Study guide
1.2 Exam Format, Cost, Score, and Delivery
AWS AI Practitioner Study Guide Exam
Track your progress as you read
Finished sections get a check mark.
1 Chapter 1: AIF-C01 Orientation and Official Source Control
1.1 Credential Scope, Code, and Search Language 1.2 Exam Format, Cost, Score, and Delivery 1.3 Official Exam Guide, Skill Builder, and Practice Workflow 1.4 Target Candidate Boundaries and Out-of-Scope Tasks 1.5 Domain Weights and Study Prioritization 1.6 Exam Policy, Retake, Results, and Recertification
2 Chapter 2: AI/ML Foundations and Use-Case Fit
2.1 AI, ML, Deep Learning, and Core Terminology 2.2 Supervised, Unsupervised, and Reinforcement Learning 2.3 Data Types, Labels, Structure, and Quality 2.4 Inference Patterns: Batch, Real-Time, and Embedded AI 2.5 AI Use-Case Fit and No-AI Decisions 2.6 Classification, Regression, Clustering, Forecasting, and Recommendation 2.7 AI/ML Foundations Case Lab
3 Chapter 3: ML Lifecycle, Metrics, and Practitioner MLOps
3.1 Data Collection, EDA, Preprocessing, and Feature Concepts 3.2 Training, Evaluation, Deployment, and Monitoring Lifecycle 3.3 Model Sources: Managed APIs, Open Source, and Custom Models 3.4 Evaluation Metrics and Business Metrics 3.5 Practitioner MLOps: Repeatability, Monitoring, and Retraining 3.6 SageMaker Lifecycle Service Map 3.7 ML Lifecycle Case Lab
4 Chapter 4: Generative AI Foundations and Inference Concepts
4.1 Foundation Models, LLMs, Transformers, and Modalities 4.2 Tokens, Context Windows, Embeddings, and Vector Search 4.3 Inference Parameters: Temperature, Top-p, and Output Controls 4.4 Hallucination, Grounding, and Context Quality 4.5 GenAI Use-Case Fit and Risk Triage 4.6 Prompt Injection, Data Leakage, and User Input Risk 4.7 Generative AI Foundations Case Lab
5 Chapter 5: Prompting, Model Selection, Customization, and Evaluation
5.1 Prompt Engineering Patterns and Business Quality 5.2 Zero-Shot, Few-Shot, Templates, and Instruction Design 5.3 Model Selection: Capability, Latency, Cost, and Risk 5.4 RAG vs Fine-Tuning vs Prompting vs Custom Models 5.5 Model Evaluation, Human Review, and Red-Team Feedback 5.6 Cost, Performance, and Throughput Decision-Making 5.7 Prompting and Model Selection Case Lab
6 Chapter 6: Amazon Bedrock, RAG, Agents, and Guardrails
6.1 Bedrock Core Concepts, Model Access, and Managed FM Choice 6.2 Knowledge Bases, RAG, Data Sources, and Grounding 6.3 AI Agents, Tools, Orchestration, and Business Workflows 6.4 Guardrails, Content Filters, Denied Topics, and Sensitive Data 6.5 Bedrock Model Evaluation, Monitoring, and Human Feedback 6.6 Bedrock Cost, Latency, Throughput, and Operational Fit 6.7 Bedrock, RAG, and Agents Case Lab
7 Chapter 7: AWS Managed AI/ML Services and SageMaker Map
7.1 Managed AI Services vs Foundation Model Apps vs Custom ML 7.2 Text, Language, Search, and Document AI Services 7.3 Vision, Speech, Contact Center, and Personalization Services 7.4 Amazon Quick, Amazon Q Developer, Kiro, and Practitioner Fit 7.5 SageMaker Canvas, Studio, Clarify, Autopilot, and Data Wrangler 7.6 Data Foundation Services: S3, Glue, OpenSearch, and Quick Sight 7.7 AWS AI Service Selection Case Lab
8 Chapter 8: Responsible AI, Human Review, and Safety
8.1 Fairness, Bias, Transparency, and Explainability 8.2 Privacy, Safety, Human Review, and Accountability 8.3 Guardrails, Clarify, Human Review, and Content Safety Controls 8.4 Responsible AI Risk Registers and Governance Workflows 8.5 Monitoring, Feedback, Drift, and Incident Response 8.6 Responsible AI Case Lab
9 Chapter 9: Security, Compliance, Governance, and Cost Controls
9.1 Shared Responsibility, IAM, and Least Privilege for AI 9.2 Encryption, Secrets, Networking, and Data Privacy 9.3 Prompt Injection, Data Exfiltration, and GenAI Threat Modeling 9.4 Logging, Monitoring, CloudTrail, CloudWatch, and Config 9.5 Compliance: Artifact, Config, Macie, and Policy Evidence 9.6 AI Cost Controls, Pricing, Throughput, and Budget Governance 9.7 Security and Governance Case Lab
10 Chapter 10: Integrated AWS AI Business Scenario Labs
10.1 Customer Support GenAI Assistant Lab 10.2 Document Intelligence and Compliance Review Lab 10.3 Personalization, Forecasting, and Fraud Detection Lab 10.4 Enterprise Search, RAG, and Knowledge Management Lab 10.5 Responsible AI and Security Review Board Lab 10.6 Cost, Performance, and Operations Review Lab 10.7 Full AIF-C01 Business Simulation
11 Chapter 11: Final Review, Exam Readiness, and Recertification
11.1 Final 30-Day AIF-C01 Study Plan 11.2 Official Practice Resources and Weak-Domain Remediation 11.3 90-Minute Exam Timing, Flagging, and Guessing Workflow 11.4 Test-Day Checklist: Online or Test Center 11.5 Post-Exam Results, Retake, and Recertification Plan 11.6 AWS AI Practitioner Final Mixed Review
1.2 Exam Format, Cost, Score, and Delivery
Key Takeaways Explain This Topic AI
AIF-C01 is a 90-minute exam with 65 total questions.
The exam includes 50 scored questions and 15 unscored questions, and unscored questions are not identified.
AWS reports results on a 100-1000 scaled score, with 700 as the minimum passing score.
The listed exam cost is 100 USD, with taxes and foreign exchange caveats, and delivery is through Pearson VUE testing centers or online proctoring.
Last updated: October 2026
Format facts that change how you work
Imagine a business analyst who has studied every domain but reaches question 58 with four minutes left. That is not only a knowledge problem. It is a format problem. AIF-C01 gives 90 minutes for 65 total questions, so pacing must be deliberate from the first screen. Some items will be quick definition checks, while others may require reading a scenario, identifying the business requirement, and choosing the AWS-documented response.
The current AWS exam guide describes multiple question types, including multiple choice, multiple response, ordering, and matching. You do not need to know which item type will appear next, and this guide does not claim to know live exam content. You do need to practice slowing down when a question asks for more than one response or asks for an order, because partial misunderstanding can turn a known concept into a wrong answer.
Official exam fact Current value Study impact
Exam duration 90 minutes Average pace is under 90 seconds per item, with extra time reserved for scenarios.
Total questions 65 Do not plan around a shorter practice quiz rhythm.
Scored questions 50 Your final score is based on scored items only.
Unscored questions 15 They are not identified, so treat every item seriously.
Score scale 100-1000 Do not translate the score directly into a simple percentage.
Minimum passing score 700 Plan for broad domain competence, not one perfect section.
Exam cost 100 USD Taxes and foreign exchange may affect the final registration amount.
Delivery Pearson VUE test center or online proctored exam Choose the environment that reduces avoidable test-day friction.
Scoring behavior
The exam guide says unanswered questions are scored as incorrect and that there is no penalty for guessing. That creates a simple rule: do not leave blanks. If you are stuck, eliminate answers that violate the scenario, choose the strongest remaining option, mark for review if the exam interface allows it, and move on. Spending six minutes on one uncertain item can damage the rest of the exam.
The scoring model is compensatory. That means the pass decision is based on the overall scaled score, not separate pass marks for each domain. Section-level classifications should be interpreted cautiously. A weak domain label after an attempt is useful for study planning, but it is not a mathematical breakdown of exactly how many items you missed or how many items will appear next time.
Delivery choice scenario
A candidate with reliable home internet, a quiet room, a compatible computer, and comfort with online check-in may choose online proctoring. A candidate who shares space, has unpredictable network quality, or prefers a controlled environment may choose a Pearson VUE testing center. The credential value is the same; the delivery decision is about reducing operational risk.
For online proctoring, the risk is usually environment control. You need a clean workspace, a compliant ID process, working camera and microphone, and a stable connection. For a testing center, the risk is usually travel and arrival timing. You need ID, appointment confirmation, transportation margin, and awareness that personal items will be restricted. Neither path makes the exam easier. The better path is the one with fewer avoidable distractions for you.
Pacing workflow
Spend the first minutes reading instructions and understanding whether any item type needs special handling.
On each question, identify the business goal, the AI/ML concept, the AWS service or policy area, and the constraint.
Answer high-confidence items quickly without over-checking.
For uncertain items, eliminate obviously wrong choices, choose the best remaining answer, and mark for review if available.
Never leave an item unanswered, because unanswered questions count as incorrect.
Use final review for marked items and obvious misreads, not for restarting the exam from question one.
Why unscored questions matter
Unscored items are used by certification programs for exam development, but AIF-C01 does not identify them during the test. You cannot safely guess which 15 questions are unscored. A strange or experimental-feeling item may still be scored, and a normal-looking item may be unscored. The only rational behavior is to answer every item with the same seriousness.
This also protects you from post-exam overanalysis. After the exam, candidates often remember the hardest or oddest items and assume those decided the result. Because 15 items are unscored and because scoring is scaled and compensatory, that memory is not a reliable diagnostic. Use the official score report and domain feedback for study direction instead of trying to reconstruct the form.
Cost and registration control
The AWS certification page lists the cost as 100 USD, with caveats for taxes and foreign exchange. Budget for the registration amount shown in the actual checkout flow. If your employer reimburses certification fees, capture the exact receipt and policy requirements before scheduling. If you are self-funding, remember that a failed attempt requires a full registration fee for a retake after the required waiting period.
The format facts do not guarantee an outcome, but they prevent bad preparation. A candidate who knows the time, item count, scoring behavior, cost, and delivery options can focus attention on AI decision-making rather than logistics surprises.