Course : ISTQB - Certified Artificial Intelligence (AI) Tester, certification

ISTQB ® Certification (CT-AI) (CTFL)

Practical course - 4d - 28h00 - Ref. IAQ
Price : 2800 € E.T.

ISTQB - Certified Artificial Intelligence (AI) Tester, certification

ISTQB ® Certification (CT-AI) (CTFL)



This training course provides you with the key skills needed to validate artificial intelligence systems. You'll learn how to test Machine Learning models, manage bias, transparency and ethics. You'll know how to design and run tests adapted to AI: neural networks, autonomous systems, A/B or metamorphic tests. You'll also discover how to use AI for defect analysis and test case generation. The final exam validates your expertise in AI system testing.


INTER
IN-HOUSE
CUSTOM

Practical course in person or remote class
Disponible en anglais, à la demande

Ref. IAQ
  4d - 28h00
2800 € E.T.




This training course provides you with the key skills needed to validate artificial intelligence systems. You'll learn how to test Machine Learning models, manage bias, transparency and ethics. You'll know how to design and run tests adapted to AI: neural networks, autonomous systems, A/B or metamorphic tests. You'll also discover how to use AI for defect analysis and test case generation. The final exam validates your expertise in AI system testing.


Teaching objectives
At the end of the training, the participant will be able to:
Comprendre les tendances de l’IA, ses applications concrètes et son impact sur les secteurs d’activité
Develop ML model testing skills and address challenges such as bias, transparency and ethics
Design and run AI-specific test scenarios

Intended audience
Software testers, quality assurance professionals, AI engineers and developers, product owners, project managers, quality managers, analysts, consultants and AI-related professions.

Prerequisites
ISTQB® Certified Tester Foundation certification.

Certification
L’examen de certification AI Testing (CT-AI) est inclus dans la formation et se déroule en présentiel dans nos centres de formation, en français, ou à distance si la formation a lieu en distanciel. Il a lieu le dernier jour de la formation. L’épreuve consiste en un QCM de 40 questions, d’une durée de 60 minutes. Les candidats dont la langue maternelle n’est pas le français ou en situation de handicap peuvent bénéficier d’un quart-temps supplémentaire, sous réserve d’une demande effectuée au moins 5 jours avant l’examen. Un score minimum de 65 % de bonnes réponses est requis pour obtenir la certification.
Remote certifications
See the certifier’s official documentation for the list of prerequisites for completing the online certification exam.

Course schedule

1
Introduction to AI

  • AI types: narrow, general and super AI.
  • AI as a service (AIaaS).
  • Standards and regulations.

2
Quality features of AI systems

  • Flexibility, adaptability and autonomy.
  • Bias, ethics and safety in AI.
  • Transparency, interpretability and explicability.

3
Overview of Machine Learning (ML)

  • ML workflow and algorithm selection.
  • Overfitting, underfitting.

4
ML - Data

  • Training, validation and test data sets.
  • Data quality issues and effects on ML models.
  • Data labeling and approaches.

5
Measuring ML functional performance

  • Confusion and performance matrix in ML.
  • Limits and test suites for ML models.

6
ML - Neural networks and testing

  • Introduction to neural networks.
  • Implementation of a simple perceptron.
  • Coverage measurements for neural networks.

7
Testing AI-based systems - Overview

  • Specification and test levels.
  • Test data and approaches.
  • Test for automation bias.

8
Test IA quality features

  • Challenges in testing autonomous systems.
  • Address algorithmic bias and complexity.
  • Testing complex AI systems.

9
Methods and techniques for testing AI systems

  • Adversarial attacks and data poisoning.
  • Pairwise, back-to-back, A/B and metamorphic tests.
  • Selection of test techniques.

10
Test environments for AI systems

  • Configuration and considerations for test environments.
  • Virtual test environments for AI testing.

11
Using AI for testing

  • AI technologies for testing.
  • AI in defect analysis and test case generation.
  • AI in fault prediction and HMI testing.

12
Certification exam

  • Multiple-choice questionnaire, 40 questions.
  • 1 hour, 65% correct answers required.


Customer reviews
4,1 / 5
Customer reviews are based on end-of-course evaluations. The score is calculated from all evaluations within the past year. Only reviews with a textual comment are displayed.
MARIA-GIOVANNA P.
26/05/26
5 / 5

The course answered all my questions about AI, particularly regarding ethics and security. Thank you to the trainer – he was brilliant! Well-organised, knowledgeable, clear and a good listener. And the morning review of the previous day’s chapters was very useful as it gave us a chance to revise. The final day was devoted to exam practice, which was excellent as we really took our time without any stress or rushing.
JEREMIE M.
26/05/26
4 / 5

Allowing sufficient time for each topic PPT slides are fine, but many of the Paint-based slides are not very reusable
LAALJ W.
26/05/26
5 / 5

I’m very pleased with this course – it’s been incredibly informative!




This programme is an original creation, developed by the teaching teams at ORSYS Formation. Any reproduction, representation, adaptation or use, in whole or in part, without the prior written authorisation of ORSYS, is strictly prohibited. ORSYS reserves the right to take any action necessary to protect its intellectual property rights.

Dates and locations
Select your location or opt for the remote class then choose your date.
Remote class

Dernières places
Date garantie en présentiel ou à distance
Session garantie

REMOTE CLASS
2026 : 15 Sep., 8 Dec.

2027 : 19 Jan., 19 Jan., 27 Apr., 27 Apr., 14 Sep., 14 Sep., 26 Oct., 26 Oct.

PARIS LA DÉFENSE
2026 : 8 Sep., 1 Dec.

2027 : 19 Jan., 27 Apr., 14 Sep., 26 Oct.



This programme is an original creation, developed by the teaching teams at ORSYS Formation. Any reproduction, representation, adaptation or use, in whole or in part, without the prior written authorisation of ORSYS, is strictly prohibited. ORSYS reserves the right to take any action necessary to protect its intellectual property rights.