ISTQB Certified AI Tester Course

ISTQB CT-AI Tester Certification: Complete Overview

Want a quick, complete overview of the ISTQB CT-AI Tester certification? Below you’ll find everything you need to know. From the AI testing syllabus, key topics, exam structure (questions, duration, passing score), and preparation tips to where to take the exam and the career benefits of becoming an ISTQB-certified AI tester. Your concise guide to ISTQB CT-AI Certification starts here.

Course Modules / Syllabus

The ISTQB Certified Tester AI Testing (CT-AI) certification covers a comprehensive set of topics designed to equip testers with AI testing knowledge and skills, from core AI concepts to practical testing techniques.

Module 1: Introduction to AI

• Definition and scope of Artificial Intelligence
• Types of AI (Narrow, General, Super AI)
• AI vs. conventional systems
• AI technologies, frameworks, and hardware
• AI as a Service (AIaaS) and pre-trained models
• Standards and regulations relevant to AI systems

Module 2: Quality Characteristics of AI-Based Systems

• Flexibility, adaptability, and autonomy
• Evolution and transparency
• Ethics, bias, and explainability
• Side effects, reward hacking, and safety considerations

Module 3: Machine Learning (ML) Fundamentals

• Forms of ML — supervised, unsupervised, reinforcement
• ML workflow and algorithm selection
• Overfitting and underfitting issues and implications

Module 4: ML Data and Preparation

• Data preparation for ML models
• Training, validation, and test datasets
• Dataset quality and labelling challenges
• Effects of data quality on model performance

Module 5: ML Functional Performance Metrics

• Confusion matrix and classification metrics
• Regression and clustering metrics
• Limitations of performance measures

Module 6: Neural Networks and Coverage Measures

• Basics of neural networks
• Testing considerations and coverage measures for neural nets

Module 7: Testing AI-Based Systems Overview

• Test levels: input data, component, system, and acceptance testing
• Test data strategies for AI systems
• Concept drift and automation bias testing

Module 8: Testing AI-Specific Quality Characteristics

• Challenges in testing self-learning and autonomous systems
• Bias testing and explainability validation
• Test oracles, acceptance criteria, and non-deterministic behaviors

Module 9: Methods & Techniques for AI Testing

• Adversarial attacks and data poisoning
• Pairwise and back-to-back testing
• A/B testing, metamorphic testing
• Experience-based testing and exploratory analysis

Module 10: Test Environments for AI Systems

• Test setup requirements for AI systems
• Virtual environments and infrastructure considerations

Module 11: Using AI for Testing

• AI technologies applied to testing tasks
• AI for defect analysis, test case generation
• AI-driven regression test optimization and UI testing