Generative AI for Testing

Enable each participant to understand the fundamentals of artificial intelligence applied to software testing, discover concrete use cases, use AI tools to generate, analyze, and automate tests, identify limitations and best practices, and build an action plan to integrate AI into their QA strategy.

Understanding and Exploring AI for QA

• Fundamentals of AI, NLP, and generative AI applied to testing
• Limitations of traditional testing and benefits of AI
• Identifying relevant use cases for testers
• Review of AI tools dedicated to software testing

Experimenting, Guiding, and Integrating

• Hands-on workshops: prompts, data, logs, scripts
• Capstone case study: end-to-end application of AI use cases
• Best practices, limitations, and ethical guidelines
• Developing an AI action plan tailored to your project context

At the end of the training, participants will be able to:

• Understand the fundamentals of AI applied to software testing,by identifying key concepts (AI, ML, NLP, LLM) and their relevance in a QA context.
• Identify the limitations of traditional testing approaches,and explain how AI can address challenges such as test debt, maintainability, and speed.
• Recognize the main use cases of AI in software quality,distinguishing potential benefits across different stages of the testing cycle (design, execution, analysis…).
• Effectively use generative AI to produce testing artifacts,by crafting appropriate prompts to generate test cases, data, or reports with critical thinking.
• Compare AI tools available on the market for testing, and select the most suitable solutions based on project type, constraints, and user profiles.
• Apply AI concretely to a complete testing scenario, generating and leveraging test cases, scripts, data, and log analyses within a continuous, hands-on project.
• Master best practices and understand the limits of AI usage, incorporating human validation, confidentiality, traceability, and responsible governance.
• Develop a realistic action plan to integrate AI in QA, defining quick wins, relevant metrics, and a progressive roadmap.

The training alternates between theoretical input, demonstrations, and hands-on exercises based on real-world cases. Each participant will have the opportunity to use the tools and produce their own results.