ExamFinch.com My Study

Cheat sheet

ISTQB CT-GenAI Cheat Sheet

Practice this exam

GenAI Foundations

  • 12% of exam
  • AI spectrum LLM building blocks LLM test capabilities Tokenization + embeddings Foundation vs reasoning Multimodal models

Prompt Engineering

  • 45% of exam
  • Prompt components Prompting techniques Prompting for test tasks Zero/one/few-shot System vs user prompt Meta prompting

Managing GenAI Risks

  • 20% of exam
  • GenAI defects Non-determinism control Attack vectors AI standards + regulations Hallucination + bias GDPR + privacy

LLM Test Infrastructure

  • 13% of exam
  • LLM test architecture RAG + agents Fine-tuning + LLMOps Vector database Relational vs vector Orchestration

Organizational Adoption

  • 10% of exam
  • Shadow AI Adoption phases GenAI strategy Selecting models Prompt patterns Evolving test roles

Quick Facts

  • Exam CT-GenAI Specialist
  • Credential Testing with Generative AI
  • Questions 40 multiple choice
  • Time 60 min (75 non-native)
  • Pass 65% (26/40)
  • Level Specialist
  • Prerequisite ISTQB Foundation (CTFL)
  • K-levels K1, K2, K3
  • Weights By syllabus teaching time

Five Syllabus Chapters FO

  • Foundations | Prompting | Risks | Infrastructure | Adoption
  • Ch1: foundations Ch2: prompting Ch3: risks Ch4: infrastructure Ch5: adoption

Foundation vs Reasoning LLM FO

Foundation LLM

  • General-purpose base
  • Broad pretraining
  • Needs task adaptation

Reasoning LLM

  • Multi-step logic
  • Chain-of-thought
  • High-cognitive tasks
  • Base vs deep reasoning

AI Spectrum FO

  • Symbolic AI Rule-based logic systems
  • Machine learning Data-driven pattern models
  • Deep learning Neural network layers
  • Generative AI Creates new content
  • Foundation LLM General-purpose pretrained base
  • Instruction-tuned LLM Follows user instructions
  • Reasoning LLM Multi-step chain-of-thought

AI Spectrum FO

  • Symbolic | ML | Deep | Generative
  • Symbolic: rules ML: data-driven Deep: neural nets Generative: creates content

Chatbot vs LLM Application FO

AI chatbot

  • Conversational UI
  • Direct prompting
  • Ad-hoc tasks

LLM application

  • API-integrated
  • Automated tasks
  • Scalable, embedded
  • Chat vs integrated

LLM Building Blocks FO

  • Tokenization Text split into tokens
  • Embedding Token as numeric vector
  • Transformer Attention-based architecture
  • Context window Max tokens per call
  • Temperature Controls output randomness
  • Non-determinism Same input, varying output
  • SLM Small language model
  • Multimodal model Text, image, audio

LLM Test Capabilities FO

  • Requirements analysis Spot gaps, ambiguities
  • Test case creation Generate cases, objectives
  • Test oracle Generate expected results
  • Test data Datasets, boundary values
  • Automation support Generate, improve scripts
  • Result analysis Summarize, classify anomalies
  • Testware creation Plans, reports, docs

Six Prompt Components PR

  • Role | Context | Instruction | Input | Constraints | Output
  • Role: persona Context: background Instruction: task Input: data Constraints: limits Output: format

System vs User Prompt PR

System prompt

  • Developer-defined
  • Sets rules
  • Stays constant

User prompt

  • Per-interaction input
  • Changes each turn
  • Visible request
  • Rules vs request

Prompting Technique Picker PR

  • No examples needed → Zero-shot ( Simple task )
  • Show one example → One-shot
  • Show several examples → Few-shot ( Consistent format )
  • Complex multi-step task → Prompt chaining ( Verify each step )
  • Improve the prompt → Meta prompting
  • Set persistent rules → System prompt
  • Assign a persona → Role component

Six Prompt Components PR

  • Role Persona for model
  • Context Background test information
  • Instruction The task directive
  • Input data Stories, code, examples
  • Constraints Restrictions and rules
  • Output format Expected response structure

Three Core Techniques PR

  • Prompt chaining | Few-shot | Meta prompting
  • Chaining: step-by-step Few-shot: examples Meta: refine prompts

Zero-shot vs Few-shot PR

Zero-shot

  • No examples
  • Relies on pretraining
  • Simple tasks

Few-shot

  • Several examples
  • In-context guidance
  • Consistent format
  • None vs examples

Test Task Picker PR

  • Find test-basis gaps → Test analysis
  • Create test cases → Test design
  • Need expected result → Test oracle
  • Generate test inputs → Test data generation
  • Build test scripts → Automation support
  • Summarize test results → Result analysis

Prompting Techniques PR

  • Zero-shot No examples given
  • One-shot Single example given
  • Few-shot Several examples given
  • Prompt chaining Break into verified steps
  • Meta prompting LLM refines its prompts
  • System prompt Developer-set behavior rules
  • User prompt Per-interaction input

Prompting for Test Tasks PR

  • Test analysis Conditions, coverage, defects
  • Test design Cases from user stories
  • Regression testing Keyword-driven scripts
  • Test monitoring Metrics from test data
  • Boundary value Suggested test technique
  • Gherkin style Given-When-Then conditions
  • Prioritization Rank by risk

NIST AI RMF RI

  • Govern | Map | Measure | Manage
  • Govern: culture Map: context Measure: analyze Manage: respond

Hallucination vs Reasoning Error RI

Hallucination

  • Fabricated content
  • Unsupported facts
  • Invented criteria

Reasoning error

  • Faulty logic
  • Misread structure
  • Wrong conclusion
  • False fact vs bad logic

Risk Mitigation Picker RI

  • Output looks wrong → Cross-verification ( Check sources )
  • Outputs keep varying → Lower temperature ( Set random seed )
  • Complex reasoning fails → Prompt chaining
  • Handling sensitive data → Anonymize input ( Data minimization )
  • Untrusted input data → Secure environment
  • Need AI governance → NIST AI RMF

GenAI Defects RI

  • Hallucination Confident but wrong output
  • Reasoning error Faulty logic, inference
  • Bias Skewed training-data output
  • Cross-verification Check known sources
  • Consistency check Outputs must agree
  • Output testing Run generated testware

Non-Determinism Control RI

  • Temperature Lower for consistency
  • Random seed Reproducible sampling
  • Complete context Reduces hallucination risk
  • Divide prompts Chain into steps
  • Compare models Cross-check multiple LLMs

Attack Vectors RI

  • Data exfiltration Extract training data
  • Request manipulation Disrupt model output
  • Data poisoning Corrupt training data
  • Malicious code Hidden backdoors, calls
  • Data exposure Leak sensitive information
  • GDPR EU data protection

AI Standards + Regulations RI

  • ISO/IEC 42001 AI management system
  • ISO/IEC 23053 AI systems framework
  • EU AI Act Risk-tier regulation
  • NIST AI RMF Govern, map, measure, manage
  • CO2 emissions GenAI environmental impact

RAG vs Fine-Tuning IN

RAG

  • Adds retrieved context
  • Model unchanged
  • Update the index

Fine-tuning

  • Retrains weights
  • Teaches style
  • Costlier to update
  • Retrieve vs retrain

Architecture Picker IN

  • Need fresh enterprise data → RAG ( Vector database )
  • Teach domain style → Fine-tuning ( Retrain weights )
  • Multi-step automation → LLM agent ( Tool use )
  • Structured test data → Relational database
  • Semantic retrieval → Vector database
  • Run in production → LLMOps

LLM Test Architecture IN

  • Front-end Tester query interface
  • Back-end Auth, retrieval, prompts
  • Integrated LLM API or in-house
  • Relational database Structured test data
  • Vector database Semantic embedding retrieval
  • Post-processing Refine raw output

Autonomous vs Semi-Autonomous IN

Autonomous agent

  • Minimal oversight
  • Self-directed
  • Higher risk

Semi-autonomous agent

  • Periodic human check
  • Guards critical tasks
  • Lower risk
  • Independent vs supervised

RAG + Agents IN

  • RAG Retrieval plus generation
  • Chunking 256-512 token splits
  • Grounded response Rooted in retrieval
  • LLM agent Uses tools to act
  • Autonomous agent Minimal human oversight
  • Orchestration Multi-agent collaboration

Fine-Tuning + LLMOps IN

  • Fine-tuning Retrain on domain data
  • Overfitting Too specialized, brittle
  • Opacity Hard to explain
  • LLMOps Operate LLMs in production
  • LLM-as-a-Service Hosted vendor model
  • In-house model Self-hosted control

Three Adoption Phases AD

  • Discovery | Initiation | Utilization
  • Discovery: awareness Initiation: use cases Utilization: full integration

Adoption + Governance AD

  • Shadow AI Unapproved tool use
  • IP dispute Unclear licensing risk
  • GenAI strategy Objectives, models, compliance
  • Prompt pattern Reusable prompt template
  • Quality gate Review generated testware
  • Transparency Disclose GenAI use

Selecting Models AD

  • Model performance Benchmark for tasks
  • Fine-tuning potential Domain adaptability
  • Recurring cost Licensing plus operations
  • Community support Docs and troubleshooting

Common Traps

Hallucination vs reasoning error

  • Hallucination = false fact ≠ Reasoning error = bad logic

System vs user prompt

  • System = fixed rules ≠ User = each request

RAG vs fine-tuning

  • RAG = add context ≠ Fine-tune = retrain weights

Zero vs few-shot

  • Zero-shot = no examples ≠ Few-shot = several examples

Temperature effect

  • Low = consistent output ≠ High = varied output

Fluent vs correct

  • Fluent = reads well ≠ Correct = actually true

Relational vs vector DB

  • Relational = structured data ≠ Vector = semantic retrieval

Chatbot vs application

  • Chatbot = conversational ≠ Application = API-integrated

Last Minute

  • 1. 40 questions, 60 minutes
  • 2. 75 minutes if non-native
  • 3. Pass 65%, 26 of 40
  • 4. K1, K2, K3 only
  • 5. CTFL Foundation required first
  • 6. Five chapters; prompting is largest
  • 7. Plausible output can be wrong
  • 8. Hallucination = false fact
  • 9. Lower temperature for consistency
  • 10. RAG adds context, no retrain
  • 11. Fine-tuning retrains model weights
  • 12. Know NIST AI RMF functions
  • 13. Anonymize sensitive data always
  • 14. Lifetime certificate, no renewal

ISTQB Generative AI Testing Specialist (CT-GenAI)

  • Practice Questions 100 questions Study Guide 17 topics Cheat Sheet 92 facts Flashcards 50 cards Shorts 1 short Free CE Podcast