AI in Testing: From ChatGPT to Test Code Generation

Effective AI Usage in Testing: From ChatGPT to Test Code Generation

Learning objective

This workshop shows testers how to use ChatGPT and AI coding tools such as Cursor in everyday work. It covers enough model theory to explain the tools' behavior, then applies that knowledge to test design, automation, analysis, and code review.

After completing the workshop, participants will be able to:

• understand how large language models (LLMs) like ChatGPT work,
• write effective prompts for testing tasks,
• use AI responsibly when generating and reviewing automated test code.

Scope

• LLM fundamentals and practical understanding of ChatGPT
• Key concepts: AI, NLP, LLMs, prompts
• Model mechanics: tokenization, embeddings, attention mechanism
• Transformer architecture and model training basics
• Prompt engineering methods and best practices
  • role prompting ("act as")
  • few-shot prompting
  • chain-of-thought style reasoning
  • challenge/critique prompts
  • language strategy for prompting
• Testing-focused AI applications
  • test data generation
  • test case generation
  • pair-testing with AI
  • using AI to accelerate learning and analysis
• Practical exercise: generating CI setup (GitHub Actions) with AI
• AI IDE workflows (Cursor and similar)
  • AI-assisted coding and refactoring for tests
  • semantic search and working with technical documentation
• End-to-end workshop labs
  • building automated tests with Playwright and JavaScript/TypeScript
  • evaluating what to delegate to AI vs what to keep manual
• Risk and quality controls
  • common AI failure modes and hallucinations
  • safe usage patterns in test engineering
• Next-step learning paths, including API-level AI usage

Preparation

Who should attend?

The workshop is intended for testers and QA engineers who know programming fundamentals (preferably JavaScript).

What to prepare

Participants should bring a laptop prepared according to trainer instructions provided before the workshop.

Format

Most of the training is practical. Short theory blocks introduce each topic before participants work through exercises and guided implementations.

Training materials

• workshop presentation,
• ready-to-run code examples organized by module,
• working notes and reference links,
• additional guidance materials used during labs.

What you will leave with

• a working understanding of LLMs in a testing context,
• prompt patterns for common testing tasks,
• experience generating and checking automated tests with AI,
• a clear view of common failure modes and the reviews needed to catch them,
• examples and workflows you can adapt to your own project.