ISTQB publishes exactly what the CT-GenAI tests and how much each part is worth. Here it is — every domain, its weight, the topics inside it, and the lessons that cover them.
Domain 1
Introduction to Generative AI for Software Testing
Types of AI, how large language models work (tokens, context windows, multimodal input), foundation vs instruction-tuned vs reasoning models, what LLMs can do for test tasks, and chatbots vs LLM-powered test tools. Official share: 7 of 40 exam questions.
2 topics in this domain
- Generative AI Foundations and Key Concepts
- Leveraging Generative AI in Software Testing: Core Principles
Domain 2
Prompt Engineering for Effective Software Testing
Prompt structure, core prompting techniques (chaining, few-shot, meta prompting), system vs user prompts, applying GenAI to test analysis, design, regression automation and monitoring, and evaluating and refining results. Official share: 11 of 40 exam questions, 16 of 46 points.
3 topics in this domain
- Effective Prompt Development
- Applying Prompt Engineering Techniques to Software Test Tasks
- Evaluate Generative AI Results and Refine Prompts for Software Test Tasks
Domain 3
Managing Risks of Generative AI in Software Testing
Hallucinations, reasoning errors and biases and how to catch and mitigate them, non-deterministic output, data privacy and security risks, energy use, and the AI regulations, standards and frameworks that apply. Official share: 10 of 40 exam questions.
3 topics in this domain
- Hallucinations, Reasoning Errors and Biases
- Data Privacy and Security Risks of Generative AI in Software Testing
- Energy Consumption, Regulations, Standards and Best Practice Frameworks
Domain 4
LLM-Powered Test Infrastructure for Software Testing
Architecture of LLM-powered test tools, Retrieval-Augmented Generation, LLM-powered agents that automate test processes, fine-tuning for test tasks, and LLMOps. Official share: 5 of 40 exam questions.
2 topics in this domain
- Architectural Approaches for LLM-Powered Test Infrastructure
- Fine-Tuning and LLMOps: Operationalizing Generative AI for Software Testing
Domain 5
Deploying and Integrating Generative AI in Test Organizations
Shadow AI, a GenAI strategy for testing, choosing LLMs/SLMs, recurring costs and adoption phases, and the skills, team practices and role changes that adoption brings. Official share: 7 of 40 exam questions.
2 topics in this domain
- Roadmap for the Adoption of Generative AI in Software Testing
- Manage Change when Adopting Generative AI for Software Testing