Intermediate guides are for readers who have written prompts or built a small LLM feature and now want it to work reliably. Most of the AI agent guides sit here: production MCP servers, memory and retrieval, guardrails, human approval, observability, evals, cost control and deployment, each with runnable Python.
On the prompting side they cover the mental model series, long-form writing, long-context prompting, Program-of-Thought and routing between small and large models. The security guides at this level cover prompt injection defences for agents, secure prompt design, input and output validation, monitoring and a production checklist. You should be comfortable with Python and with the basic parts of a prompt; if a term is new, a beginner guide explains it.
The library lists all guides with filters for topic, level, category and reading time.