Testing with Generative AI (CT-GenAI)

Day 1: Foundations, Prompt Engineering, and Risks

Focus: understanding the technology, creating effective prompts, and managing risks.

• Block 1: Introduction to GenAI in Software Testing
  • Fundamentals of Generative AI
  • Key concepts:
    • Large Language Models (LLMs)
    • Tokens
    • Context
  • Core principles of using GenAI in testing processes
• Block 2: Prompt Engineering for Effective Testing
  • Creating effective prompts for testers
  • Applying advanced prompt engineering techniques in practice
  • Evaluating AI-generated outputs
  • Iterative prompt improvement and optimization
• Block 3: Managing GenAI Risks in the Testing Process
  • AI hallucinations
  • Reasoning errors
  • Model bias
  • Data privacy concerns
  • Cybersecurity risks associated with AI systems

Day 2: Technical Solutions, LLMOps, and Implementation

Focus: architecture, operationalization, and organizational adoption strategies.

• Block 4: Regulations and Standards
  • AI regulations and compliance requirements (e.g., AI Act)
  • Industry standards and best-practice frameworks
  • Energy consumption and the environmental impact of Generative AI
• Block 5: LLM-Based Solutions for Testing
  • Architectural approaches for building LLM-powered testing tools (e.g., Retrieval-Augmented Generation – RAG)
  • Fine-tuning AI models
  • LLMOps fundamentals
  • Operationalizing AI solutions within testing environments
• Block 6: Implementing and Integrating GenAI in Testing Organizations
  • Building a GenAI adoption roadmap for QA teams
  • Organizational change management during the implementation of generative AI technologies
  • Best practices for integrating GenAI into existing testing workflows