AI & QA Learning Library¶
A structured curriculum for the manual QA → AI QA transformation — from AI fundamentals and test automation, through data and LLM/RAG evaluation, to enterprise platforms, observability, and quality leadership.
🚪 Choose Your Starting Point¶
🌱 I'm new to AI testing¶
Follow The Learning Path — six stages from manual QA to AI QA, each with a goal, ordered reading, and a self-test checkpoint. 10–14 weeks, no prior AI knowledge.
⚡ I already automate — teach me AI¶
Skip to the core. Read the AI Test Strategy umbrella, then dive into AI Fundamentals for gaps and the evaluation guides for depth.
👔 I lead a QA team¶
Start with the 3-part Enterprise AI QA Strategy — governance, RAG evaluation, and observability — plus the AI QA Lead role requirements.
⭐ Featured Guides¶
AI Fundamentals for Beginners¶
Everything from zero — ML, neural networks, LLMs, RAG, and how each is tested.
Playwright Framework Tutorial¶
From bare project to professional framework — Page Objects, fixtures, CI.
AI Test Strategy¶
How to test LLMs, RAG, agents, MCP & multi-agent systems — one umbrella page.
RAG Evaluation Metrics — Deep Dive¶
Whitepaper-grade metric mechanics — the math behind faithfulness, recall, NDCG.
Enterprise LLM Gateway Architecture¶
How a proxy in your cloud routes to Claude on Bedrock — every element explained.
LLM Observability — LiteLLM & Langfuse¶
Track usage, capture logs, and see the problems in production.
🗂️ Browse the Full Library¶
🧭 Foundations¶
🎭 Automation Testing¶
- Playwright Project Anatomy
- Playwright Framework Tutorial
- API Testing with Playwright
- Playwright Advanced Guide
- Advanced API Testing
📊 Data Testing¶
🤖 AI Testing¶
🤝 AI-Assisted QA¶
- AI QA Agents Catalogue
- Test-Case Generator Agent
- Autonomous QA Multi-Agent Pipeline
- LLM Observability — LiteLLM & Langfuse
☁️ Cloud AI Platforms¶
🏛️ AI Rollout Strategy¶
- Overview — 3-Part Blueprint
- Part 1 — Foundations & Risk
- Part 2 — RAG Testing & Evaluation
- Part 3 — Adoption & Observability