Gen AI & Agentic AI for Software Automation Testing

Name: Gen AI & Agentic AI for Software Automation Testing
Rating: 4.4 (3992 reviews)

Learn GenAI & Agentic QA with Playwright MCP/CLI, Codex, Agent SKILLS, Local LLMs, Selenium & GitHub Agentic Workflows

Created byKarthik KK

Last updated 11/2026

English

Arabic [Auto],German [Auto],

What you'll learn

Understand the basics of Generative AI and its real world use cases
Understand different LLMs available in the market
Using Local LLMs to harness in power within local machine with Llama 3.x Models
Using Gen AI in Automation and Manual Software Testing
Using Gen AI related tools in Software Testing like TestRigor, ZeroStep, Playwright etc
Using Gen AI APIs to extend automation testing capabilities with Intelligent Test execution

Course content

16 sections • 96 lectures • 11h 24m total length

Introduction6:29
Explore how generative AI applies to software testing, including manual and automated testing. Learn to generate test cases, map data, generate code, and track bugs with AI.

Introduction1:34
Introduction to Generative AI and Why for Software Testing ?9:11
Explore how generative AI uses large language models to generate software code and manual test cases, and learn tokenization, data sources, and free tier access.
What is Large Language Model and what are its potential ?12:43
Harness ChatGPT and GPT models to generate simple selenium c-sharp dotnet login tests for app.somi.com, with setup, locator weighting, and wait mechanisms.
Understanding AI Agents and How they make LLM so useful?9:50
Explore how ChatGPT uses AI agents to perform research operations, including online search, deep research, enterprise automation comparisons between Playwright and Selenium, and an 80% reduction in test execution time.
What is Prompt Engineering and Why its so important for Software Testing?10:13
Discover how cloud models like Claude's sonnet and opus power generative ai for test automation, including prompt engineering and auto generation of selenium c# framework code and page object models.
What is Context Engineering and how its different from Prompt Engineering5:04
Summary0:45
Test your knowledge !

Introduction5:14
Discover how to run LLaMA from Meta locally for software testing, enabling data privacy, cost savings, and self-contained inference with GPT for all and other local tools.
Introduction to different AI Model and how HuggingFace is so powerful9:14
Running an Small Language Model in our Local Machine (Edge Devices)9:24
Running an Large Language Model locally - QWEN Model with 27B Parameters5:18
Writing Selenium Code with Framework level using your iPhone with Local Model6:21
Accessing Local AI Model running in Ollama via API with Postman9:15
Accessing Local LLM with LM Studio as the inferencing Engine12:25
Running MultiModel like Voice/Text/Image with LFM3 Omini in oMLX Engine8:04
Test your knowledge !

Introduction2:07
Writing Manual Tests with the Power of Generative AI10:02
Generating Manual Tests with Agentic AI Tools like Codex10:27
Understanding Context Augmented Generation (CAG) for Generating Test Cases8:44
Generating Manual Test Case with Test Requirement, Product Requirement using CAG6:42
Using Local Large Language Model to Generate BDD Test Cases with CAG8:27
Understanding RAG (Retrieval Augmented Generation) and using it with AnythingLLM11:14
Configuring RAG with AnythingLLM and getting grounded Answer with Local LLM9:15
How RAG works with in Real world with ChatBots in AI Applications6:56
Test your knowledge!

Introduction1:49
What is an AI Agent and how it helps LLM to access external world !6:04
What is an Model Context Protocol (MCP) server and how it helps LLM with Testing6:37
Understanding and Configuring Playwright MCP Server in Claude Desktop12:15
Understanding Tools of Playwright MCP Server and how it invokes behind the scene6:13
Configuring MCP Server in LM Studio and using with Local LLMs for Testing9:41
Configuring FileSystem MCP Server and using it for File System Operation4:42

Introduction3:15
Using VS Copilot For Writing Agentic Automated QA Test using MCP Servers10:19
Configuring Playwright MCP Server with VS Copilot to write Automated Test7:37
Create Agentic Playwright Test with Test Plan and Product Requirement7:09
Creating Agentic E2E Testing of Playwright with Framework code using Codex17:07
Running Agentic Test with Codex CLI and understanding Claude Code6:54
Running Agentic Test with Local LLM using Pi Coding Agent for FREE, Private Test9:21
Using Agentic Tools to Refactor and Understand Existing Automation Test Code6:26

Introduction2:01
Introduction to Playwright CLI and how its different from Playwright MCP Server3:31
Installing Playwright CLI and using it without Coding Agents6:53
Using Local LLMs + Coding Agent to run Test using Playwright CLI6:18
Understanding Agent SKILLs and installing Playwright Agent SKILLs11:08
Using Playwright Agent SKILLs with Local LLMs + Coding Agent for better Output5:03
Understanding Playwright Test Agents (Planner/Generator/Healer)4:53

Introduction7:45
Explore how generative AI enhances API testing for microservices. Learn to use Swagger and Postman, test get/post/put/delete operations, and generate robust scenarios with a large language model.
Writing RestSharp API Testing with Application Schema14:16
Leverage swagger schemas to auto-generate RestSharp API tests in csharp .net, using a builder pattern and schema-driven prompts to cover all endpoints, serialization, and edge cases.
API Testing with PostBot of Postman - An Gen AI Feature3:49
Leverage postman's post bot AI feature to automatically write and run tests for API requests, generate test scripts from Swagger schemas, and leverage ChatGPT and AI tools.

Introduction to GitHub Agentic Workflow3:27
Understanding how GitHub Agentic Workflow Works with a Demo11:06
Running Smoke Test GitHub Agentic Workflow in Repository using Playwright CLI12:45
Understanding more Agentic Workflows to use for Repository Automation7:59
Start HandCoding Repo-Ask Agentic Workflow for Repository Automation12:08
Adding Agent Engine to the Agentic Workflow4:49
Compiling and Running the Repo-Ask Agentic Workflow in GitHub10:28
Creating Smoke-Test Agentic Workflow using Coding Agent and Playwright CLI13:25
Running the Smoke-Test Agentic Workflow in GitHub with Issue Trigger2:51

Requirements

Basics of Programming
Basics of Software Testing
Curiosity to learn modern Cutting Edge Tech

Description

Welcome to this practical, hands-on course on Generative AI and Agentic QA for Software Testing, where you will learn how to integrate modern AI technologies into real-world software testing activities.

This course goes beyond using ChatGPT to generate test scripts. You will explore how AI coding agents such as OpenAI Codex, GitHub Copilot, Claude Code, and Pi Coding Agent can work with Playwright, MCP servers, command-line tools, and LLMs to assist with end-to-end software testing.

Here’s what you’ll master:

Understand Generative AI, Large Language Models (LLMs), AI Agents, and how they are transforming modern software testing.
Master Prompt Engineering and Context Engineering to get better results from AI-powered testing tools.
Generate manual test cases, test plans, BDD scenarios, and test data from software requirements using Generative AI.
Explore RAG and CAG to generate context-aware test cases using requirements, product documentation, and local AI models.
Run Local LLMs using Ollama and LM Studio for private, secure, and cost-effective AI-assisted test development.
Understand Model Context Protocol (MCP) and use Playwright MCP Server with AI Agents to automate real web applications.
Use Playwright CLI and Agent SKILLS with AI coding agents for intelligent browser automation and testing.
Build Agentic End-to-End Test Automation using OpenAI Codex, GitHub Copilot, Claude Code, and Pi Coding Agent.
Leverage Generative AI for API Testing using Swagger, RestSharp, Postman, and AI-powered test generation.
Explore self-improving automation tests and intelligent locator healing using LLMs with Selenium and C#.
Integrate automated tests into CI/CD pipelines using GitHub Actions and AI-assisted workflow generation.
Build GitHub Agentic Workflows to automate repository-level testing, smoke tests, and issue-triggered QA activities.

By the end of this course, you will understand how to apply Generative AI and AI Agents across multiple stages of the software testing lifecycle—from requirements analysis and test design to automated execution, API testing, and continuous integration.

Learn to move beyond traditional test automation and explore the next generation of AI-powered software testing.

Who this course is for:

BA
QA
Dev
Anyone who is interested in AI

Gen AI & Agentic AI for Software Automation Testing

What you'll learn

Explore related topics

Course content

Introduction to Course and Gen AI1 lecture • 6min

Introduction to Generative AI, AI Agents and LLMs7 lectures • 49min

Running Large Language Models (LLMs) in Local Machine ⚡️8 lectures • 1hr 5min

AI-Powered Manual Testing: Requirements, Test Plans, and Test Design⚡️9 lectures • 1hr 14min

Understanding AI Agents, MCP Servers and Tool Calling in both Cloud & Local LLM7 lectures • 47min

Agentic QA for Software Automation Testing with MCP Server, Local and Cloud LLM8 lectures • 1hr 8min

Understanding and Working Playwright CLI and Agent SKILLs7 lectures • 40min

API Testing with Gen AI ⚡️3 lectures • 26min

CI/CD of Application with GitHub Actions using Copilot/Codex4 lectures • 27min

Working with GitHub Agentic Workflows using AI Agents for Repository Automation9 lectures • 1hr 19min

Requirements

Description

Who this course is for: