ISTQB Specialist (CT-GenAI v1.1) Probeprüfung #2

The second full-length practice exam for the ISTQB Certified Tester Testing with Generative AI (CT-GenAI) v1.1 syllabus, in force since April 2026. It follows the official exam format exactly: 40 questions worth 46 points, 60 minutes, and 30 points to pass (65%). Scoring is weighted as the real exam weights it — K1 and K2 questions are worth 1 point, K3 questions 2 — so the six applied questions carry 12 of the 46 points between them. The chapter split is the official one: 7 questions from Introduction to Generative AI, 11 from Prompt Engineering (16 points, and the home of five of the six K3 items), 10 from Managing (AI) Risks, 5 from LLM-Powered Infrastructure and 7 from Deployment & Integration. The K-level mix matches the published structure too: 8 questions at K1, 26 at K2 and 6 at K3. Where mock exam 1 concentrates on prompting for test analysis, test data and pilot governance, this one leans on three other areas. The first is model behaviour that testers meet in practice: sampling temperature, version upgrades that change how a prompt behaves, multimodal input from a screenshot, and the gap between fluent output and correct output. The second is deriving tests with a named technique — a decision table from three pricing conditions, state transition coverage over an order lifecycle, API cases bounded by a schema, automation code grounded in a real page object, and a triage prompt whose every decision cites the log line it came from. The third is operational risk: prompt injection through a support ticket, a hallucinated package name as a supply-chain problem, fabricated standard citations, provider due diligence, and pseudonymisation before defect reports leave the organisation. Every option, correct and incorrect alike, carries its own rationale, and every question has an overall explanation, so a wrong answer tells you which misconception to correct. As with mock exam 1, remember that CT-GenAI is about testing with generative AI; testing AI-based systems is the subject of CT-AI, which is a separate exam.