AI Agent : Automated QA Test Case Generator and Executer

2026 - Build an AI Agent for API Test Automation using Python, JIRA-API & Gen AI

Welcome to "Automated QA Test Case Generator and Executer using AI" — a hands-on course that combines the power of GenAI, Langchain, and Python to fully automate the generation and execution of API test cases.

In today’s fast-paced development cycles, writing manual test cases is time-consuming and error-prone. This course introduces a modern solution: using Google Gemini via Langchain to auto-generate structured API test cases from JIRA stories, execute them dynamically with pytest, and produce rich HTML test reports.

This course is designed for QA Engineers, SDETs, and Automation Engineers who want to build a production-style, AI-assisted API testing workflow that automatically generates and executes test cases from real project requirements.

You’ll start by learning how to connect to JIRA and fetch story details, then see how those details are transformed into executable test cases using AI-powered prompt engineering. You'll also build a powerful pytest-based framework that supports dynamic test execution, custom validation, and professional-grade reporting.

Whether you're a QA engineer, SDET, or developer interested in practical AI integration, this course gives you a real-world project framework you can adapt and scale. From CI/CD-ready automation workflows to prompt tuning and error handling, everything is covered.

By the end of this course, you’ll have a fully working AI-integrated API testing framework — and the skills to extend it for any API-first project.

Skills you will learn:
1) JIRA Integration with Python
2) GenAI Integration with Pytest and Langchain
3) AI-powered prompt engineering
4) Pytest-HTML Reporting

We’ve added a brand-new Phase-2 module to take this AI-powered API automation framework to the next level.

In this update, you’ll learn how to:

• Support multiple AI models (Gemini & Groq)

• Enforce strict structured output from LLMs

• Separate AI generation from regression execution

• Execute tests in parallel using pytest-xdist

• Enhance HTML reports with API request/response logging

These enhancements make the framework production-ready and aligned with enterprise QA architecture practices.

If you’ve completed Phase-1, I strongly recommend continuing with Phase-2 to understand how to scale AI automation in real-world environments.