Skip to content
BytePatterns
Foundational · AIF-C01Prep available

AWS Certified AI Practitioner (AIF-C01) practice exam and study path

A free, timed 65-question AIF-C01 practice exam — 90 minutes, the same length as the real exam, scored by domain, with every option explained after you submit. Also 135 practice questions you can check one at a time, a page for every task in the exam guide, and a study path. No sign-up.

Start the free practice examGet the exam packPractise question by question →
AI Practitioner exam pack:

$19once

The foundational AI exam: machine learning and generative AI concepts, where each AWS AI service fits, and how to use them responsibly.

The exam

Exam code
AIF-C01
Questions
65 questions (50 scored)
Time
90 minutes
Passing score
700 of 1,000 (scaled)
Exam fee
$100 (USD)
Question types
multiple choice, multiple response, ordering, matching

From AWS's certification page and exam guide, checked Oct 6, 2026. The exam is scored as a whole (compensatory): there is no pass mark per domain.

Domains and weights

  • Domain 1: Fundamentals of AI and ML

    20%

  • Domain 2: Fundamentals of GenAI

    24%

  • Domain 3: Applications of Foundation Models

    28%

  • Domain 4: Guidelines for Responsible AI

    14%

  • Domain 5: Security, Compliance, and Governance for AI Solutions

    14%

On our roadmap this comes after Cloud Practitioner. See the whole roadmap.

Practice

135 original practice questions, every option explained with the AWS documentation page that proves it. Free, no sign-up; progress stays on this device.

Your results on this device →

More practice exams

The lessons, the sample questions on every task page and the first full practice exam are free and stay free. A pack adds the further timed AIF-C01 practice exams.

AI Practitioner exam pack

$19once

  • Every paid AIF-C01 practice exam, timed, with every option explained
  • The next version of this exam included when it changes
  • Lifetime access — one payment, no subscription
  • 14-day refund, no conditions
  • 14-day refund, no conditions: ask within 14 days of buying and you get the whole payment back.
  • No pass guarantee. These are practice exams written by us from the exam guide and the AWS documentation; a score here does not predict your result on the real exam.

Study path

One module per exam domain. Lessons that already exist on BytePatterns are linked; the rest are being written.

  1. Module 1: Fundamentals of AI and ML

    1. 1AI, ML, deep learning, generative AI and agentic AI: how the terms nestTask 1.1

      Partly covered by: What Is Machine Learning

    2. 2Data and learning: labeled and unlabeled data, supervised, unsupervised and reinforcement learningTask 1.1

      Partly covered by: What Is Machine Learning

    3. 3Training and inference: real-time, serverless, asynchronous and batchTask 1.1

      Partly covered by: Training vs Inference

    4. 4When AI fits and when it does not: regression, classification, clusteringTask 1.2

      Partly covered by: What Is Machine Learning

    5. 5The managed AI services: Comprehend, Translate, Transcribe, Polly, Lex, Rekognition, Textract, PersonalizeTask 1.2

      Lesson coming

    6. 6Traditional ML or a foundation model: explainability, regulation and operational limitsTask 1.2

      Lesson coming

    7. 7The ML lifecycle and MLOps with SageMaker AITask 1.3

      Lesson coming

    8. 8Model metrics and business metrics: accuracy, precision, recall, F1, ROITask 1.3

      Lesson coming

  2. Module 2: Fundamentals of GenAI

    1. 9Tokens, chunks, embeddings and vectorsTask 2.1

      Lesson: Tokenization, BPE vs WordPiece, Embeddings, Cosine Similarity, Chunking and Reranking

    2. 10Transformers and LLMs, diffusion and multimodal modelsTask 2.1

      Partly covered by: Attention, Intuitively, Transformers: Big Picture, What Is an LLM

    3. 11The foundation model lifecycle, token pricing and context engineeringTask 2.1

      Partly covered by: Context Windows, Tokenization

    4. 12Agents: tools, memory, orchestration, multi-agent patterns and the Model Context ProtocolTask 2.1

      Partly covered by: Agents and Tools, The Tool-Use Loop

    5. 13What generative AI does well and where it fails: hallucinations and nondeterminismTask 2.2

      Partly covered by: Temperature and Sampling

    6. 14Choosing a model and measuring business valueTask 2.2

      Partly covered by: Model Routing and Fallbacks, Measuring AI Value

    7. 15Building on AWS: Bedrock, SageMaker AI, JumpStart, AgentCore, Strands Agents, Quick and KiroTask 2.3

      Lesson coming

    8. 16Cost tradeoffs: on-demand, batch, provisioned throughput and custom modelsTask 2.3

      Lesson coming

  3. Module 3: Applications of Foundation Models

    1. 17Choosing a foundation model and setting inference parametersTask 3.1

      Partly covered by: Temperature and Sampling, Context Windows

    2. 18Retrieval Augmented Generation and Amazon Bedrock Knowledge BasesTask 3.1

      Partly covered by: Retrieval-Augmented Generation, Chunking and Reranking

    3. 19Vector stores on AWS: OpenSearch Service, Aurora, Neptune, RDS for PostgreSQLTask 3.1

      Partly covered by: Vector Databases, Approximate Neighbours

    4. 20The customization ladder: in-context learning, RAG, fine-tuning, distillation, pre-trainingTask 3.1, 3.3

      Partly covered by: Fine-Tuning vs Prompting

    5. 21AI agents and their business usesTask 3.1

      Partly covered by: Agents and Tools

    6. 22Prompt engineering: context, instructions, zero-shot, few-shot, chain-of-thought and templatesTask 3.2

      Lesson coming

    7. 23Prompt risks: injection, jailbreaking, poisoning and exposureTask 3.2

      Partly covered by: Guardrails

    8. 24Prompt versioning with Amazon Bedrock Prompt ManagementTask 3.2

      Lesson coming

    9. 25Training and fine-tuning: continued pre-training, instruction tuning, distillation, RLHF and data preparationTask 3.3

      Partly covered by: Fine-Tuning vs Prompting, Adapters and LoRA

    10. 26Evaluating foundation models: human review, benchmarks, ROUGE, BLEU, BERTScore and model-as-judgeTask 3.4

      Partly covered by: Evaluating LLMs, LLM as a Judge

    11. 27Evaluating RAG, agents and business outcomesTask 3.4

      Lesson coming

  4. Module 4: Guidelines for Responsible AI

    1. 28The dimensions of responsible AI and Amazon Bedrock GuardrailsTask 4.1

      Partly covered by: Guardrails

    2. 29Bias, variance and datasets: subgroup analysis, bias metrics and human reviewTask 4.1

      Lesson coming

    3. 30Legal risks of generative AI and sustainable model choiceTask 4.1

      Lesson coming

    4. 31Transparency and explainability: model cards, AI Service Cards and open modelsTask 4.2

      Lesson coming

    5. 32Human-centered design for explainable AITask 4.2

      Lesson coming

  5. Module 5: Security, Compliance, and Governance for AI Solutions

    1. 33Securing AI workloads: IAM, encryption, PrivateLink, Macie and shared responsibilityTask 5.1

      Partly covered by: Shared Responsibility & IAM, VPC: Subnets, NAT & Firewalls

    2. 34Securing agents: AgentCore Identity, Policy in AgentCore, guardrails and prompt injectionTask 5.1

      Partly covered by: Guardrails, The Tool-Use Loop

    3. 35Hallucination detection and groundingTask 5.1

      Partly covered by: Retrieval-Augmented Generation

    4. 36Data lineage, cataloging and secure data engineeringTask 5.1

      Lesson coming

    5. 37Governance services: Config, Inspector, Artifact, CloudTrail, Trusted AdvisorTask 5.2

      Lesson coming

    6. 38Data governance and review processes; the Generative AI Security Scoping MatrixTask 5.2

      Lesson coming

Every task in the exam guide

The exam guide splits each domain into task statements. Each one has a page with a short summary, the lessons that teach it and open sample questions.

Domain 1: Fundamentals of AI and ML

Domain 2: Fundamentals of GenAI

Domain 3: Applications of Foundation Models

Domain 4: Guidelines for Responsible AI

Domain 5: Security, Compliance, and Governance for AI Solutions

How these questions are made

  • Written by us from the exam guide's task statements and the AWS documentation — never from real exam content.
  • Every option carries its own explanation and a link to the AWS page that proves it.
  • A question enters a timed exam only after an independent check; until then it is a practice question.
  • Results are a plain percentage, per domain too — not an imitation of AWS's scaled score.

Questions about the AIF-C01 practice exam

Is the AIF-C01 practice exam free?
Yes. The full practice exam (65 questions, 90 minutes) is free with no sign-up, and so are the 135 practice questions, the task pages and the study path. Your attempts are saved in this browser, on this device.
How many questions does it have, and is it timed?
65 questions in 90 minutes: the same number of questions and the same time as the real AIF-C01 exam. When the time runs out, the exam is submitted as it stands, and unanswered questions count as wrong.
Are the answers explained?
After you submit, not during: like the real exam, the timed exam gives no feedback until the end. Then you get your score overall and per exam domain, and every question with each option explained and a link to the AWS documentation page behind it. In practice mode an answer is explained as soon as you check it.
What does the AI Practitioner exam pack add?
3 more timed practice exams (Practice exam 1: 65 questions, 90 minutes; Practice exam 2: 65 questions, 90 minutes; Practice exam 3: 65 questions, 90 minutes), each scored and explained the same way, and the next version of this exam when it changes. One payment, lifetime access, no subscription. Everything above stays free. See the pack.
Can I get a refund?
Yes, with no conditions: ask within 14 days of buying and you get the whole payment back. The details are in the terms.
Is this an official AWS practice exam?
No. BytePatterns is not affiliated with, endorsed or sponsored by Amazon Web Services. Every question is written by us from the public exam guide and the AWS documentation, never from real exam content, and a score here does not predict your result on the real exam. AWS lists its own preparation resources on its certification page.