You can see it againUnder pressure people bring back shapes and positions long after the wording has gone.
Picture superiority · Shepard 1967, Standing 1973
ISTQBCertified Tester AI Testing
The ISTQB Certified Tester AI Testing (CT-AI) certification equips testing professionals to design and execute tests for AI-based systems, including machine learning and generative AI. It addresses the unique challenges of probabilistic behavior, non-determinism, and data reliance, and introduces AI-specific quality characteristics. This certification is essential for testers, data scientists, and developers working with modern AI systems.
Exam formatMultiple choice
Duration60 minutes
DeliveryISTQB Member Boards
Passing score29 out of 44
Free questions1587
Content last reviewed 30 July 2026 · Up to date
The certification
What Certified Tester AI Testing proves, and what it asks of you
What this certification covers, who it is written for, and what the exam itself looks like on the day.
11domains
63objectives
395concepts
What it is
What this certification is
What it validates, who it is written for, and the experience it assumes.
About this certification
The ISTQB Certified Tester AI Testing (CT-AI) certification provides comprehensive knowledge for testing AI-based systems, covering machine learning systems and generative AI such as large language models. It focuses on the specific characteristics of AI, including probabilistic behavior, non-determinism, and reliance on data, and introduces AI-specific quality characteristics defined by ISO/IEC 25059.
The syllabus follows a lifecycle-based approach, covering input data testing, model testing, and ML development testing, along with relevant test approaches for modern AI-based systems. This certification is ideal for professionals involved in testing AI-based systems, including testers, test analysts, test managers, data scientists, and software developers, as well as those seeking a general understanding of testing AI-based systems.
Who it’s for
This certification is aimed at individuals involved in testing AI-based systems, including testers, test analysts, test engineers, test managers, test consultants, data analysts, data scientists, software developers involved in developing AI-based systems, and user acceptance testers. It is also suitable for individuals seeking a general understanding of testing AI-based systems, such as project managers, quality managers, software development managers, business analysts, IT directors, and management consultants.
Recommended experience
While there is no formal experience requirement beyond the CTFL prerequisite, a background in software testing and familiarity with AI concepts is beneficial. Understanding of fundamental software testing concepts; Basic knowledge of artificial intelligence and machine learning; Experience in test design and execution
The syllabus
What you’ll learn
Every domain and objective ISTQB measures, with the weight they carry on the exam.
The official ISTQB exam outline · checked 30 July 2026 · See the source
Domain 1: Introduction to AI
- AI Fundamentals
- AI Technologies and Frameworks
- AI as a Service
- Pre-Trained Models and Transfer Learning
- Standards and Regulations
Domain 2: 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
Domain 3: Machine Learning (ML) - Overview
- Supervised Learning
- Unsupervised Learning
- Reinforcement Learning
- ML Workflow
- Selecting a Form of ML
- Factors Involved in ML Algorithm Selection
- Overfitting
- Underfitting
- Hands-On Exercise: Demonstrate Overfitting and Underfitting
Domain 4: ML - Data
- Challenges in Data Preparation
- Hands-On Exercise: Data Preparation for ML
- Hands-On Exercise: Identify Training and Test Data and Create an ML Model
- Dataset Quality Issues
- Data Quality and its Effect on the ML Model
- Approaches to Data Labelling
- Mislabeled Data in Datasets
Domain 5: ML Functional Performance Metrics
- Confusion Matrix
- Limitations of ML Functional Performance Metrics
- Hands-On Exercise: Evaluate the Created ML Model
- Benchmark Suites for ML
Domain 6: ML - Neural Networks and Testing
- Hands-On Exercise: Implement a Simple Perceptron
- Coverage Measures for Neural Networks
Domain 7: Testing AI-Based Systems Overview
- AI-Based System Testing Fundamentals
- Testing Levels and Integration
- Specialized Testing Considerations
Domain 8: Testing AI-Specific Quality Characteristics
- Challenges Testing Self-Learning Systems
- Testing Autonomous AI-Based Systems
- Testing for Algorithmic, Sample and Inappropriate Bias
- Challenges Testing Probabilistic and Non-Deterministic AI-Based Systems
- Challenges Testing Complex AI-Based Systems
- Hands-On Exercise: Model Explainability
- Test Oracles for AI-Based Systems
- Test Objectives and Acceptance Criteria
Domain 9: Methods and Techniques for the Testing of AI-Based Systems
- Adversarial Attacks
- Data Poisoning
- Hands-On Exercise: Pairwise Testing
- Back-to-Back Testing
- A/B Testing
- Hands-On Exercise: Metamorphic Testing
- Hands-On Exercise: Exploratory Testing and Exploratory Data Analysis (EDA)
- Selecting Test Techniques for AI-Based Systems
Domain 10: Test Environments for AI-Based Systems
- Test Environments for AI-Based Systems
- Virtual Test Environments for Testing AI-Based Systems
Domain 11: Using AI for Testing
- Hands-On Exercise:The Use of AI in Testing
- Using AI to Analyze Reported Defects
- Using AI for Test Case Generation
- Using AI for the Optimization of Regression Test Suites
- Hands-On Exercise: Build a Defect Prediction System
- Using AI to Test Through the Graphical User Interface (GUI)
- Using AI to Test the GUI
On the day
The exam itself
Everything ISTQB publishes about sitting it, and nothing we inferred.
Prerequisites
Must hold the ISTQB Certified Tester Foundation Level (CTFL) certification.
CertificationCertified Tester AI Testing
Exam formatMultiple choice
Duration60 minutes
Questions40 questions
Passing score29 out of 44
DeliveryISTQB Member Boards
LanguagesEnglish, Non-native language support (+25% time)
After you pass
Where this credential goes next
The path ISTQB lays out, how the credential is kept, and where to book.
Step-by-step path to Certified Tester AI Testing
PrerequisiteMust hold the ISTQB Certified Tester Foundation Level (CTFL) certification.
Credential earnedCertified Tester AI Testing Certification Renewal and maintenance
ISTQB certifications do not require renewal except for Expert Level. Stay current with the latest technologies and maintain your certification.
Learn more about renewal requirements Lifecycle status
This certification is currently active and available. ISTQB maintains this certification to validate current skills and industry relevance.
Exam status: ActiveMaintained by ISTQB
Exam registration
Register for the exam through ISTQB Member Boards, ISTQB’s authorized testing partner.
Schedule your examVisit the official ISTQB certification page for exam policies and requirements.
View the official pageYour coach
And when you are serious, your coach Pip takes over
Your coach in the app reads what you have answered with the book closed and tells you one thing to do tonight. It will not count an answer you gave with the page open, and it will tell you when you are not ready.
See how the coach worksBefore you book
Questions people ask
How does CT-AI v2.0 differ from the retiring CT-AI v1.0?
CT-AI v2.0 is the latest version and replaces v1.0. The v1.0 certification will be retired: English versions remain available until April 21, 2027, and non-English versions until October 21, 2027. After these dates, all exams and training courses based on v1.0 will no longer be available.
Is the CTFL certification required before taking CT-AI?
Yes, the ISTQB Certified Tester Foundation Level (CTFL) is a mandatory prerequisite for the CT-AI v2.0 certification.
Does the CT-AI exam include any hands-on or lab-based components?
The CT-AI exam is a multiple-choice exam with 40 questions. There is no hands-on or lab-based component.
What is the retake policy for the CT-AI exam?
ISTQB exam retake policies are defined by the exam provider. Please refer to the specific exam provider's terms and conditions for details on waiting periods and retake limits.
What job roles does the CT-AI certification map to?
The CT-AI certification is aimed at testers, test analysts, test engineers, test managers, test consultants, data analysts, data scientists, software developers involved in AI-based systems, and user acceptance testers. It is also suitable for project managers, quality managers, and IT directors seeking a general understanding of testing AI-based systems.
Can I recertify by passing a different ISTQB exam?
ISTQB certifications do not require renewal except for Expert Level. Therefore, there is no recertification requirement for CT-AI.
Are there regional differences in exam delivery for CT-AI?
Exams are delivered by ISTQB Member Boards and exam providers worldwide. Availability and delivery options may vary by region. Please contact your local ISTQB Member Board or an exam provider for specific regional information.
Information freshness · Content last reviewed on 2026-07-30 Up to date
Practice free questions 1587 questions, free, no account needed.
The curriculum
The whole exam, mapped and written
Every domain, every objective, and every concept ISTQB measures — each one written out.
11domains
63objectives
395concepts
343free pages
The domains, and what sits inside them
Every objective below is a page you can open and practise now, without an account.
The official ISTQB exam outline · checked 30 July 2026 · See the source
1Domain 1: Introduction to AI118 questions
2Domain 2: Quality Characteristics for AI-Based Systems185 questions
Flexibility and Adaptability7 concepts · 6 pagesOpen →Autonomy6 concepts · 5 pagesOpen →Evolution3 concepts · 3 pagesOpen →Bias5 concepts · 5 pagesOpen →Ethics4 concepts · 6 pagesOpen →Side Effects and Reward Hacking10 concepts · 5 pagesOpen →Transparency, Interpretability and Explainability10 concepts · 6 pagesOpen →Safety and AI6 concepts · 5 pagesOpen →
3Domain 3: Machine Learning (ML) - Overview235 questions
Supervised Learning6 concepts · 6 pagesOpen →Unsupervised Learning6 concepts · 6 pagesOpen →Reinforcement Learning6 concepts · 5 pagesOpen →ML Workflow5 concepts · 6 pagesOpen →Selecting a Form of ML6 concepts · 6 pagesOpen →Factors Involved in ML Algorithm Selection8 concepts · 6 pagesOpen →Overfitting5 concepts · 4 pagesOpen →Underfitting5 concepts · 5 pagesOpen →Hands-On Exercise: Demonstrate Overfitting and Underfitting11 concepts · 6 pagesOpen →
4Domain 4: ML - Data193 questions
Challenges in Data Preparation8 concepts · 6 pagesOpen →Hands-On Exercise: Data Preparation for ML6 concepts · 5 pagesOpen →Hands-On Exercise: Identify Training and Test Data and Create an ML Model3 concepts · 5 pagesOpen →Dataset Quality Issues6 concepts · 6 pagesOpen →Data Quality and its Effect on the ML Model6 concepts · 6 pagesOpen →Approaches to Data Labelling10 concepts · 8 pagesOpen →Mislabeled Data in Datasets5 concepts · 5 pagesOpen →
5Domain 5: ML Functional Performance Metrics83 questions
6Domain 6: ML - Neural Networks and Testing29 questions
7Domain 7: Testing AI-Based Systems Overview77 questions
8Domain 8: Testing AI-Specific Quality Characteristics213 questions
Challenges Testing Self-Learning Systems9 concepts · 5 pagesOpen →Testing Autonomous AI-Based Systems7 concepts · 6 pagesOpen →Testing for Algorithmic, Sample and Inappropriate Bias6 concepts · 6 pagesOpen →Challenges Testing Probabilistic and Non-Deterministic AI-Based Systems8 concepts · 5 pagesOpen →Challenges Testing Complex AI-Based Systems7 concepts · 6 pagesOpen →Hands-On Exercise: Model Explainability4 concepts · 6 pagesOpen →Test Oracles for AI-Based Systems10 concepts · 6 pagesOpen →Test Objectives and Acceptance Criteria6 concepts · 6 pagesOpen →
9Domain 9: Methods and Techniques for the Testing of AI-Based Systems201 questions
Adversarial Attacks7 concepts · 5 pagesOpen →Data Poisoning7 concepts · 6 pagesOpen →Hands-On Exercise: Pairwise Testing5 concepts · 4 pagesOpen →Back-to-Back Testing7 concepts · 6 pagesOpen →A/B Testing9 concepts · 6 pagesOpen →Hands-On Exercise: Metamorphic Testing6 concepts · 4 pagesOpen →Hands-On Exercise: Exploratory Testing and Exploratory Data Analysis (EDA)5 concepts · 6 pagesOpen →Selecting Test Techniques for AI-Based Systems7 concepts · 7 pagesOpen →
10Domain 10: Test Environments for AI-Based Systems74 questions
11Domain 11: Using AI for Testing179 questions
Hands-On Exercise:The Use of AI in Testing3 concepts · 4 pagesOpen →Using AI to Analyze Reported Defects6 concepts · 5 pagesOpen →Using AI for Test Case Generation5 concepts · 5 pagesOpen →Using AI for the Optimization of Regression Test Suites5 concepts · 6 pagesOpen →Hands-On Exercise: Build a Defect Prediction System7 concepts · 6 pagesOpen →Using AI to Test Through the Graphical User Interface (GUI)6 concepts · 6 pagesOpen →Using AI to Test the GUI8 concepts · 6 pagesOpen →
Not a table of contents
Every line on this map already opens
In front of every objective the practice pages are already there, free and without an account. This is one objective, opened.
AI Fundamentals4 pagesOpen →
Free in front of it
16 questions on this objective, five to a page. Every range above is a real page, open now, with no account.
Reading the map is not the same as knowing the ground
The curriculum tells you what is on the exam. Proving you know it is a different job — and it is the one the closed-book run does.
Free questions
1587 questions. No account, no card.
The whole bank is open. 5 questions to a page, every answer explained, and a discussion thread on each one.
1587questions
343pages
63objectives
Freealways
Browse by domain
Every objective, and every page range, is a link — so you can pick up exactly where you left off.
1Domain 1: Introduction to AI118 questions
2Domain 2: Quality Characteristics for AI-Based Systems185 questions
3Domain 3: Machine Learning (ML) - Overview235 questions
4Domain 4: ML - Data193 questions
5Domain 5: ML Functional Performance Metrics83 questions
6Domain 6: ML - Neural Networks and Testing29 questions
7Domain 7: Testing AI-Based Systems Overview77 questions
8Domain 8: Testing AI-Specific Quality Characteristics213 questions
9Domain 9: Methods and Techniques for the Testing of AI-Based Systems201 questions
10Domain 10: Test Environments for AI-Based Systems74 questions
11Domain 11: Using AI for Testing179 questions
What a practice page gives you
1Five to a page
Short enough to finish, long enough to matter.
2Every answer explained
Not only which one is right — why the others are wrong.
3A discussion on each
Ask, answer, and vote. Every question has its own thread.
A question, and the idea behind it
Every question comes from a concept
These are not trivia. Each one is written against a concept in the book, so when you get one wrong there is somewhere to go and find out why.
The visual book
See it once. Carry it into the exam.
The pages shown here come from our AI-900 book — an example of how each concept is written in plain language and, where the idea needs one, drawn as a full page you can take in at a glance.
395concepts
1587free questions
Why a picture, and not another paragraph
Three reasons, and each one is a real finding rather than a slogan.
You can see it againThe whole idea at onceWhere it starts, what happens in the middle, what comes out, and the mistake to avoid.
Multimedia principle · MayerThe look-alikes sit togetherThe pairs the exam tests are drawn side by side, so the difference is seen, not told.
Dual coding · PaivioWhat one page is made of
You are never asked to read a poster here — only to see how one is built. After that, every other page is legible at a glance.
1A numbered strip on top
The idea as a sequence, followed with a finger before a word is read.
2Panels for the parts
What it is, how the machine learns it, when it is the right tool.
3The trap, framed
The distinction the exam tests, given its own box instead of buried in prose.
4One line at the bottom
The sentence to carry into the exam room.
Open book, on purpose
Answer it with the picture beside you
This is the part that teaches. The illustration and the written explanation stay where they are while you work, so a scenario stops being a memory test and becomes something you can simply look at.
It teaches · it does not count
A smartphone uses AI to unlock when the owner looks at the camera. Which AI capability is being used?
AImage classification
BFacial recognition
COptical character recognition
DObject detection
Look at the five steps. Detect finds a face, align straightens it, encode turns it into numbers, search compares it with a stored face, and decide answers one question: is this the same person? Classification would only say “a face”. Detection would only draw a box. Neither decides whose.
Then the page shuts, and it starts counting
The same questions come back with the book closed — that run is the one that counts. After it, your coach picks one thing for tonight, sized to the time you have, and brings pages back before you lose them.
Testing effect · Roediger & Karpicke 2006 · spacing effect · Cepeda et al. 2006
Official resources
Straight from ISTQB
Where the exam is defined, scheduled and scored.
3official links
395concepts mapped
The source
ISTQB’s own pages
We link to them rather than repeat them, so nothing here goes stale behind them.
Checked against the source
Every objective on the official ISTQB outline already has questions here
We build from the official skills outline, not from a summary of it — 63 objectives, 395 concepts written under them, and free questions against every one. When ISTQB changes the outline, this page changes with it.
63objectives on the outline→395concepts written→1587free questions
An official page tells you what will be asked. It cannot tell you what you will get right.
That is the only question worth answering the night before, and no link answers it. You answer it by taking the questions with the book closed, and seeing what comes back.