🧠 QE-AI-Track — AI for Quality Engineers¶
21 progressive parts from LLM basics to building autonomous testing agents.
| Part | Topic | Key Skills |
|---|---|---|
| - 01 | LLM Basics | Foundation models, attention, anti-hallucination rules |
| - 02 | Prompt Engineering | RICE-POT framework, 6 reusable QA templates |
| - 03 | Job Assistant AI | AI tools for daily QA workflows |
| - 04 | AI Agents | Agent architectures, planning, tool use |
| - 05 | AI Agents (n8n) | No-code QA automation, approval gates |
| - 06 | AI Agents (LangFlow) | Visual agent building, flaky test analyzer |
| - 07 | Vibe Coding Agents | AI-assisted test generation |
| - 08 | RAG | Chunking, embeddings, ChromaDB, Qdrant |
| - 09 | QA Copilot | Multi-source RAG (FastAPI + React) |
| - 10 | MCP Basics | Model Context Protocol, Playwright MCP |
| - 11 | Python for QA | Python essentials for testing |
| - 12 | MCP Creation | Build custom MCP servers |
| - 13 | CrewAI Agents | Multi-agent QA systems |
| - 14 | CrewAI QA Pipeline | End-to-end AI test pipeline |
| - 15 | Production QA Pipeline | Enterprise-grade AI QA |
| - 16-19 | DeepEval | AI evaluation, test quality metrics |
| - 20 | Browser Pilot | AI-driven browser testing |
| - 21 | LangChain | Advanced LLM orchestration |