Learn Gen AI for Testing: Functional , Automation, Agent AI

Explore functional testing as black-box validation of software against functional requirements, including user registration and login, user interface forms, cross-browser and mobile testing, end-to-end flows, test plans, and scenarios.

Learn API testing that validates login flows without a user interface, using post, put, and delete requests to verify JSON or XML responses and status 200; enables early defect detection.

Explore automation testing across functional, API, mobile, and cloud tests. Use selenium and playwright with Java, Python, JavaScript, or C to automate and validate tests.

Explore zero-shot, few-shot, and instruction-based prompting with ChatGPT, applying role-based context and output format controls to craft tailored responses such as seven-day October Norway itineraries and budget-friendly plans.

Analyze Grok UI for generative AI and compare its speed to ChatGPT. Review prompts that generate seven-day Norway travel plans with budgets, music, museums, and llama model support.

Master prompting through Google Gemini to generate itinerary plans with images and maps for Norway in October, and validate outputs against real-time Google results.

Explore Microsoft Copilot’s interface, prompt-driven trip planning for Norway, and the comparative capabilities of Copilot, Gemini, and ChatGPT, highlighting pros, cons, and use cases for testing and automation.

Analyze requirements with gen ai to shape testing plans and design within the sdlc. Use chatgpt, gemini, and an agentic ui to automate requirement analysis and test planning.

Leverage Gen AI to generate test effort estimates from a test estimation template, distributing 200 test cases by complexity and aligning activities from requirement analysis through closure.

Leverage Gen AI to craft software test plans, including scope, requirements, risks, entry and exit criteria, and timelines. Use prompts to generate defect reporting, stakeholder approvals, and cross-browser testing considerations.

Explore how to design functional and API test cases from a requirements document using JNI and prompt engineering, including positive and negative scenarios and sample data.

Explore test automation with Python and Java using Selenium and Playwright, then delve into a genetic framework with small agents and build your own automation agents in Python.

Learn how to set up a maven-based selenium project from scratch in Eclipse, add dependencies via pom.xml, configure Chrome driver, and run a basic Google search test.

Generate a selenium java automation script with gen ai to create a page object model and xpath for amazon.in product search, including maven dependencies and chrome driver setup.

Read a url and product name from an external Excel file using Gen AI with Apache POI, and create a simple Excel utility to fetch data.

Add an extent report to a Selenium framework using Gen AI, VS Code Copilot, and Maven; implement a report utility and integrate with tests.

Set up a gen ai testing environment by installing VS Code and Python, creating a virtual environment, and configuring gRPC and Google Gemini API keys in the .env file.

Install and configure Playwright across platforms, set up Node.js and the VS Code extension, initialize a project, install dependencies, and run a headless test on Chromium, Firefox, or WebKit.

Explore playwright basics by building a simple script, understanding context and page, and exploring record and playback alongside a move toward a generative ai perspective.

Explore Playwright basics with codegen and reporting, configure timeouts and screenshots, enable video on failure, and use the HTML reporter, while generating TypeScript tests from VS Code.

Learn how the MCP server pairs Playwright with model control protocol to generate and run automated test scripts using generative ai.

Build a simple language model app with LangChain using grok, environment keys, and a llama model to explore retrieval augmented generation and vector store retrievers.

Learn how streamlit provides a fast, interactive user interface for language models and build a streamlit chatbot with a few lines of Python and an env file for API keys.

Explore browser use for automated testing, enabling browser control, HTML extraction, and visual understanding. Use multi-tab management, element tracking, custom actions, and multi-LLM support like GPT and Gemini.

Master browser automation with the browser use agent by running tasks such as opening amazon.com, searching laptops, and adding the first result to cart using a Gemini language model.

Create a browser automation chatbot with a Streamlit UI that uses an async agent and LM providers to execute prompt-driven browser tasks.

Learn how SmolAgent from Hugging Face automates web tasks by first generating code and then executing it, using Selenium, DuckDuckGo search tool, and model-agnostic workflows.