From @pranjulya.si. One free resource for every step, plus a 6-month plan.

<aside> ⏱️

The plan assumes about 10 hours a week alongside a job. Backend dev? Skip Month 1 and start at step 4.

</aside>

Month 1: Foundations

  1. Python: The official Python tutorial
  2. APIs: FastAPI tutorial (build a small REST API)
  3. SQL: SQLBolt (interactive lessons)

Month 2: How AI works

  1. ML basics: Google Machine Learning Crash Course
  2. Neural nets: 3Blue1Brown: Neural networks
  3. Tokens + context: play with the OpenAI tokenizer, then watch Andrej Karpathy's "Let's build the GPT Tokenizer" on YouTube
  4. Embeddings: The Illustrated Word2vec (Jay Alammar)

Months 3–5: Build (the most important part)

  1. Prompting: Prompt engineering overview (Claude docs)
  2. Structured output: Structured outputs guide (OpenAI docs)
  3. RAG: Introducing Contextual Retrieval (Anthropic)
  4. Tools + MCP: Model Context Protocol docs
  5. Agents: Building effective agents (Anthropic)

Month 5: Production

  1. Evals: Your AI product needs evals (Hamel Husain)
  2. Tracing: Langfuse docs (open source LLM tracing)