We're so confident of our products that we provide no hassle product exchange.
ISQI CT-GenAI Exam Overview:
| Certification Vendor: | iSQI / ISTQB |
| Exam Name: | ISTQB Certified Tester Testing with Generative AI v1.0 |
| Exam Number: | CT-GenAI |
| Related Certifications: | ISTQB Certified Tester Foundation Level (CTFL) ISTQB Advanced Level Certifications ISTQB Expert Level Certifications |
| Certificate Validity Period: | Lifetime |
| Exam Duration: | 60 (+25% for non-native language speakers) |
| Exam Price: | ~150 - 200 USD (varies by region) |
| Passing Score: | 30 / 46 points (65%) |
| Exam Format: | Multiple choice, Single / multiple correct answers, 1–2 points per question |
| Real Exam Qty: | 40 |
| Available Languages: | English, German, Spanish, Portuguese, Chinese |
| Recommended Training: | ISTQB Accredited Training Providers |
| Exam Registration: | iSQI Official Registration |
| Sample Questions: | ISQI CT-GenAI Sample Questions |
| Exam Way: | Online remote proctored (iSQI FLEX) or in-person at test centres |
| Pre Condition: | Must hold ISTQB Certified Tester Foundation Level (CTFL) certification |
| Official Syllabus URL: | https://istqb.org/certifications/gen-ai/ |
ISQI CT-GenAI Exam Syllabus Topics:
| Section | Weight | Objectives |
|---|---|---|
| LLM-Powered Test Infrastructure | 10% | - RAG, fine-tuning, and model adaptation - Architecture and deployment considerations - AI agents and integration with test tools |
| Prompt Engineering for Effective Software Testing | 35% | - Prompt patterns for test design, data generation, automation - Iterative refinement and evaluation of prompts - Principles and structure of effective prompts |
| Managing Risks of Generative AI in Software Testing | 25% | - Hallucinations, bias, inaccuracy, and consistency risks - Validation, verification, and mitigation strategies - Data privacy, security, and compliance concerns |
| Deploying and Integrating GenAI in Test Organisations | 15% | - Strategy, governance, and adoption roadmap - Roles, skills, and team readiness - Measuring value and continuous improvement |
| Introduction to Generative AI for Software Testing | 15% | - Capabilities and limitations relevant to testing - Use cases across the testing lifecycle - Core concepts: Generative AI, LLMs, foundation models |
ISQI ISTQB Certified Tester Testing with Generative AI (CT-GenAI) v1.0 Sample Questions:
1. Consider applying the meta-prompting technique to generate automated test scripts for API testing. You need to test a REST API endpoint that processes user registration with validation rules. Which one of the following prompts is BEST suited to this task?
A) Role: Act as a software engineer. | Context: You are testing registration logic. | Instruction: Create Python scripts to verify endpoint behavior. | Input Data: POST /api/register with test users. | Constraints: Add checks for status codes. | Output Format: Deliver functional scripts.
B) Role: Act as an automation tester. | Context: You are validating an API endpoint. | Instruction: Generate Python test scripts that send POST requests and validate responses. | Input Data: User credentials. | Constraints: Include basic scenarios with asserts. | Output Format: Provide organized scripts.
C) Role: Act as a test automation engineer with API testing experience. | Context: You are verifying user registration that enforces field and format validation. | Instruction: Generate pytest scripts using requests for both positive (valid) and negative (invalid email, weak password, missing fields) cases. | Input Data: POST /api/register with validation rules for email and password length. | Constraints:
Include fixtures, clear assertions, and naming consistent with pytest. | Output Format: Return complete Python test files.
D) Role: Act as a test automation engineer. | Context: You are creating tests for a registration endpoint. | Instruction: Generate Python test scripts using pytest covering both valid and invalid inputs. | Input Data: POST /api/register with email and password. | Constraints: Follow pytest structure. | Output Format: Provide scripts.
2. Which statement BEST describes vision-language models (VLMs)?
A) VLMs are a subset of multimodal LLMs integrating visual and textual information.
B) VLMs are a superset of multimodal LLMs.
C) VLMs process audio and video but not images.
D) VLMs are unrelated to multimodal LLMs and focus only on UI automation.
3. Which statement about fine-tuning for test tasks is INCORRECT?
A) It replaces the model's general knowledge entirely and prevents overfitting
B) It can be applied to smaller SLMs to improve task performance with lower compute
C) It adapts a pre-trained model to a domain using task-specific data
D) It enhances relevance to organizational terminology and formats
4. Which standard specifies requirements for managing AI systems within an organization, supporting consistent GenAI use in testing?
A) EU AI Act
B) NIST AI RMF 1.0
C) ISO/IEC 23053:2022
D) ISO/IEC 42001:2023
5. Your team needs to generate 500 API test cases for a REST API with 50 endpoints. You have documented 10 exemplar test cases that follow your organization's standard format. You want the LLM to generate test cases following the pattern demonstrated in your examples. Which of the following prompting techniques is BEST suited to achieve your goal in this scenario?
A) Zero-shot prompting
B) Few-shot prompting
C) Prompt chaining
D) Meta prompting
Solutions:
| Question # 1 Answer: C | Question # 2 Answer: A | Question # 3 Answer: A | Question # 4 Answer: D | Question # 5 Answer: B |
By Hannah
