ISTQB Testing with Generative AI (CT-GenAI) Training

Future-proof your testing career with AI skills that matter

Generative AI is transforming the way we build and test software. With the ISTQB CT-GenAI certification, you’ll learn how to put AI to work in your testing process, safely, effectively, and with confidence. This course is designed to give you both the practical techniques and the strategic insights needed to thrive in a world where AI is part of everyday QA.

Duration	Language	Method
3-days	English	Virtual and Class-room

Invest in Your Future Today

Generative AI isn’t just a buzzword it’s shaping the next decade of software testing. With this certification, you’ll be ready to lead the change, not chase it.

REQUEST QUOTE

3-days

Virtual / Class-room

Exam Included

ISTQB Certification

By attending the ISTQB® Certified Tester – Testing with Generative AI (CT-GenAI) course, you’ll gain a solid understanding of how Generative AI can support and transform software testing. You will learn the fundamentals of Large Language Models (LLMs), how to craft effective prompts, and how to apply GenAI to test analysis, design, automation, and reporting. The training also equips you to identify and manage GenAI-specific risks such as bias, hallucinations, and data privacy issues, while exploring modern AI-enabled test infrastructures like RAG, fine-tuned models, and AI agents. Finally, you’ll discover how to integrate GenAI strategically into your organization, empowering both teams and processes to achieve smarter, faster, and more reliable testing.

The training materials provide solutions for the exercises, mock exams, sample questions covering every learning objective in the ISTQB GenAI Syllabus.

Copies of the ISTQB GenAI syllabus and Glossary, detailed advice on how to prepare for the exam, and more.

General Course Information

This course is ideal for testers and test teams preparing for the ISTQB GenAI certification.

Who should attend this course?

This course is ideal for:

Software testers and test analysts
Test automation engineers and QA leads
Test managers, consultants, and IT leaders
Anyone curious about how AI can improve testing quality and efficiency

and any person in ICT with an interest in quality assurance.

Pre-requisites:

You’ll need ISTQB Foundation Level (CTFL) certification before attempting the exam. Howere anyone can attend the training course.

LEARNING OBJECTIVES

Attendees will learn to:

Understand the fundamentals of Generative AI and Large Language Models (LLMs) and their relevance in software testing.
Apply prompt engineering techniques to generate useful and reliable outputs for testing activities.
Use GenAI to support key testing tasks such as analysis, design, automation, and reporting.
Identify and manage risks specific to GenAI, including hallucinations, bias, privacy, and security issues.
Evaluate and implement GenAI-enabled test infrastructures, such as Retrieval-Augmented Generation (RAG), fine-tuning, and AI agents.
Understand the environmental, ethical, and organizational considerations of using GenAI in testing.
Develop strategies for introducing and scaling GenAI within teams and organizations.
Gain practical skills to maximize GenAI’s benefits while maintaining accuracy, reliability, and trust in testing outcomes.

Session Plan

The course runs for two days. Each day is about 360 minutes of class time, from 9:00 to 5:00. For accredited course offerings, materials are covered as described. For custom courses, materials may be deleted, added, or expanded upon as needed.
Please note that timings are approximate, depending on attendee interest and discussion. All of the lectures include exercises except as noted.

Course Content

Chapter 1: Introduction to Generative AI for Software Testing

1.1. Generative AI Foundations and Key Concepts
1.1.1 AI Spectrum: Symbolic AI, Classical Machine Learning, Deep Learning, and Generative AI
1.1.2 Basics of Generative AI and LLMs
1.1.3 Foundation, Instruction-Tuned and Reasoning LLMs
1.1.4 Multimodal LLMs and Vision-Language Models

1.2 Leveraging Generative AI in Software Testing: Core Principles
1.2.1 Key LLM Capabilities for Test Tasks
1.2.2 AI Chatbots and LLM-Powered Testing Applications for Software Testing
Chapter 2: Prompt Engineering for Effective Software Testing

2.1. Effective Prompt Development
2.1.1 Structure of Prompts for Generative AI in Software Testing
2.1.2 Core Prompting Techniques for Software Testing
2.1.3 System Prompt and User Prompt

2.2 Applying Prompt Engineering Techniques to Software Test Tasks
2.2.1 Test Analysis with Generative AI
2.2.2 Test Design and Test Implementation with Generative AI
2.2.3 Automated Regression Testing with Generative AI
2.2.4 Test Monitoring and Test Control with Generative AI
2.2.5 Choosing Prompting Techniques for Software Testing

2.3 Evaluate Generative AI Results and Refine Prompts for Software Test tasks
2.3.1 Metrics for Evaluating the Results of Generative AI on Test tasks
2.3.2 Techniques for Evaluating and Iteratively Refining Prompts
Chapter 3: Managing Risks of Generative AI in Software Testing

3.1 Hallucinations, Reasoning Errors and Biases
3.1.1 Hallucinations, Reasoning Errors and Biases in Generative AI
3.1.2 Identify Hallucinations, Reasoning Errors and Biases in LLM Output
3.1.3 Mitigation techniques of GenAI hallucinations, reasoning errors and biases in software test
tasks
3.1.4 Mitigation of Non-Deterministic Behavior of LLMs

3.2 Data Privacy and Security Risks of Generative AI in Software Testing
3.2.1 Data Privacy and Security Risks Associated with Using Generative AI
3.2.2 Data Privacy and Vulnerabilities in Generative AI for Test processes and Tools
3.2.3 Mitigation Strategies to Protect Data Privacy and Enhance Security in Testing with
Generative AI

3.3 Energy Consumption and Environmental Impact of Generative AI in Software Testing
3.3.1 The Impact of Using GenAI on Energy Consumption and CO2 Emissions

3.4 AI Regulations, Standards, and Best Practice Frameworks
3.4.1 AI Regulations, Standards and Frameworks Relevant to GenAI in Software Testing
Chapter 4: LLM-Powered Test Infrastructure for Software Testing

4.1 Architectural Approaches for LLM-Powered Test Infrastructure
4.1.1 Key Architectural Components and Concepts of LLM-Powered Test Infrastructure
4.1.2 Retrieval-Augmented Generation
4.1.3 The Role of LLM-Powered Agents in Automating Test processes

4.2 Fine-Tuning and LLMOps: Operationalizing Generative AI for Software Testing
4.2.1 Fine-Tuning LLMs for Test tasks
4.2.2 LLMOps when Deploying and Managing LLMs for Software Testing
Chapter 5: Deploying and Integrating Generative AI in Test organizations

5.1 Roadmap for the Adoption of Generative AI in Software Testing
5.1.1 Risks of Shadow AI
5.1.2 Key Aspects of a Generative AI Strategy in Software Testing
5.1.3 Selecting LLMs/SLMs for Software Test Tasks
5.1.4 Phases when Adopting Generative AI in Software Testing

5.2 Manage Change when Adopting Generative AI for Software Testing
5.2.1 Essential Skills and Knowledge for Testing with Generative AI
5.2.2 Building Generative AI Capabilities in Test Teams
5.2.3 Evolving Test Processes in AI-Enabled Test organizations

ISTQB GenAI Exam

Included in our training fee is one ISTQB GenAI exam session hosted by the SASTQB (Southern African Software Testing Qualifications Board) www.sastqb.org.za

Duration: 60 minutes

Number of Questions: 40 Multiple Choice

Pass Mark: 65%

ISTQB GenAI Training Schedule

23 February 2026
4 May 2026
24 August 2026
14 December 2026

Book Training

Are you ready to book for the ISTQB Foundation course? Follow the link below to start the process.

Request For Quote

Reach out to our office for a formal quotation. We offer training for individuals and companies. Group bookings qualify for a discounted price.

REQUEST QUOTE