Course Overview

The Generative AI in Software Testing program is a comprehensive 40-hour training designed to equip software testers, developers, and AI enthusiasts with the skills to leverage Generative AI for modern quality assurance (QA) and test automation. This hands-on course covers the core principles of artificial intelligence, including machine learning, deep learning, natural language processing, and large language models (LLMs), with a focus on their practical applications in software testing.

Participants will learn to use AI-powered QA tools such as ChatGPT, Gemini, Copilot, and MABL to generate test cases, automate testing workflows, create synthetic test data, and enhance defect detection. The program also introduces prompt engineering techniques for improving AI interactions and fine-tuning custom AI models for testing scenarios using platforms like Cohere with Retrieval-Augmented Generation (RAG).

By the end of the course, attendees will be able to design, implement, and deploy AI-driven test automation solutions, boosting efficiency and accuracy in QA processes, while staying ahead in the evolving landscape of intelligent software testing.

Program Duration

Duration: 5 days (40 hours)

Format: Classroom-based, Virtual Instructor-Led Training

COURSE OBJECTIVES

By the end of this 40-hour program, participants will be able to:

·      Understand the foundations of Generative AI

o  Explain core AI concepts, including Machine Learning, NLP, Deep Learning, and Artificial Neural Networks.

o  Identify the capabilities, benefits, and limitations of Generative AI in software testing.

·      Familiarize with Generative AI tools for QA

o  Explore various AI-powered QA tools such as ChatGPT, Gemini, Copilot, and MABL.

o  Evaluate how AI-driven tools enhance test automation and software quality assurance.

·      Apply Prompt Engineering techniques

o  Create effective prompts to leverage AI for generating test scenarios, scripts, and documentation.

o  Use AI chatbots to assist in automating testing workflows.

·      Perform AI-powered Test Automation

o  Utilize MABL for creating, recording, and enhancing automated test cases.

o  Implement assertions, waits, variable handling, and synthetic data generation for robust test automation.

o  Analyze test results and visual changes using AI insights and reporting tools.

·      Implement AI-driven Test Data and Fine-tuning

o  Generate and manage data-driven tests using AI techniques.

o  Prepare, upload, and use training data to fine-tune LLMs for QA tasks.

·      Develop and Deploy Custom AI Models for QA

o  Train and evaluate custom fine-tuned models using tools like Cohere and Python SDK.

o  Integrate Retrieval-Augmented Generation (RAG) for querying external data sources to improve testing intelligence.

·      Automate QA Workflows with Generative AI

o  Build connectors and integrate AI models with existing QA pipelines.

o  Enhance testing productivity by reducing manual effort and improving defect detection through AI automation.

SKILLS THE STUDENTS WILL GAIN

·      Artificial intelligence

·      Prompt engineering

·      Generative AI

·      Train AI Models

AUDIENCE

·      AI enthusiasts

·      Software developers

·      Software Testers

·      Test engineers