AI Practitioner · 24% of the exam

Fundamentals of Generative AI: free practice questions

5 sample questions from our 14-question bank for this domain — answers and explanations included. These are the same scenario-based style as the real AWS exam.

1. A company wants an AWS generative AI coding assistant to help developers write, explain, and debug code. Which service is designed for this?

  • A. Amazon Q Developer✓ Correct
  • B. Amazon Macie
  • C. Amazon QuickSight
  • D. AWS Config
Explanation

Amazon Q Developer is the generative AI assistant for software development tasks — writing, explaining, and debugging code. Macie (B) discovers sensitive data in S3, QuickSight (C) is BI/dashboards, and Config (D) tracks resource configuration — none is a coding assistant.

2. Which AWS service provides access to a range of foundation models from multiple providers through a single managed API for building generative AI applications?

  • A. Amazon Bedrock✓ Correct
  • B. Amazon S3
  • C. Amazon EC2 Auto Scaling
  • D. AWS CloudTrail
Explanation

Amazon Bedrock offers foundation models from multiple providers (Anthropic, Meta, Amazon, and others) via one managed, serverless API. S3 (B) is object storage, EC2 Auto Scaling (C) manages compute capacity, and CloudTrail (D) logs API activity — none is the generative AI model service.

3. Which of the following is a typical, well-suited use case for generative AI? (Select the BEST answer)

  • A. Summarizing long documents and drafting first-pass content✓ Correct
  • B. Guaranteeing 100% factually verified legal rulings with no review
  • C. Performing exact financial ledger reconciliation requiring deterministic accuracy
  • D. Replacing all database transactions
Explanation

Summarization and drafting are core generative AI strengths. Options B and C require deterministic, verifiable correctness that generative models can't guarantee (they can hallucinate), so they need human review or traditional systems. Option D misapplies generative AI to transactional database work.

4. In a large language model, what is a TOKEN?

  • A. A unit of text (a word or sub-word) that the model processes; cost and context limits are measured in tokens✓ Correct
  • B. An IAM credential
  • C. A pixel in a generated image
  • D. A row in a DynamoDB table
Explanation

LLMs break text into tokens (words or sub-word pieces); usage/pricing and context-window limits are counted in tokens. Option B confuses it with a security credential, and options C and D describe unrelated image and database concepts.

5. A developer wants to quickly discover, evaluate, and deploy prebuilt foundation models within Amazon SageMaker. Which capability provides this?

  • A. Amazon SageMaker JumpStart✓ Correct
  • B. Amazon SageMaker Ground Truth only
  • C. Amazon CloudWatch Logs
  • D. AWS Trusted Advisor
Explanation

SageMaker JumpStart provides a hub of prebuilt foundation models and solutions you can evaluate and deploy quickly. Ground Truth (B) is for data labeling, CloudWatch Logs (C) is monitoring, and Trusted Advisor (D) gives account best-practice checks — none is the model hub.

9 more questions in this domain

Practice the full bank with instant grading, flashcards, and a timed mock exam.

Start practicing free