Overview

ActiveLearning’s AI Software Testing Training Philippines course gives testers and QA teams practical skills they can apply on the job right after class. In 14 hours of high quality onsite or live online training, you use generative AI to speed up test analysis, test case design, test scripts, and regression testing, so you spend more time on the testing work that actually needs human judgment. You also learn how to write clear, structured prompts, spot AI hallucinations and bias, and keep your test data safe when working with AI tools.

By the end of this AI Software Testing Training Philippines program, you leave with a reusable set of prompts and methods for AI-assisted testing, plus the skills to help your team adopt generative AI responsibly. What you get from AI Software Testing Training Philippines:

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

Who Should Attend

Individual Professionals

This course is designed for testers, test analysts, test automation engineers, and test managers looking to bring generative AI into their daily testing work. It’s also a strong fit for user acceptance testers and developers who test their own work, as well as business analysts, project managers, and quality managers who want a practical, hands-on start with generative AI in testing.

Organizations and Teams

For QA and testing teams adopting AI tools across their test process, this course builds a shared way of working with generative AI, from prompting practices to risk guidelines. It’s especially useful for software development and IT teams that need consistent AI practices, as well as IT directors and managers building a generative AI strategy for testing across their organization.

Prerequisites

No coding is required for this course. Basic knowledge of software testing is expected. The ISTQB Foundation Level (CTFL) certificate is the formal entry requirement for the CT-GenAI exam, so we recommend CTFL knowledge or certification. Participants need a laptop and internet access for the hands-on exercises.

Course Outline

Introduction to Generative AI for Software Testing

  • AI spectrum: symbolic AI, classical machine learning, deep learning and generative AI
  • Basics of LLMs: tokens, context windows, embeddings and transformers
  • Foundation, instruction-tuned and reasoning LLMs
  • Multimodal LLMs and vision-language models
  • Key LLM capabilities for test tasks
  • AI chatbots versus LLM-powered testing tools
  • Hands-on: tokenization and token counts; prompts with text and image inputs

Prompt Engineering for Effective Software Testing

  • Structure of a prompt, and system prompts versus user prompts
  • Core prompting techniques for software testing
  • Test analysis with generative AI
  • Test design and test implementation with generative AI
  • Automated regression testing with generative AI
  • Test monitoring and test control with generative AI
  • Choosing the right prompting technique for each test task
  • Metrics for evaluating generative AI results on test tasks
  • Techniques for evaluating and iteratively refining prompts

Managing Risks of Generative AI in Software Testing

  • Hallucinations, reasoning errors and bias: how to spot and reduce them
  • Handling the non-deterministic behavior of LLMs
  • Data privacy and security risks, and how to protect test data
  • Energy use and environmental impact of generative AI
  • AI regulations, standards and best-practice frameworks

LLM-Powered Test Infrastructure for Software Testing

  • Key architecture components of LLM-powered test infrastructure
  • Retrieval-Augmented Generation (RAG)
  • LLM-powered agents in test automation
  • Fine-tuning LLMs for test tasks
  • LLMOps for deploying and managing LLMs

Deploying and Integrating Generative AI in Test Organizations

  • Risks of shadow AI
  • Key parts of a generative AI strategy for testing
  • Selecting LLMs and small language models (SLMs) for test tasks
  • Phases of adopting generative AI in testing
  • Skills, team capability building and evolving test processes