ISTQB CT-GenAI

Generative AI Fundamentals for Testing

60 questions

Easy

Generative AI foundations

  1. Which type of AI represents knowledge through symbols and explicitly written logical rules?
  2. In which type of AI do people select the features the model learns from before training?
  3. What is deep learning based on?
  4. What sets generative AI apart from the other types of AI?
  5. What is the main advantage of generative AI for test tasks compared with classical machine learning?
  6. What is a token in a language model?
  7. What are embeddings?
  8. What does the context window of an LLM refer to?
  9. What is a small language model (SLM)?
  10. Which neural network architecture are today's LLMs based on?
  11. What does an LLM compute step by step during inference?
  12. Why can the same prompt give a different answer when it is sent a second time?
  13. What is a foundation LLM?
  14. What is an instruction-tuned LLM further trained with?
  15. What are reasoning LLMs especially designed for?
  16. What can a multimodal LLM do that a text-only LLM cannot?
  17. What do vision-language models combine?

Generative AI in software testing

  1. In which two ways can testers use generative AI?
  2. Which test task does an LLM support when it suggests the expected results for test cases?
  3. What makes AI chatbots especially accessible for testers?

Medium

Generative AI foundations

  1. A team trains a model on 40,000 historical defect reports classified by hand, using preselected features such as module and severity. Which type of AI is this?
  2. Which activities often remain a human task even with deep learning?
  3. What applies to the embeddings of two tokens with a similar meaning, such as "crash" and "abort"?
  4. What are the consequences of a larger context window?
  5. An LLM suggests an expected value for a test case that sounds very convincing. Which assessment is correct?
  6. A tester wants to pass a 300-page system specification to an LLM. What should she clarify first?
  7. Which statements about tokens are correct?
  8. How does a multimodal LLM process an image before the transformer works with it?
  9. Which tasks are typical for vision-language models?
  10. A tester gives a multimodal LLM a screenshot of the order page and the text of a defect report. Which task fits?
  11. What is a model optimized for during instruction tuning?
  12. In which order do the training stages of LLMs build on one another?
  13. What are instruction-tuned LLMs sometimes called to distinguish them from reasoning LLMs?

Generative AI in software testing

  1. How can an LLM help with analysing requirements?
  2. How do LLMs support the creation of test data?
  3. How does an LLM help when evaluating test results?
  4. Which tasks can an LLM take on in test automation?
  5. Which features characterize LLM-powered testing applications compared with chatbots?
  6. What is meant by prompt chaining when working with a chatbot?
  7. Regardless of access via chatbot or application, what most determines useful LLM results in testing?

Hard

Generative AI foundations

  1. A checking tool rejects commits as soon as a list of fixed conditions maintained by experts is violated, such as "no credentials in plain text". Which type of AI does this approach correspond to most closely?
  2. A tester sends the same prompt twice and receives two different sets of test cases. Which conclusions are correct?
  3. When analysing a very long log, an LLM no longer takes the early entries into account and contradicts them. What is the most likely cause?
  4. A test log is too long for the context window. Which measures help?
  5. A team wants to bring 500 test case titles into a fixed naming style. Which choice of model makes the most sense?
  6. Test cases for valid and invalid transition sequences are to be derived from a state model of a payment process with many conditions. Which kind of model fits best?
  7. A team uses a pure foundation LLM without further training to write test cases from a template. Instead of carrying out the instruction, the model often just continues the prompt. What explains this?
  8. A tester gives a multimodal LLM a wireframe of the registration page and the related user story. Which results can she reasonably expect?
  9. After comparing 40 screenshots with the acceptance criteria, a multimodal LLM reports three discrepancies. Which statements are correct?
  10. A search for "app closes during sign-in" also finds the older defect report "crash at login", although no word matches. What makes this possible?
  11. A team compares the token count of test reports of equal length in German and English. Which statements are correct?
  12. Which statements about using generative AI in testing compared with classical machine learning are correct?
  13. Which trade-offs apply when using a reasoning LLM instead of an instruction-tuned model?
  14. A company wants to run a model on its own test machines without the cloud, solely to bring error messages into a uniform format. Which kind of model is the obvious choice?

Generative AI in software testing

  1. Every night, the CI pipeline is to create draft test cases automatically from new user stories. Which approach fits?
  2. For which tasks is an AI chatbot better suited than a fully integrated LLM application?
  3. For a shipping cost rule, an LLM suggests "free from €40" as the expected result, while the requirement states €50. What is the right way for the tester to proceed?
  4. An acceptance criterion reads "The search returns results quickly". How can an LLM help in a useful way?
  5. An LLM is to suggest boundary values for the field "age" (valid from 18 to 65) using two-value boundary value analysis. Which values belong in a correct answer?
  6. After a nightly run, 300 automated tests have failed. How can an LLM support the team in a useful way?

Certifications & exams

Which exam comes next?

You can already practise for 51 exams, and 16 are up for a vote. See all certifications with their official information, cast your vote or suggest your exam.

See all certifications