Overview

This AI-Powered Software Testing training teaches you how to apply generative AI and large language models (LLMs) to modern software testing. You’ll learn how to write effective prompts for test analysis, test design, and automated regression testing, how to manage the risks that come with GenAI, such as hallucinations, reasoning errors, and data privacy concerns, and how to bring LLM-powered tools into your team’s existing test infrastructure. The course closes with a practical roadmap for rolling out generative AI across a test organization, so you leave with a plan you can actually apply at work.

  • 14 hours of high quality onsite or live online training
  • Instructor-led training delivery options
  • Hands-on practice with real software testing tasks
  • Guidance on AI risks, data privacy, and responsible use
  • Letter of Course Completion
  • Unlimited course refresher for 1 year
  • Practical prompting techniques for test analysis, design, and regression testing

Who Should Attend

Individual Professionals

This course is for testers, test analysts, test automation engineers, test managers, user acceptance testers, and software developers who want practical, hands-on skills in prompting large language models for test analysis, test design, and automated regression testing. It’s also suited to project managers, quality managers, software development managers, business analysts, IT directors, and management consultants who want a working understanding of generative AI’s capabilities, limitations, and risks in a testing context, even if they won’t be writing prompts themselves day to day.

Organizations and Teams

For QA and testing teams moving from scattered, individual AI use to a shared, risk-aware approach, this course builds a common foundation across prompting practices, test data handling, and output evaluation. It’s also built for software development and IT teams standardizing their AI practices, and for IT directors and managers who need to define and roll out a generative AI strategy and adoption roadmap for testing across the organization, not just introduce the tools, but actually operationalize them.

Prerequisites

An ISTQB Foundation Level certificate is recommended before attending, since this course builds on core testing concepts. No prior AI or machine learning background is required, the course introduces generative AI and LLM concepts from the ground up.

Course Outline

Introduction to Generative AI for Software Testing

  • Foundations of generative AI and large language models (LLMs)
  • Differences between foundation, instruction-tuned, and reasoning LLM
  • Multimodal LLMs and vision-language model
  • Key LLM capabilities for test task
  • AI chatbots vs. LLM-powered testing applications

Prompt Engineering for Effective Software Testing

  • Structuring prompts for software testing tasks
  • Core prompting techniques, including system prompts and user prompt
  • Applying prompts to test analysis
  • Applying prompts to test design and test implementation
  • Using GenAI for automated regression testin
  • Test monitoring and test control with GenA
  • Evaluating GenAI results and refining prompts for better output

Managing Risks of Generative AI in Software Testing

  • Identifying hallucinations, reasoning errors, and biases in LLM output
  • Mitigation techniques for GenAI hallucinations and non-deterministic behavior
  • Data privacy and security risks when using GenAI in testin
  • Mitigation strategies to protect data and enhance securit
  • Energy consumption and environmental impact of GenA
  • AI regulations, standards, and best practice frameworks

LLM-Powered Test Infrastructure for Software Testing

  • Key architectural components of LLM-powered test infrastructure
  • Retrieval-augmented generation (RAG) for testing
  • The role of LLM-powered agents in automating test processes
  • Fine-tuning LLMs for test tasks
  • LLMOps for deploying and managing LLMs in software testing

Deploying and Integrating Generative AI in Test Organizations

  • Building a roadmap for adopting GenAI in software testing
  • Risks of “shadow AI” and how to manage them
  • Selecting the right LLMs or SLMs for test tasks
  • Phases for rolling out GenAI adoption
  • Building essential GenAI skills within test teams
  • Evolving test processes in AI-enabled organizations