AI & QA Learning Library¶
A self-contained, plain-English reference for testing AI systems — from the absolute basics of machine learning to LLM evaluation, RAG testing, security red-teaming, and the tools that tie it together.
Start at the top if you're new. Jump straight to a topic if you're not.
🌱 Start Here — Foundations¶
AI Fundamentals for Beginners ⭐¶
The one long read that covers everything from zero — the AI journey, machine learning, neural networks, LLMs, RAG, how they differ, and how each is tested.
🎭 Playwright & TypeScript¶
Playwright Project Anatomy ⭐¶
Every file in a Playwright project explained — package.json, node_modules,
playwright.config.ts, tsconfig.json and why they exist.
Playwright Framework Tutorial ⭐¶
Building a real, maintainable framework — Page Objects, fixtures, test data, utils, env config, CI — with every file's purpose explained.
TypeScript Cheat Sheet ⭐¶
Just enough TypeScript to read and write tests — types, interfaces, classes, generics, async/await, and the symbols you'll see daily.
🧠 Core Concepts¶
RAG vs Agents vs Agentic RAG¶
The three dominant AI architectures, side by side — what each is, when to use it.
MCP Servers — FAQ¶
What the Model Context Protocol is and why it matters for connecting LLMs to tools.
Enterprise LLM Platforms¶
Azure OpenAI, AWS Bedrock, and OpenAI compared for production use.
🧪 Testing & Evaluation¶
LLM Testing Lifecycle¶
The end-to-end process for testing a language model, stage by stage.
RAG Automation Testing Roadmap ⭐¶
A 6-stage plan for testing a RAG pipeline, with concrete test cases per stage.
LLM & Agent Evaluation Matrix¶
What to measure, and which metric answers which question.
Ragas FAQ · DeepEval FAQ¶
The two industry-standard evaluation frameworks, explained.
AI QA Agents Catalogue ⭐¶
Five practical AI agents that augment a QA team's day-to-day work.
Autonomous QA Multi-Agent Pipeline¶
A 7-agent pipeline for self-running quality engineering.
Test-Case Generator Agent¶
A JIRA + RAG + LangGraph architecture for AI-generated test cases.
MCP Testing Roadmap¶
Six steps for testing MCP-based systems comprehensively.
🛡️ Security & Red Teaming¶
Prompt Injection — Complete Guide¶
The #1 LLM security risk, how it works, and how to test for it.
Red / Blue / Purple Teams for AI¶
How adversarial, defensive, and collaborative security testing apply to AI.
🧰 Tooling¶
Commercial LLM / MCP Testing Tools¶
A survey of the paid and open-source tools in the AI-testing landscape.
💡 Framing — Why & How to Move¶
QA Evolution — Testing Intelligence ⭐¶
"QA is no longer testing software. We are testing intelligence." The case for why QA is changing.
QA → AI QA — 6-Week Transition Plan ⭐¶
A practical, week-by-week roadmap for a traditional QA moving into AI testing.