
Explore zero-shot prompting by acting as a QA engineer to generate functional test cases for an e-commerce login, formatted as a simple list.
Explore chain-of-thought prompting to guide large language models to reason step by step, using prompts with role, context, and constraints to build comprehensive test suites.
Explore how tokens and the context window determine what large language models can process, with examples of tokenization, memory limits, and practical demos.
Learn practical tips to save tokens in large language model workflows, including prompt engineering, context window management, output length control, model selection, caching, and retrieval augmented generation.
Download the practice files to follow along with this section.
Learn to generate a master test plan from an SRS using generative AI, prompt engineering, and IEEE 829 formatting for an ecommerce app.
Explore agile test planning with epics and user stories, unleash generative AI to craft release and sprint test plans, and integrate Jira for automated QA workflows.
Download the practice files to follow along with this section.
Download the practice files to follow along with this section.
Learn to use GitHub Copilot in Eclipse to scan and fix a Selenium Java project, upgrade Maven dependencies, and propose fixes with AI agents.
Download the practice files to follow along with this section.
Use the playwright MCP server and AI agents to analyze network requests, API status, and 400/500 status codes, then generate a markdown network audit report for QA testing.
Understand Chrome DevTools MCP server for debugging, performance analysis, and deep diagnostics, while installing and configuring it in VS Code, including disabling usage statistics and running accessibility checks.
Leverage AI agents and MCP servers to fetch Jira user stories, automatically generate test plans and Playwright test cases, and accelerate sprint testing with human oversight.
Sign up for Jira, set up the Atlassian MCP server, and connect Jira with Confluence to create epics and user stories, start a sprint, and prepare AI-driven test plans.
Download TXT File which contains details about different custom agents created in this section.
Demonstrates invoking a lead test automation agent to delegate tasks to sub agents and generate Gherkin tests, csv files, and Playwright tests from a Jira ticket in the current workspace.
QA is changing fast, and if you've been in the field for any amount of time, you've probably already felt it. The test scripts that used to be your bread and butter? They're not enough anymore. The engineers who thrive in the next few years won't just be the ones who know how to automate. They'll be the ones who know how to build systems that automate the automation.
That's exactly what this course is about.
This course isn't a "prompt ChatGPT to write your test cases" tutorial. It's a hands-on, ground-up guide to embedding Generative AI into the way you actually work, from the first requirement to the final bug report. You'll build production-grade test suites and set up AI agents that can read requirements, write code, chase down failures, and file bugs without you babysitting them.
Along the way, you'll get real experience with tools that are already reshaping the industry: GitHub Copilot for rapid scripting, Claude Code for refactoring entire codebases straight from your terminal, and n8n for wiring together AI-powered testing workflows that would've seemed like science fiction two years ago. You'll also go deep on the Model Context Protocol (MCP), one of the most exciting developments in AI right now, which lets you connect large language models directly to your testing tools and environments.
By the time you're done, you won't just be someone who uses AI to test software. You'll be someone who builds the agents doing the testing.
That's a very different career trajectory.