ISTQB® CT AI Testing
Software Testing
Course Overview
Apply AI-supported testing tools to generate optimized test suites, detect anomalies, and accelerate defect analysis. By mastering these practices, you streamline testing cycles, strengthen model reliability, and transform AI from a potential risk into a strategic advantage for your organization.
Why Choose the ISTQB® CT AI Testing
· A Complete Foundation for AI & ML in Testing
o Gain a practical understanding of Al concepts, machine learning workflows, model behavior, dataset structures, and the challenges unique to Al-based systems.
· Real-World Al Testing Techniques
o Learn how to evaluate accuracy, reliability, robustness, validation datasets, model drift, bias, and explainability, using proven testing principles.
· Al-Augmented QA Skills
o Discover how Al can support repetitive testing tasks like generating test scenarios, optimizing test suites, identifying anomalies, and accelerating analysis.
· Risk-Aware Al Adoption
o Build the ability to identify and manage issues such as dataset bias, overfitting, adversarial risk, inconsistent predictions, and ethical concerns.
· Career & Organizational Impact
o Gain the skills to contribute to Al-driven QA initiatives, evaluate Al-powered tools, and support teams adopting Al testing strategies
Duration: 4 days / 32 hours
Delivery Method: Classroom-based, Virtual Instructor-Led Training
COURSE HIGHLIGHTS
What You’ll Get with the ISTQB® CT AI Testing Program
Accelerate your AI-testing journey with a comprehensive, hands-on, globally recognized qualification. Here’s what the program empowers you with:
· Responsible Al Knowledge
o Understand ethical considerations, governance models, privacy needs, and risk-mitigation strategies in Al-driven environments.
· Live Instructor-Led Training
o 24 hours of expert-led sessions delivered over three days, combining interactive instruction with guided hands-on practice to apply concepts to real-world scenarios.
· Course Materials & Templates
o Access comprehensive study guides, quick-reference templates, and curated learning resources, available for 30 days after training to support on-the-job application.
· Exam Coaching & Mock Tests
o Certification-oriented preparation with practice questions, simulated exams, and detailed feedback to identify improvement areas and boost confidence.
This certification ensures you can meaningfully evaluate, test, and support Al systems in modern software organizations.
PRE REQUISITES
Who Should Enroll for the CT AI Testing Program
· Testing & QA Professionals
o Testers, test analysts, test engineers, automation engineers, QA leads, test managers.
· AI & Data Professionals
o Data analysts, data engineers, ML practitioners involved in model quality validation.
· Technology & Delivery Teams
o Software developers, project managers, product managers, team leaders, IT directors.
· Anyone Working with AI-Enabled Applications
o Ideal for those needing practical understanding of how to verify, validate, and trust AI systems.
Course Outline
DAY 1: Foundations of AI, ML & System Behaviour
· Introduction to AI, ML & Deep Learning
o Understand what AI means and why “AI Effect” matters.
o Distinguish Narrow, General, and Super AI.
o Compare AI systems with conventional rule-based systems.
o Learn key AI technologies, hardware and development frameworks.
o Explore AI as a Service (AIaaS), including contracts and examples.
· Pre-Trained Models & Transfer Learning
o Understand how pre-trained models accelerate ML development.
o Learn how transfer learning reuses existing model knowledge.
o Recognize risks like bias, drift, and instability when using pre-trained models.
· Machine Learning (ML) – Overview
o Explore supervised, unsupervised and reinforcement learning.
o Understand the complete ML workflow from data to deployment.
o Learn how to select ML techniques based on problem and data.
o Identify overfitting and underfitting with hands-on demonstrations.
· Standards, Regulations & Responsible AI
o Get an overview of global AI standards, regulations and ethical practices.
DAY 2: AI Quality Characteristics, Risks & Data Foundations
· Quality Characteristics of AI-Based Systems
o Explore flexibility, adaptability, autonomy and evolution.
o Understand challenges like bias, ethics, side effects and reward hacking.
o Learn transparency, interpretability, explainability and safety aspects.
· ML – Data Foundations
o Understand the role of data preparation in the ML workflow.
o Identify challenges in cleaning, preprocessing and validating ML data.
o Learn the purpose of training, validation and test datasets.
o Perform hands-on activities on dataset creation and ML model building.
· Data Quality & Labeling Challenges
o Explore dataset issues like imbalance, noise, drift and leakage.
o Understand how data quality impacts model accuracy and behavior.
o Learn supervised learning labeling methods and mislabeled data risks.
DAY 3: Metrics, Neural Networks & Testing AI-Based Systems
· ML Functional Performance Metrics
o Learn confusion matrix fundamentals for evaluating classification models.
o Understand metrics for classification, regression and clustering.
o Identify limitations in commonly used ML metrics.
o Practice evaluating ML models with benchmark suites.
· Neural Networks & Explainability
o Understand how neural networks work through perceptron implementation.
o Learn coverage techniques for neural network testing.
· Testing AI-Based Systems
o Understand how to specify and document AI components.
o Explore testing levels: input data, model, component, integration, system and acceptance.
o Learn how to design test data and detect automation bias.
o Understand how to test for concept drift and choose the right test approach.
· AI Quality Characteristic Testing
o Learn methods to test for bias, transparency and explainability.
o Understand testing challenges in self-learning, autonomous, probabilistic and complex AI systems.
o Learn about test oracles, acceptance criteria and model explainability.
DAY 4: Advanced AI Testing Techniques & AI for Testing
· Advanced Methods & Techniques
o Learn adversarial attacks, data poisoning and their impact.
o Understand pairwise testing, back-to-back testing and A/B testing.
o Apply metamorphic testing and exploratory data analysis with hands-on sessions.
· Test Environments for AI Systems
o Understand environment needs for AI system validation.
o Learn how virtual testing environments support AI model evaluation.
· Using AI for Testing
o Explore AI-driven defect analysis and prediction techniques.
o Learn AI-based test case generation and regression suite optimization.
o Understand how AI enhances UI testing through intelligent interaction.
· Exam Preparation & Final Assessment
o Review key ISTQB® CT-AI concepts and exam topics.
o Understand exam structure, format and scoring.
o Participate in a mock exam followed by a detailed debrief.
REGISTER NOW