AIF-C01 AWS Certified AI Practitioner Free Practice Questions and Answers

A company is developing machine-learning models with Amazon SageMaker. Multiple teams need to share and manage the variables they use during model development. Which SageMaker feature best fits?

• A. Amazon SageMaker Feature Store
• B. Amazon SageMaker Data Wrangler
• C. Amazon SageMaker Clarify
• D. Amazon SageMaker Model Cards

An educational game asks users to calculate the chance of drawing a green marble from a jar containing six red, four green, and three yellow marbles. Which approach has the least operational overhead?

• A. Train a supervised regression model
• B. Train a reinforcement-learning model
• C. Calculate the probability with simple rules and computation
• D. Use unsupervised learning to estimate probability density

A company has a very large collection of unlabeled customer data and wants to group customers into tiers for an advertising campaign. Which learning approach is appropriate?

• A. Supervised learning
• B. Unsupervised learning
• C. Reinforcement learning
• D. Reinforcement learning from human feedback

A team is selecting a foundation model for a generative AI application on Amazon Bedrock. They need to know how much information can fit into a single prompt. Which model property should they compare?

• A. Temperature
• B. Context window
• C. Batch size
• D. Model size

A company wants to reduce the risk that common prompt-engineering attacks manipulate a conversational large language model into unsafe actions or disclosure. Which measure is most relevant?

• A. Use a prompt template that guides the model to detect attack patterns
• B. Increase the model temperature
• C. Use only models listed in Amazon SageMaker
• D. Reduce the number of input tokens