AI Full-Stack Learning Course

Start simple: experience one AI example, prepare the smallest environment, look at the map, then enter Chapter 1.

The course has a main line and expansion tracks. Chapters 1-9 build the core path from tools to Python, data, models, LLMs, RAG, and Agents. Chapters 10-12 are specialization tracks for vision, NLP, and multimodal/AIGC work. The elective modules are deeper side roads for deployment, advanced Python, and classic ML.

Follow the Pictures

0.1 Run the quick experience: see input -> model -> output before learning terms.

0.2 Set up the minimum environment: Python, Git, and one project folder are enough for week one.

0.3 Look at the capability map: tools, data, models, LLM, RAG, Agent, and delivery are one path.

0.4 Choose a learning path: pick one route, then start Chapter 1.

One Rule

Read briefly, run something, keep evidence. At the end of each stage, you should have something another person can inspect: a README command, a saved output, a metric table, a trace, a failure note, or a small demo.