Certified Tester AI Testing (CT-AI)

Overview Learning objectives What you'll learn Key facts FAQs Course syllabus What our customers say Get in touch

Course overview

The ISTQB Certified Tester AI Testing (CT-AI) course equips software testers with the knowledge and techniques needed to test systems powered by artificial intelligence and machine learning. You’ll explore how AI influences software behaviour, introduces new risks, and changes how tests are designed. Aligned to the ISTQB syllabus, this training prepares you for this well-recognised certification and helps you apply practical testing approaches to AI-driven systems.

AI testing skills for experienced software testers and QA professionals

This four-day ISTQB AI Testing course helps software testing professionals develop practical skills for testing AI-enabled systems and machine learning models. Understand machine learning workflows, data-related risks and specialised testing approaches used in AI environments, while building the knowledge needed to evaluate AI-enabled applications and prepare for the ISTQB Certified Tester AI Testing (CT-AI) certification.

Learning objectives

Understand characteristics of AI systems
Identify risks in AI testing
Apply testing techniques for AI systems
Understand machine learning workflows
Evaluate machine learning data quality
Test self-learning systems
Select ML testing approaches
Address AI testing challenges
Design and execute test cases for AI-based systems

What you'll learn

Testing AI systems introduces a new set of challenges for software testers. This training explores the common risks you need to manage, and how testing approaches can be used when working with artificial intelligence and machine learning systems. You’ll learn how ML models influence system behaviour and how to validate AI-driven applications in modern software development environments.

Foundations of artificial intelligence

Build a practical understanding of artificial intelligence and how AI-enabled systems differ from traditional software. You’ll explore core AI technologies, development frameworks and common architectures used in modern applications. This foundation helps you recognise where AI introduces new behaviours and testing considerations.

Machine learning fundamentals

Learn how machine learning systems are developed and trained. You’ll work through core ML workflows, including how training and validation datasets are used, and see how data quality directly affects model performance. The module also explores how to select appropriate algorithms and tackle common challenges, so you can make more informed testing decisions.

Testing AI-based systems

Understand how testing strategies change when working with AI-driven applications. You’ll explore how AI systems are specified and validated across different test levels, with a focus on selecting and managing the right test data to support reliable outcomes. The course also introduces specialised techniques, such as adversarial and metamorphic testing, helping you apply the right approach to address the unique risks and behaviours of AI-based systems.

AI quality characteristics

AI-based systems introduce unique quality concerns. You’ll examine challenges such as bias, transparency and explainability, as well as the risks associated with probabilistic behaviour. You’ll learn how testers evaluate these characteristics to ensure AI-enabled systems remain reliable and trustworthy.

What's included

Accredited training for ISTQB Certified Tester AI Testing (CT-AI)
ISTQB Certified Tester AI Testing (CT-AI) exam
Guidance from our experienced trainers
Optional add-ons available at checkout, including Pass Protect exam insurance

Key facts

Certification

ISTQB Certified Tester AI Testing (CT-AI).

Who it’s for

This course is designed for software testers and quality professionals who want to develop practical skills in AI testing and understand how artificial intelligence affects software quality.

Prerequisites

You must hold the ISTQB Certified Tester Foundation Level qualification. It is also recommended that you have around 18 months of practical experience in software testing.

Exam information

A 40-question, multiple-choice exam, lasting 60 minutes. The pass mark is 65%.

Optional extras

Pass Protect.

Pre-course

There is no pre-course work for this course.

FAQs

The ISTQB Certified Tester AI Testing training follows the official syllabus and prepares you for the CT-AI certification exam. You’ll develop a clear understanding of how AI-powered systems behave in practice, including the challenges created by non-deterministic outputs and data dependency, strengthening your ability to test AI-enabled applications.

Is the ISTQB AI Testing exam included and how do I book it?

Yes. You’ll receive an exam voucher prior to the start of your course which allows you to book your ISTQB Certified Tester AI Testing (CT-AI) exam at a time and location that suits you. Make sure you book and sit the exam before the voucher expiry date.

How can the ISTQB AI Testing certification support my career?

This certification helps you build specialised knowledge in testing artificial intelligence and machine learning systems. As AI technologies become more widely used, organisations increasingly need testers who understand the risks, behaviours and validation techniques associated with AI-driven systems. Completing this course demonstrates your ability to test AI-enabled applications and supports progression into more advanced testing and quality roles.

What courses can I take after the ISTQB AI Testing certification?

After completing the ISTQB AI Testing certification, many professionals continue developing their skills in areas such as automation, test management or specialist testing disciplines. ISTQB offers a range of advanced certifications, which you can complete through TSG, to support your ongoing personal development.

How difficult is the ISTQB AI Testing exam?

The ISTQB Certified Tester AI Testing (CT-AI) exam consists of 40 multiple-choice questions and lasts 60 minutes. The exam is closed book and requires a 65% pass mark to achieve certification. The course covers all topics included in the ISTQB syllabus, ensuring you understand the concepts and testing approaches needed to answer exam questions confidently.

Course syllabus

Dive into the detail of the course by looking at the syllabus below.

Introduction to AI
- Definition of AI and AI effect
- Narrow, general and super AI
- AI-based and conventional systems
- AI technologies
- AI development frameworks
- Hardware for AI-based systems
- AI as a service (AIaaS)
- Pre-trained models
- Standards, regulation and AI

Quality characteristics for AI-based systems
- Flexibility and adaptability
- Autonomy
- Evolution
- Bias
- Ethics
- Side effects and reward hacking
- Transparency, interpretability and explainability
- Safety and AI

Machine learning (ML) overview
- Forms of ML
- ML workflow
- Selecting a form of ML
- Factors involved in ML algorithm selection
- Overfitting and underfitting

ML – Data
- Data preparation as part of the ML workflow
- Training, validation and test datasets in the ML workflow
- Dataset quality issues
- Data quality and its effect on the ML model
- Data labelling for supervised learning

ML functional and performance metrics
- Confusion metrics
- ML functional performance metrics for classification, regression and clustering
- Limitation of ML functional performance metrics
- Selecting ML functional performance metrics
- Benchmark suites for ML performance

ML neural networks and testing
- Neural networks
- Coverage measures for neural networks

Testing AI-based systems overview
- Specification of AI-based systems
- Test levels for AI-based systems
- Test data for testing AI-based systems
- Testing for automation bias in AI-based systems
- Documenting an AI component
- Testing for concept drift
- Selecting a test approach for an ML system

Testing AI-specific quality characteristics
- Challenges testing self-learning systems
- Testing autonomous self-learning systems
- Testing for algorithmic, sample and inappropriate bias
- Challenges testing probabilistic and non-deterministic AI-based systems
- Challenges testing complex AI-based systems
- Testing transparency, interpretability and explainability of AI-based systems
- Test oracles for AI-based systems
- Test objectives and acceptance criteria

Methods and techniques for the testing of AI-based systems
- Adversarial attacks and data poisoning
- Pairwise testing
- A/B testing
- Back-to-back testing
- Metamorphic testing (MT)
- Experience-based testing of AI-based systems
- Selecting test techniques for AI-based systems

Test environments for AI-based systems
- Test environments for AI-based systems
- Virtual test environments for testing AI-based systems

Using AI for testing
- AI technologies for testing
- Using AI to analyse defect reports
- Using AI for test case generation
- Using AI for the optimisation of regression test suites
- Using AI for defect prediction
- Using AI for testing user interfaces

What our customers say

she manages to keep our attention during the full course and provide real life examples to make the topic understandable.