which model evaluation strategy meets these requirements?

Options:

A.

Bilingual Evaluation Understudy (BLEU)

B.

Root mean squared error (RMSE)

C.

Recall-Oriented Understudy for Gisting Evaluation (ROUGE)

D.

F1 score

Question 36

An ecommerce company wants to evaluate several foundation models (FMs) for a customer survey summarization task. The company has created an LLM-as-a-judge evaluation job in Amazon Bedrock.

Which built-in evaluation metric can the company use for this task?

Options:

A.

Context relevance

B.

Context coverage

C.

Faithfulness

D.

Root mean square error (RMSE)

Question 37

A company is using Amazon Bedrock to process vendor invoices. The company needs to obtain compliance documentation for submission to regulatory authorities.

Which AWS service meets these requirements?

Options:

A.

AWS Config

B.

Amazon Bedrock

C.

Amazon SageMaker AI

D.

AWS Artifact

Question 38

A company wants to make a chatbot to help customers. The chatbot will help solve technical problems without human intervention. The company chose a foundation model (FM) for the chatbot. The chatbot needs to produce responses that adhere to company tone.

Which solution meets these requirements?

Options:

A.

Set a low limit on the number of tokens the FM can produce.

B.

Use batch inferencing to process detailed responses.

C.

Experiment and refine the prompt until the FM produces the desired responses.

D.

Define a higher number for the temperature parameter.

Question 39

A company is using Amazon Bedrock to develop an AI assistant. The AI assistant will respond to customer questions about the company ' s products. The company conducts initial tests of the AI assistant. The company finds that the AI assistant ' s responses do not represent the company well and might damage customer perception.

The company needs a prompt engineering technique to improve the AI assistant ' s responses so that the responses better represent the company.

Which solution will meet this requirement?

Options:

A.

Use zero-shot prompting.

B.

Use chain-of-thought (CoT) prompting.

C.

Use Retrieval Augmented Generation (RAG).

D.

Provide a persona and tone in the prompt.

Question 40

A company is building a large language model (LLM) question answering chatbot. The company wants to decrease the number of actions call center employees need to take to respond to customer questions.

Which business objective should the company use to evaluate the effect of the LLM chatbot?

Options:

A.

Website engagement rate

B.

Average call duration

C.

Corporate social responsibility

D.

Regulatory compliance

Question 41

A company has deployed an AI application in production on AWS. The application ' s responses have become less accurate over time. The company needs a solution to send alerts when the application performance drifts.

Which AWS service or feature will meet this requirement?

Options:

A.

Amazon Augmented AI (Amazon A2I)

B.

Amazon SageMaker Model Monitor

C.

Amazon Rekognition

D.

AWS Trusted Advisor

Question 42

A company designed an AI-powered agent to answer customer inquiries based on product manuals.

Which strategy can improve customer confidence levels in the AI-powered agent ' s responses?

Options:

A.

Writing the confidence level in the response

B.

Including referenced product manual links in the response

C.

Designing an agent avatar that looks like a computer

D.

Training the agent to respond in the company ' s language style

Question 43

A company wants to use AI to protect its application from threats. The AI solution needs to check if an IP address is from a suspicious source.

Options:

A.

Build a speech recognition system.

B.

Create a natural language processing (NLP) named entity recognition system.

C.

Develop an anomaly detection system.

D.

Create a fraud forecasting system.

Question 44

A company is using Amazon Bedrock to answer questions. The Amazon Bedrock foundation model (FM) uses the company ' s internal documentation to respond to the questions. The documentation is updated frequently. The company needs a solution that avoids recurring costs for model training while keeping responses current.

Which solution will meet these requirements?

Options:

A.

Use Amazon Bedrock Knowledge Bases with Retrieval Augmented Generation (RAG) when responding to questions.

B.

Use Amazon Bedrock model customization to fine-tune the FM after each documentation update.

C.

Use prompt engineering with static examples embedded in the prompt that reference the initial documentation.

D.

Cache the previous responses and reuse the responses for similar questions without checking for documentation updates.

Question 45

A company is using Amazon SageMaker to develop AI models.

Select the correct SageMaker feature or resource from the following list for each step in the AI model lifecycle workflow. Each

SageMaker feature or resource should be selected one time or not at all. (Select TWO.)

SageMaker Clarify

SageMaker Model Registry

SageMaker Serverless Inference

Question # 45

Options:

Question 46

A company wants to use a large language model (LLM) to develop a conversational agent. The company needs to prevent the LLM from being manipulated with common prompt engineering techniques to perform undesirable actions or expose sensitive information.

Which action will reduce these risks?

Options:

A.

Create a prompt template that teaches the LLM to detect attack patterns.

B.

Increase the temperature parameter on invocation requests to the LLM.

C.

Avoid using LLMs that are not listed in Amazon SageMaker.

D.

Decrease the number of input tokens on invocations of the LLM.

Question 47

A media streaming platform wants to provide movie recommendations to users based on the users ' account history.

Options:

A.

Amazon Polly

B.

Amazon Comprehend

C.

Amazon Transcribe

D.

Amazon Personalize

Question 48

A company wants to customize a foundation model (FM). The company wants to understand the customization methods and data types that are available.

Select the correct customization method from the following list for each description. Select each customization method one time. (Select THREE.)

Customization methods:

• Continued pre-training

• Distillation

• Fine-tuning

Question # 48

Options:

Question 49

A financial company is creating an AI model for customer loan applications. The company wants to demonstrate the principles of human-centered design for explainable AI.

Which Amazon SageMaker AI feature meets these requirements?

Options:

A.

Amazon SageMaker Model Registry

B.

Amazon SageMaker Clarify

C.

Amazon SageMaker Pipelines

D.

Amazon SageMaker Feature Store

Question 50

A company wants to create an application to summarize meetings by using meeting audio recordings.

Select and order the correct steps from the following list to create the application. Each step should be selected one time or not at all. (Select and order THREE.)

• Convert meeting audio recordings to meeting text files by using Amazon Polly.

• Convert meeting audio recordings to meeting text files by using Amazon Transcribe.

• Store meeting audio recordings in an Amazon S3 bucket.

• Store meeting audio recordings in an Amazon Elastic Block Store (Amazon EBS) volume.

• Summarize meeting text files by using Amazon Bedrock.

• Summarize meeting text files by using Amazon Lex.

Options:

Question 51

A company is building a generative AI application to help customers make travel reservations. The application will process customer requests and invoke the appropriate API calls to complete reservation transactions.

Which Amazon Bedrock resource will meet these requirements?

Options:

A.

Agents

B.

Intelligent prompt routing

C.

Knowledge Bases

D.

Guardrails

Question 52

A company used Amazon Bedrock to build an AI assistant. The AI assistant received a user prompt that instructed the assistant to provide the guidelines that the company used to configure the assistant. The prompt also instructed the assistant to display the full text of the initial setup. The AI assistant revealed its system prompt in the response.

Which type of prompt attack has occurred?

Options:

A.

Jailbreak

B.

Prompt leakage

C.

Prompt injection

D.

Denied topic violation

Question 53

Which AWS service or feature can help an AI development team quickly deploy and consume a foundation model (FM) within the team ' s VPC?

Options:

A.

Amazon Personalize

B.

Amazon SageMaker JumpStart

C.

PartyRock, an Amazon Bedrock Playground

D.

Amazon SageMaker endpoints

Question 54

A media company uses three AI agents to automate content moderation. The three agents are a detector agent, a redactor agent, and an auditor agent.

Which mechanism ensures that the agents share flagged segment details and process tasks in the required order?

Options:

A.

Model Context Protocol (MCP) for tool integration

B.

Multi-agent communication patterns that use persistent memory

C.

Real-time video stream compression

D.

Dynamic adjustment of inference batch size

Question 55

A company is testing the security of a foundation model (FM). During testing, the company wants to get around the safety features and make harmful content.

Options:

A.

Fuzzing training data to find vulnerabilities

B.

Denial of service (DoS)

C.

Penetration testing with authorization

D.

Jailbreak

Question 56

An AI practitioner is developing a prompt for large language models (LLMs) in Amazon Bedrock. The AI practitioner must ensure that the prompt works across all Amazon Bedrock LLMs.

Which characteristic can differ across the LLMs?

Options:

A.

Maximum token count

B.

On-demand inference parameter support

C.

The ability to control model output randomness

D.

Compatibility with Amazon Bedrock Guardrails

Question 57

Which option is a benefit of ongoing pre-training when fine-tuning a foundation model (FM)?

Options:

A.

Helps decrease the model ' s complexity

B.

Improves model performance over time

C.

Decreases the training time requirement

D.

Optimizes model inference time

Question 58

A company is training ML models on datasets. The datasets contain some classes that have more examples than other classes. The company wants to measure how well the model balances detecting and labeling the classes.

Which metric should the company use?

Options:

A.

Accuracy

B.

Recall

C.

Precision

D.

F1 score

Question 59

A company wants to use Amazon Bedrock. The company needs to review which security aspects the company is responsible for when using Amazon Bedrock.

Options:

A.

Patching and updating the versions of Amazon Bedrock

B.

Protecting the infrastructure that hosts Amazon Bedrock

C.

Securing the company ' s data in transit and at rest

D.

Provisioning Amazon Bedrock within the company network

Question 60

A company wants to learn about generative AI applications in an experimental environment.

Which solution will meet this requirement MOST cost-effectively?

Options:

A.

Amazon Q Developer

B.

Amazon SageMaker JumpStart

C.

Amazon Bedrock PartyRock

D.

Amazon Q Business

Question 61

A company is building a generative AI (GenAI) application. The company wants to implement mechanisms to monitor and direct AI system behavior.

Which responsible AI dimension is the company applying?

Options:

A.

Fairness

B.

Explainability

C.

Controllability

D.

Safety

Question 62

An AI practitioner wants to generate a speech-to-speech agent that can receive audio input and respond with audio output in real time.

Which model type will meet these requirements?

Options:

A.

Decoder-only

B.

Encoder-only

C.

Transformer-based

D.

Diffusion

Question 63

A company has petabytes of unlabeled customer data to use for an advertisement campaign. The company wants to classify its customers into tiers to advertise and promote the company ' s products.

Which methodology should the company use to meet these requirements?

Options:

A.

Supervised learning

B.

Unsupervised learning

C.

Reinforcement learning

D.

Reinforcement learning from human feedback (RLHF)

Question 64

What is tokenization used for in natural language processing (NLP)?

Options:

A.

To encrypt text data

B.

To compress text files

C.

To break text into smaller units for processing

D.

To translate text between languages

Question 65

An education company is building a chatbot whose target audience is teenagers. The company is training a custom large language model (LLM). The company wants the chatbot to speak in the target audience’s language style by using creative spelling and shortened words.

Which metric will assess the LLM’s performance?

Options:

A.

F1 score

B.

BERTScore

C.

Recall-Oriented Understudy for Gisting Evaluation (ROUGE)

D.

Bilingual Evaluation Understudy (BLEU) score

Question 66

A company wants to create a chatbot to answer employee questions about company policies. Company policies are updated frequently. The chatbot must reflect the changes in near real time. The company wants to choose a large language model (LLM).

Options:

A.

Fine-tune an LLM on the company policy text by using Amazon SageMaker.

B.

Select a foundation model (FM) from Amazon Bedrock to build an application.

C.

Create a Retrieval Augmented Generation (RAG) workflow by using Amazon Bedrock Knowledge Bases.

D.

Use Amazon Q Business to build a custom Q App.

Question 67

A financial company is using ML to help with some of the company ' s tasks.

Which option is a use of generative AI models?

Options:

A.

Summarizing customer complaints

B.

Classifying customers based on product usage

C.

Segmenting customers based on type of investments

D.

Forecasting revenue for certain products

Question 68

Which use case is MOST suitable for a binary classification model?

Options:

A.

Providing multiple product recommendations to a customer based on the customer ' s previous purchases

B.

Determining product pricing

C.

Detecting spam emails

D.

Marketing products to customers based on customer demographics

Question 69

A financial company stores patterns of fraudulent behavior in a database. The company uses this data to conduct investigations.

The company wants to use a graph-based ML solution to develop an AI tool that helps with these investigations.

Which AWS service will meet these requirements?

Options:

A.

Amazon OpenSearch Service

B.

Amazon Aurora

C.

Amazon Neptune

D.

Amazon MemoryDB

Question 70

A pharmaceutical company wants to analyze user reviews of new medications and provide a concise overview for each medication. Which solution meets these requirements?

Options:

A.

Create a time-series forecasting model to analyze the medication reviews by using Amazon Personalize.

B.

Create medication review summaries by using Amazon Bedrock large language models (LLMs).

C.

Create a classification model that categorizes medications into different groups by using Amazon SageMaker.

D.

Create medication review summaries by using Amazon Rekognition.

Question 71

A company is building a customer service chatbot. The company wants the chatbot to improve its responses by learning from past interactions and online resources.

Which AI learning strategy provides this self-improvement capability?

Options:

A.

Supervised learning with a manually curated dataset of good responses and bad responses

B.

Reinforcement learning with rewards for positive customer feedback

C.

Unsupervised learning to find clusters of similar customer inquiries

D.

Supervised learning with a continuously updated FAQ database

Question 72

A financial services company has developed an AI model by using AWS. The AI model assists with reviewing customer loan applications. Because regulatory requirements require transparency, the company needs to be able to explain how the model makes its decisions.

Which AWS service or feature meets these requirements?

Options:

A.

Amazon SageMaker Clarify

B.

Amazon Rekognition

C.

Amazon Comprehend

D.

Amazon SageMaker Model Monitor

Question 73

An AI practitioner is determining the appropriate data type for various use cases.

Select the correct data type from the following list for each use case. Select each data type one time.

Question # 73

Options:

Question 74

What is the purpose of vector embeddings in a large language model (LLM)?

Options:

A.

Splitting text into manageable pieces of data

B.

Grouping a set of characters to be treated as a single unit

C.

Providing the ability to mathematically compare texts

D.

Providing the count of every word in the input

Question 75

A company wants to fine-tune an ML model that is hosted on Amazon Bedrock. The company wants to use its own sensitive data that is stored in private databases in a VPC. The data needs to stay within the company ' s private network.

Which solution will meet these requirements?

Options:

A.

Restrict access to Amazon Bedrock by using an AWS Identity and Access Management (IAM) service role.

B.

Restrict access to Amazon Bedrock by using an AWS Identity and Access Management (IAM) resource policy.

C.

Use AWS PrivateLink to connect the VPC and Amazon Bedrock.

D.

Use AWS Key Management Service (AWS KMS) keys to encrypt the data.

Question 76

An ecommerce company is developing a generative Al solution to create personalized product recommendations for its application users. The company wants to track how effectively the Al solution increases product sales and user engagement in the application.

Select the correct business metric from the following list for each business goal. Each business metric should be selected one time. (Select THREE.)

Average order value (AOV)

Click-through rate (CTR)

Retention rate

Options:

Question 77

A company is using Amazon SageMaker AI to develop AI/ML solutions. The company must use only approved data for model training. The AI/ML solutions must comply with company policy and ethical guidelines.

Which solution will meet these requirements?

Options:

A.

Amazon SageMaker Catalog

B.

Amazon SageMaker Clarify

C.

Amazon SageMaker Model Registry

D.

Amazon SageMaker Model Cards

Question 78

A financial company is building an ML model to classify fraudulent transactions based on customer data and transaction patterns. The company wants to evaluate the model’s performance. The company must ensure that the model makes correct predictions and minimizes false positives.

Which evaluation metric will meet these requirements?

Options:

A.

Accuracy

B.

R-squared

C.

F1 score

D.

Root mean squared error (RMSE)

Question 79

What does inference refer to in the context of AI?

Options:

A.

The process of creating new AI algorithms

B.

The use of a trained model to make predictions or decisions on unseen data

C.

The process of combining multiple AI models into one model

D.

The method of collecting training data for AI systems

Question 80

Which option is a benefit of using Amazon SageMaker Model Cards to document AI models?

Options:

A.

Providing a visually appealing summary of a model ' s capabilities.

B.

Standardizing information about a model ' s purpose, performance, and limitations.

C.

Reducing the overall computational requirements of a model.

D.

Physically storing models for archival purposes.

Question 81

A company wants to build an interactive application for children that generates new stories based on classic stories. The company wants to use Amazon Bedrock and needs to ensure that the results and topics are appropriate for children.

Which AWS service or feature will meet these requirements?

Options:

A.

Amazon Rekognition

B.

Amazon Bedrock playgrounds

C.

Guardrails for Amazon Bedrock

D.

Agents for Amazon Bedrock

Question 82

A company needs to monitor the performance of its ML systems by using a highly scalable AWS service.

Which AWS service meets these requirements?

Options:

A.

Amazon CloudWatch

B.

AWS CloudTrail

C.

AWS Trusted Advisor

D.

AWS Config

Question 83

A company is using a foundation model (FM) to create product descriptions. The model sometimes provides incorrect information.

Options:

A.

Toxicity

B.

Hallucinations

C.

Interpretability

D.

Deterministic outputs

Question 84

A company has a large amount of unlabeled data. The company wants to group the data based on feature similarities.

Which algorithm will meet this requirement?

Options:

A.

XGBoost

B.

K-means

C.

DeepAR forecasting

D.

Linear learner

Question 85

A digital devices company wants to predict customer demand for memory hardware. The company does not have coding experience or knowledge of ML algorithms and needs to develop a data-driven predictive model. The company needs to perform analysis on internal data and external data.

Which solution will meet these requirements?

Options:

A.

Store the data in Amazon S3. Create ML models and demand forecast predictions by using Amazon SageMaker built-in algorithms that use the data from Amazon S3.

B.

Import the data into Amazon SageMaker Data Wrangler. Create ML models and demand forecast predictions by using SageMaker built-in algorithms.

C.

Import the data into Amazon SageMaker Data Wrangler. Build ML models and demand forecast predictions by using an Amazon Personalize Trending-Now recipe.

D.

Import the data into Amazon SageMaker Canvas. Build ML models and demand forecast predictions by selecting the values in the data from SageMaker Canvas.

Question 86

A financial services company is deploying an AI customer support system to handle product inquiries. As the company adds new products and updates policies, the system must continue operating effectively without requiring rebuilding.

Which AI characteristic is required for this use case?

Options:

A.

Consistency across interaction channels

B.

Adaptability to incorporate updated information

C.

Transparency in generating responses

D.

Reliability in handling high-volume requests

Question 87

A bank is building a chatbot to answer customer questions about opening a bank account. The chatbot will use public bank documents to generate responses. The company will use Amazon Bedrock and prompt engineering to improve the chatbot ' s responses.

Which prompt engineering technique meets these requirements?

Options:

A.

Complexity-based prompting

B.

Zero-shot prompting

C.

Few-shot prompting

D.

Directional stimulus prompting

Question 88

A customer service team is developing an application to analyze customer feedback and automatically classify the feedback into different categories. The categories include product quality, customer service, and delivery experience.

Which AI concept does this scenario present?

Options:

A.

Computer vision

B.

Natural language processing (NLP)

C.

Recommendation systems

D.

Fraud detection

Question 89

A company is making a chatbot. The chatbot uses Amazon Lex and Amazon OpenSearch Service. The chatbot uses the company ' s private data to answer questions. The company needs to convert the data into a vector representation before storing the data in a database.

Which model type should the company use?

Options:

A.

Text completion model

B.

Instruction following model

C.

Text embeddings model

D.

Image generation model

Question 90

A hospital is developing an AI system to assist doctors in diagnosing diseases based on patient records and medical images. To comply with regulations, the sensitive patient data must not leave the country the data is located in.

Options:

A.

Data residency

B.

Data quality

C.

Data discoverability

D.

Data enrichment

Question 91

How can companies use large language models (LLMs) securely on Amazon Bedrock?

Options:

A.

Design clear and specific prompts. Configure AWS Identity and Access Management (IAM) roles and policies by using least privilege access.

B.

Enable AWS Audit Manager for automatic model evaluation jobs.

C.

Enable Amazon Bedrock automatic model evaluation jobs.

D.

Use Amazon CloudWatch Logs to make models explainable and to monitor for bias.

Question 92

A company wants to build and deploy ML models on AWS without writing any code.

Which AWS service or feature meets these requirements?

Options:

A.

Amazon SageMaker Canvas

B.

Amazon Rekognition

C.

AWS DeepRacer

D.

Amazon Comprehend

Question 93

An AI practitioner who has minimal ML knowledge wants to predict employee attrition without writing code. Which Amazon SageMaker feature meets this requirement?

Options:

A.

SageMaker Canvas

B.

SageMaker Clarify

C.

SageMaker Model Monitor

D.

SageMaker Data Wrangler

Question 94

A company uses foundation models (FMs) to automate daily tasks. An AI practitioner is creating system instructions that include context relevant to the tasks. The AI practitioner wants to save and reuse the instructions in daily interactions with FMs in Amazon Bedrock.

Which Amazon Bedrock solution will meet these requirements?

Options:

A.

Knowledge Bases

B.

Guardrails

C.

Playgrounds

D.

Prompt management

Question 95

A security company is using Amazon Bedrock to run foundation models (FMs). The company wants to ensure that only authorized users invoke the models. The company needs to identify any unauthorized access attempts to set appropriate AWS Identity and Access Management (IAM) policies and roles for future iterations of the FMs.

Which AWS service should the company use to identify unauthorized users that are trying to access Amazon Bedrock?

Options:

A.

AWS Audit Manager

B.

AWS CloudTrail

C.

Amazon Fraud Detector

D.

AWS Trusted Advisor

Question 96

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?

Options:

A.

Increase the temperature value.

B.

Decrease the Top K value.

C.

Increase the response length.

D.

Decrease the prompt length.

Question 97

A company wants to use a large language model (LLM) to generate product descriptions. The company wants to give the model example descriptions that follow a format.

Which prompt engineering technique will generate descriptions that match the format?

Options:

A.

Zero-shot prompting

B.

Chain-of-thought prompting

C.

One-shot prompting

D.

Few-shot prompting

Question 98

An AI practitioner has a database of animal photos. The AI practitioner wants to automatically identify and categorize the animals in the photos without manual human effort.

Which strategy meets these requirements?

Options:

A.

Object detection

B.

Anomaly detection

C.

Named entity recognition

D.

Inpainting

Question 99

A hospital wants to use a generative AI solution with speech-to-text functionality to help improve employee skills in dictating clinical notes.

Options:

A.

Amazon Q Developer

B.

Amazon Polly

C.

Amazon Rekognition

D.

AWS HealthScribe

Question 100

A company is building an AI application to automate business processes. The company uses a foundation model (FM) to support the application.

The company needs to select datasets to assess the quality of the AI model ' s behavior.

Which type of datasets will meet these requirements?

Options:

A.

Curated datasets that have had all outliers and correlations removed

B.

Synthetic datasets that have been generated by the newest FM

C.

Diverse datasets that cover various use cases and usage scenarios

D.

Randomized datasets that have arbitrary features and skewed distributions

Question 101

A financial services company is developing a generative AI (GenAI) application that handles customer information. The application must meet strict regulatory and compliance requirements. The company limits the amount of data collected and deletes training data after a defined retention period.

Which responsible AI dimension does this practice represent?

Options:

A.

Privacy and security

B.

Model transparency

C.

Fairness and bias reduction

D.

Explainability

Question 102

An airline company wants to use a generative AI model to convert a flight booking system from one coding language into another coding language. The company must select a model for this task.

Which criteria should the company use to select the correct generative AI model for this task?

Options:

A.

Syntax, semantic understanding, and code optimization capabilities

B.

Code generation speed and error handling capabilities

C.

Ability to generate creative content

D.

Model size and resource requirements

Question 103

A company that streams media is selecting an Amazon Nova foundation model (FM) to process documents and images. The company is comparing Nova Micro and Nova Lite. The company wants to minimize costs.

Options:

A.

Nova Micro uses transformer-based architectures. Nova Lite does not use transformer-based architectures.

B.

Nova Micro supports only text data. Nova Lite is optimized for numerical data.

C.

Nova Micro supports only text. Nova Lite supports images, videos, and text.

D.

Nova Micro runs only on CPUs. Nova Lite runs only on GPUs.

Question 104

A company has multiple datasets that contain historical data. The company wants to use ML technologies to process each dataset.

Select the correct ML technology from the following list for each dataset. Select each ML technology one time or not at all. (Select THREE.)

Computer vision

Natural language processing (NLP)

Reinforcement learning

Time series forecasting

Options:

Question 105

Which option is a use case for generative AI models?

Options:

A.

Improving network security by using intrusion detection systems

B.

Creating photorealistic images from text descriptions for digital marketing

C.

Enhancing database performance by using optimized indexing

D.

Analyzing financial data to forecast stock market trends

Question 106

A company is developing a mobile ML app that uses a phone ' s camera to diagnose and treat insect bites. The company wants to train an image classification model by using a diverse dataset of insect bite photos from different genders, ethnicities, and geographic locations around the world.

Which principle of responsible Al does the company demonstrate in this scenario?

Options:

A.

Fairness

B.

Explainability

C.

Governance

D.

Transparency

Question 107

An accounting firm wants to implement a large language model (LLM) to automate document processing. The firm must proceed responsibly to avoid potential harms.

What should the firm do when developing and deploying the LLM? (Select TWO.)

Options:

A.

Include fairness metrics for model evaluation.

B.

Adjust the temperature parameter of the model.

C.

Modify the training data to mitigate bias.

D.

Avoid overfitting on the training data.

E.

Apply prompt engineering techniques.

Question 108

Which THREE of the following principles of responsible AI are most critical to this scenario? (Choose 3)

* Explainability

* Fairness

* Privacy and security

* Robustness

* Safety

Options:

Question 109

A real estate company is developing an ML model to predict house prices by using sales and marketing data. The company wants to use feature engineering to build a model that makes accurate predictions.

Which approach will meet these requirements?

Options:

A.

Understand patterns by providing data visualization.

B.

Tune the model’s hyperparameters.

C.

Create or select relevant features for model training.

D.

Collect data from multiple sources.

Question 110

Sentiment analysis is a subset of which broader field of AI?

Options:

A.

Computer vision

B.

Robotics

C.

Natural language processing (NLP)

D.

Time series forecasting

Question 111

A company has built a chatbot that can respond to natural language questions with images. The company wants to ensure that the chatbot does not return inappropriate or unwanted images.

Which solution will meet these requirements?

Options:

A.

Implement moderation APIs.

B.

Retrain the model with a general public dataset.

C.

Perform model validation.

D.

Automate user feedback integration.

Question 112

Which prompting technique can protect against prompt injection attacks?

Options:

A.

Adversarial prompting

B.

Zero-shot prompting

C.

Least-to-most prompting

D.

Chain-of-thought prompting

Question 113

HOTSPOT

Select the correct AI term from the following list for each statement. Each AI term should be selected one time. (Select THREE.)

• AI

• Deep learning

• ML

Question # 113

Options:

Question 114

An AI practitioner is using an LLM-as-a-judge in Amazon Bedrock to evaluate the quality of agent responses in a production environment. The AI practitioner wants to apply a built-in metric that assesses how thoroughly the agent responses address all parts of each prompt or question.

Which metric will meet these requirements?

Options:

A.

Recall-Oriented Understudy for Gisting Evaluation (ROUGE)

B.

Completeness

C.

Following instructions

D.

Refusal

Question 115

Which term refers to the Instructions given to foundation models (FMs) so that the FMs provide a more accurate response to a question?

Options:

A.

Prompt

B.

Direction

C.

Dialog

D.

Translation

Question 116

An online learning company with large volumes of educational materials wants to use enterprise search. Which AWS service meets these requirements?

Options:

A.

Amazon Comprehend

B.

Amazon Textract

C.

Amazon Kendra

D.

Amazon Personalize

Question 117

A company runs a website for users to make travel reservations. The company wants an AI solution to help create consistent branding for hotels on the website. The AI solution needs to generate hotel descriptions for the website in a consistent writing style. Which AWS service will meet these requirements?

Options:

A.

Amazon Comprehend

B.

Amazon Personalize

C.

Amazon Rekognition

D.

Amazon Bedrock

Question 118

Select the correct prompt engineering technique from the following list for each description. Select each prompt engineering technique one time or not at all. (Select THREE.)

• Chain-of-thought prompting

• Few-shot prompting

• Role-based prompting

• Single-shot prompting

• Zero-shot prompting

Options:

Question 119

A large retail bank wants to develop an ML system to help the risk management team decide on loan allocations for different demographics.

What must the bank do to develop an unbiased ML model?

Options:

A.

Reduce the size of the training dataset.

B.

Ensure that the ML model predictions are consistent with historical results.

C.

Create a different ML model for each demographic group.

D.

Measure class imbalance on the training dataset. Adapt the training process accordingly.

Question 120

A company wants to classify images of different objects based on custom features extracted from a dataset.

Which solution will meet this requirement with the LEAST development effort?

Options:

A.

Use traditional ML algorithms with custom features extracted from the dataset.

B.

Use a pre-trained deep learning model and fine-tune the model on the dataset.

C.

Use a generative adversarial network (GAN) model to classify the images.

D.

Use a support vector machine (SVM) with manually engineered features for classification.

Question 121

A company is developing an ML model to predict customer churn.

Which evaluation metric will assess the model ' s performance on a binary classification task such as predicting chum?

Options:

A.

F1 score

B.

Mean squared error (MSE)

C.

R-squared

D.

Time used to train the model

Question 122

A company wants to create a chatbot that answers questions about human resources policies. The company is using a large language model (LLM) and has a large digital documentation base.

Which technique should the company use to optimize the generated responses?

Options:

A.

Use Retrieval Augmented Generation (RAG).

B.

Use few-shot prompting.

C.

Set the temperature to 1.

D.

Decrease the token size.

Question 123

Which AWS service helps select foundation models (FMs) for generative AI use cases?

Options:

A.

Amazon Personalize

B.

Amazon Bedrock

C.

Amazon Q Developer

D.

Amazon Rekognition

Question 124

A research company implemented a chatbot by using a foundation model (FM) from Amazon Bedrock. The chatbot searches for answers to questions from a large database of research papers.

After multiple prompt engineering attempts, the company notices that the FM is performing poorly because of the complex scientific terms in the research papers.

How can the company improve the performance of the chatbot?

Options:

A.

Use few-shot prompting to define how the FM can answer the questions.

B.

Use domain adaptation fine-tuning to adapt the FM to complex scientific terms.

C.

Change the FM inference parameters.

D.

Clean the research paper data to remove complex scientific terms.

Question 125

A company wants to use large language models (LLMs) with Amazon Bedrock to develop a chat interface for the company ' s product manuals. The manuals are stored as PDF files.

Which solution meets these requirements MOST cost-effectively?

Options:

A.

Use prompt engineering to add one PDF file as context to the user prompt when the prompt is submitted to Amazon Bedrock.

B.

Use prompt engineering to add all the PDF files as context to the user prompt when the prompt is submitted to Amazon Bedrock.

C.

Use all the PDF documents to fine-tune a model with Amazon Bedrock. Use the fine-tuned model to process user prompts.

D.

Upload PDF documents to an Amazon Bedrock knowledge base. Use the knowledge base to provide context when users submit prompts to Amazon Bedrock.

Question 126

A company built an AI-powered resume screening system. The company used a large dataset to train the model. The dataset contained resumes that were not representative of all demographics. Which core dimension of responsible AI does this scenario present?

Options:

A.

Fairness.

B.

Explainability.

C.

Privacy and security.

D.

Transparency.

Question 127

An animation company wants to provide subtitles for its content. Which AWS service meets this requirement?

Options:

A.

Amazon Comprehend

B.

Amazon Polly

C.

Amazon Transcribe

D.

Amazon Translate

Question 128

A bank uses an AI model to evaluate customer loan applications. After model deployment, the bank observes that customers who have very little credit history are flagged as high risk. These customers are flagged regardless of their income level.

Which training data characteristic caused this model bias?

Options:

A.

The training data included historical data for only the incomes of customers.

B.

The training data included historical data for only customers that have a long credit history.

C.

The training data was filtered to remove outliers based on customer income and credit history.

D.

The training data included historical data for only customers that have little or no credit history.

Question 129

A company wants to detect unauthorized API actions for foundation models (FMs) in Amazon Bedrock.

Which solution meets these requirements?

Options:

A.

Configure AWS CloudTrail to monitor API activity.

B.

Use AWS Trusted Advisor to monitor model input and output data.

C.

Create Amazon QuickSight dashboards to monitor row-level safety.

D.

Monitor user access by using Amazon Personalize.

Question 130

An AI practitioner is using Amazon Bedrock Prompt Management to create a reusable prompt. The prompt must be able to interact with external services by calling an external API. Which solution will meet this requirement?

Options:

A.

Use special tokens.

B.

Use a tools configuration.

C.

Use prompt variables.

D.

Use a stop sequence.

Question 131

A company is using a generative AI model to develop a digital assistant. The model ' s responses occasionally include undesirable and potentially harmful content. Select the correct Amazon Bedrock filter policy from the following list for each mitigation action. Each filter policy should be selected one time. (Select FOUR.)

• Content filters

• Contextual grounding check

• Denied topics

• Word filters

Options:

Question 132

A financial company is training a generative AI model to predict outcomes of loan applications. The training dataset is small. The dataset categorizes loan applicants as " younger-aged, " " middle-aged, " or " older-aged. " Most individuals in the dataset are characterized as " middle-aged. "

The company removes the age range feature from the training dataset.

Which model behavior will likely happen as a result of this change to the dataset?

Options:

A.

The model will inaccurately predict outcomes for younger and older age groups.

B.

The model will require less training data.

C.

The model will predict accurate outcomes for only younger age groups.

D.

The model will accurately predict outcomes for all ages.

Question 133

A financial company is building an AI assistant. The company wants to fine-tune a text-to-text foundation model (FM) to improve response tone.

Which data format will meet these requirements?

Options:

A.

CSV file that contains financial reporting numbers

B.

JSONL file that contains prompt-completion pairs

C.

Text file that contains sample responses that use the desired tone

D.

Microsoft Excel file that contains example AI assistant interactions

Question 134

A company is building a contact center application and wants to gain insights from customer conversations. The company wants to analyze and extract key information from the audio of the customer calls.

Which solution meets these requirements?

Options:

A.

Build a conversational chatbot by using Amazon Lex.

B.

Transcribe call recordings by using Amazon Transcribe.

C.

Extract information from call recordings by using Amazon SageMaker Model Monitor.

D.

Create classification labels by using Amazon Comprehend.

Question 135

A company wants to label training datasets by using human feedback to fine-tune a foundation model (FM). The company does not want to develop labeling applications or manage a labeling workforce. Which AWS service or feature meets these requirements?

Options:

A.

Amazon SageMaker Data Wrangler

B.

Amazon SageMaker Ground Truth Plus

C.

Amazon Transcribe

D.

Amazon Macie

Question 136

A company wants to improve multiple ML models.

Select the correct technique from the following list of use cases. Each technique should be selected one time or not at all. (Select THREE.)

Few-shot learning

Fine-tuning

Retrieval Augmented Generation (RAG)

Zero-shot learning

Options:

Page: 1 / 46
Total 455 questions