CT-GenAI v1.1: Testing with Generative AI

Is this the right certification for you?

CT-GenAI is for testers and test leads who use, or plan to use, generative AI tools in their testing work: drafting test cases, analyzing requirements, generating test data or building LLM-powered test assistants. It covers how to prompt well, how to manage the risks, and how to roll GenAI out across a test team.

Choose it if:

• You already use chat-based AI tools at work and want a structured, defensible way to do it.
• You need to explain GenAI risks such as hallucinations, bias, data privacy and security to your team or managers.
• You are planning how your test organization adopts GenAI.
• You hold CTFL, which is required.

Skip it or wait if:

• Your job is to test a product that contains AI, such as an ML model or an LLM chatbot. CT-AI is built for that.
• Your organization forbids GenAI tools and has no plans to change. Much of the value comes from practicing the techniques.

Exam at a glance

These figures describe CT-GenAI v1.1. Use the listed point threshold, rather than assuming a fixed number of correct answers on a weighted exam.

Source: ISTQB Exam Structures & Rules Tables v1.19, page 3 and the official CT-GenAI page, rechecked October 6, 2026. The CT-GenAI row confirms 40 questions, 46 points, a 30-point pass mark and 60 minutes. Confirm any approved extra time with your provider.

How the exam is weighted

ISTQB publishes the question split per chapter in its exam structure tables, not on the certification page. Here it is next to the training time the syllabus sets for accredited courses.

Syllabus chapter	Exam questions	Share of exam	Course training time
1. Introduction to generative AI for software testing	7	17.5%	100 min
2. Prompt engineering for effective software testing	11	27.5%	365 min
3. Managing risks of generative AI in software testing	10	25%	160 min
4. LLM-powered test infrastructure for software testing	5	12.5%	110 min
5. Deploying and integrating generative AI in test organizations	7	17.5%	80 min
Total	40	100%	815 min (about 13.6 hours)

What the numbers tell you: prompt engineering takes almost 45% of course time and 11 of 40 questions. Risk management is the second-heaviest chapter on the exam with 10 questions, even though it gets less than half the training time of chapter 2.

The exam uses three levels: 8 K1 questions (remember), 26 K2 questions (understand) and 6 K3 questions (apply, 2 points each). That makes 46 points in total, and you need 30 to pass.

Source: ISTQB Exam Structures & Rules Tables v1.19 (August 19, 2026). Chapter titles and training minutes come from the CT-GenAI v1.0 syllabus (July 25, 2025). ISTQB describes v1.1 as a minor update.

Entry requirements

You need CTFL. Ask which certificate evidence your provider accepts before you buy or schedule the exam.

Also known as: CT GenAI, Testing with Generative AI, Certified Tester Testing with Generative AI.

Source: Official syllabus and qualification overview.

What the syllabus covers

Chapter 1: Introduction to generative AI for software testing

How generative AI and large language models work at a practical level, and where they help across test activities.

Chapter 2: Prompt engineering for effective software testing

Structuring prompts for test tasks and evaluating the results. The syllabus names prompting techniques such as prompt chaining, few-shot prompting and meta prompting.

Chapter 3: Managing risks of generative AI in software testing

Hallucinations, reasoning errors, biases, data privacy and security, and energy use and environmental impact. Named mitigations include adjusting the temperature setting, setting random seeds for reproducibility, cross-verifying output and giving complete context in prompts.

Chapter 4: LLM-powered test infrastructure for software testing

Retrieval-augmented generation (RAG), LLM-powered agents that automate test steps, fine-tuning LLMs for test tasks, and LLMOps for deploying and running LLMs.

Chapter 5: Deploying and integrating generative AI in test organizations

The risks of shadow AI, a GenAI strategy for testing, choosing LLMs or small language models for test tasks, adoption phases, the skills testers need and how test processes evolve.

What changed in v1.1

ISTQB describes v1.1 as a minor update to CT-GenAI v1.0: targeted corrections, terminology alignment and clarification. The syllabus structure, learning objectives and overall scope are unchanged. The update does not introduce a new exam weighting. See the official minor-update announcement.

How to prepare

The suggestions below are our editorial advice, not ISTQB requirements.

1. Keep a prompt journal recording the task, context, constraints, output and your evaluation.
2. Distinguish useful drafting assistance from an assertion that still needs evidence.
3. Practice checking generated tests against an explicit source of expected behavior.
4. Discuss what can be sent to a tool under an organization’s actual data rules before proposing adoption.

A four-week study plan

This is our suggested plan for a tester with about four hours a week. It is editorial guidance, not an ISTQB requirement.

Week	Focus	Output to aim for
1	Chapter 1	A short explanation of tokens, context windows and why LLM output varies
2	Chapter 2	A prompt library for three real test tasks, with notes on what improved each result
3	Chapters 3 and 4	A risk register for GenAI use on your team and a sketch of one LLM-powered test tool
4	Chapter 5 and sample exam	An adoption roadmap outline and one timed sample with every mistake reviewed

Use the official sample exams

Take one sample under timed conditions before you open the answers, then review every guess as well as every wrong answer. Our sample exam guide shows how to turn a practice score into a study plan.

• CT-GenAI Sample Exam A Questions v1.1
• CT-GenAI Sample Exam A Answers v1.1

Mistakes that cost candidates points

• Studying the wrong AI syllabus. CT-GenAI is about using generative AI to test. CT-AI is about testing AI systems.
• Knowing technique names but not when to use them. Expect scenarios where you choose between prompt chaining, few-shot prompting and meta prompting.
• Treating risks as common sense. Chapter 3 carries 10 questions and names specific mitigations, such as temperature and random seeds.
• Ignoring shadow AI and adoption phases. Chapter 5 is 7 questions, the same as chapter 1.

Before you book

Before you pay for CT-GenAI, confirm the exam version, the language and your eligibility with the provider. Our booking checklist, country guides and exam day checklist walk you through it.

How CT-GenAI compares with related certifications

Feature	CT-GenAI v1.1	CT-AI v2.0	CTFL v4.0
Level	Specialist	Specialist	Foundation
Questions	40	40	40
Points to pass	30 of 46	29 of 44	26 of 40
Standard time	60 min	60 min	60 min
What it covers	Using generative AI in your testing work	Testing ML and generative AI systems	Testing fundamentals
Prerequisite	CTFL	CTFL	None

Common questions

How many questions are on the CT-GenAI exam, and what is the pass mark?

The exam has 40 multiple-choice questions worth 46 points. You need 30 points (65%) to pass. The standard time is 60 minutes, with 25% extra time available on request for non-native speakers.

What are the prerequisites for CT-GenAI?

You must hold the ISTQB Certified Tester Foundation Level (CTFL) certificate before taking the exam.

Is CT-GenAI the same as CT-AI?

No. CT-GenAI is about using generative AI in your testing work. CT-AI is about testing systems that contain AI, such as ML models and LLM features.

Do I need programming skills for CT-GenAI?

No. The exam is multiple choice and focuses on prompting, risk management and deployment decisions. Hands-on practice with real GenAI tools still helps, because 6 questions ask you to apply techniques.

Which CT-GenAI chapter matters most?

Prompt engineering, with 11 of 40 questions. Risk management follows with 10. Together they are more than half of the exam.

Should I study v1.0 or v1.1 material?

Study the version your exam uses. v1.1 is the current syllabus, and its sample exam is also labeled v1.1. Ask your provider which version your appointment assesses.

Can I take the CT-GenAI exam online?

Usually, yes. Most exam providers offer remote-proctored exams. Check your provider and language before you buy.

What is the CT-GenAI pass rate?

We found no scheme-wide ISTQB pass-rate figure as of October 10, 2026. Some providers publish numbers for their own candidates. If you find one, look at the exam version, the reporting period, the sample size and whether it counts first attempts or retakes before you trust it.

Does the CT-GenAI certificate expire?

No. Specialist certificates are valid for life.

How long is CT-GenAI training?

The syllabus sets 815 minutes, about 13.6 hours, for accredited courses. Chapter 2 on prompt engineering takes 365 of those minutes.

Key takeaways

• CT-GenAI has 40 questions worth 46 points, a 30-point pass mark and 60 minutes.
• Prompt engineering (11 questions) and risk management (10) make up more than half of the exam.
• CTFL is mandatory.
• v1.1 is a minor update to the July 2025 v1.0 syllabus.
• The certificate does not expire.

Related certification guides

Return to the full certification directory →

Fees and booking

Use our exam fees overview to compare exam prices, taxes, retake charges and booking terms. Our country guides carry dated fee records where we have verified them. If your country is not listed, the provider guides cover international routes. Confirm the final amount and terms directly with your provider.