サンプル問題 1： Which standard specifies requirements for managing AI systems within an organization, supporting consistent GenAI use in testing?
A: ISO/IEC 42001:2023
B: NIST AI RMF 1.0
C: ISO/IEC 23053:2022
D: EU AI Act
正解：A
Explanation: ISO/IEC 42001:2023is the international standard for an AI Management System (AIMS). It is designed to help organizations develop, provide, or use AI systems responsibly by providing a certifiable framework of requirements and controls. In a software testing context, this standard is vital for establishing governance, ensuring that GenAI tools are used consistently and ethically across the lifecycle. NIST AI RMF 1.0 (Option B) is a highly respected framework, but it is a set of voluntary guidelines for managing risk, not a "requirement standard" for a management system. ISO/IEC 23053:2022 (Option C) provides a general framework for AI using machine learning but lacks the comprehensive "management system" scope found in 42001. Finally, the EU AI Act (Option D) is a regulation (law), not a technical standard. For a test organization looking to align its GenAI strategy with international best practices and achieve formal certification, ISO/IEC 42001 is the definitive standard to follow, as it covers the organizational processes, data handling, and risk management necessary for high-quality AI operations
サンプル問題 2： What BEST protects sensitive test data at rest and in transit?
A: Rely on obfuscation instead of encryption
B: Enforce role-based access controls
C: Disable TLS and rely on VPN only
D: Use public file shares with read-only links
正解：B
Explanation: Data security is a paramount concern when using GenAI in testing, as test environments often contain sensitive business logic or PII (Personally Identifiable Information). To protect this data "at rest" (stored in databases or vector stores) and "in transit" (being sent to the LLM), a combination of technical controls is required. Role-Based Access Control (RBAC) is a fundamental security pillar that ensures only authorized individuals or services can access specific datasets or trigger GenAI workflows. This prevents unauthorized users from feeding sensitive enterprise data into public AI models. While encryption (omitted in Option A as an alternative to obfuscation) and TLS (falsely suggested to be disabled in Option C) are essential technical layers for protecting data in transit, RBAC provides the organizational "gatekeeping" necessary to manage who can interact with the AI system. In a professional GenAI strategy, testers must ensure that the tools they use adhere to strict access policies, ensuring that the "Input Data" used for prompting remains within the secured organizational boundary and is not leaked to unauthorized entities or public training sets.
サンプル問題 3： Which option BEST differentiates the three prompting techniques?
A: Few-shot = no examples; Chaining = single prompt; Meta = disable iteration
C: Chaining = give examples; Few-shot = break tasks; Meta = manual edits only
D: Few-shot = examples; Chaining = multi-step prompts; Meta = model helps draft/refine prompts
正解：D
Explanation: Differentiating between prompting techniques is essential for a tester to select the right tool for the task. Few-shot prompting is characterized by providing the model with a few examples of inputs and desired outputs, allowing it to learn the pattern and format. Prompt Chaining involves breaking a complex task into a sequence of smaller, interconnected prompts, where the output of one step becomes the input for the next (e.g., first extract requirements, then generate test cases from those requirements).Meta-prompting is a more advanced technique where the user asks the LLM to help design, write, or refine the prompt itself―essentially using the AI as a "prompt engineer" to optimize the instructions. Option D correctly identifies these core characteristics. Options A, B, and C contain fundamental mischaracterizations: for instance, Few-shot requires examples (contradicting A), and Chaining is the opposite of a single prompt (contradicting A). Mastering these distinctions allows testers to move from simple "chatting" to sophisticated AI orchestration that can handle complex, multi-stage testing workflows with high reliability.
試験はこの世界で成功しやすいことの一つです。試験は前もって範囲を教えていますから、復習はこの範囲内の自分ができないところを探し続けています。GOWUKAKUはCT-GenAI問題集を用いたCT-GenAI（ISTQB Certified Tester - Testing with Generative AI (CT-GenAI)）試験の復習方法を案内しています。
