These guides assume no experience with language models beyond having used a chat assistant. They explain one idea at a time, in plain language, with examples you can copy.
On the prompting side they cover what prompt engineering is, how to write a clear prompt, system and user messages, roles, few-shot examples, step-by-step reasoning, structured JSON output, grounding, summarization, a first evaluation loop and quick checks for hallucinations, plus how prompt injection works and short essays on why models miscount letters or repeat what they have seen. On the engineering side they cover what the Model Context Protocol is, how to build a first AI agent in Python, how to connect MCP servers to it, and how to run, debug and deploy it. The agent guides assume you can read and run basic Python. Each guide stands on its own.
The library lists all guides with filters for topic, level, category and reading time.