Claude Code & AI-agent glossary
Plain-English definitions for the terms behind Loreto — skills, RAG, AEO, MCP, and the rest.
A glossary of the core Claude Code, RAG, and AI-search terms — each defined in one quotable sentence, with links to related skills.
RAG (Retrieval-Augmented Generation)
RAG (Retrieval-Augmented Generation) is a technique where an AI model retrieves relevant documents and uses them as con…
AEO (Answer Engine Optimization)
Answer Engine Optimization (AEO) is the practice of structuring content so AI answer engines — ChatGPT, Claude, Perplex…
MCP (Model Context Protocol)
The Model Context Protocol (MCP) is an open standard that lets AI agents connect to external tools, data, and prompts t…
Claude Code skill
A Claude Code skill is a packaged, reusable workflow — a SKILL.md plus references and a runnable test — that drops into…
SKILL.md
SKILL.md is the entry file of a Claude Code skill: YAML frontmatter (a name and a description) followed by a markdown b…
Agentic RAG
Agentic RAG is retrieval-augmented generation where an autonomous agent decides which retriever tools to call, in what…
Knowledge graph
A knowledge graph stores entities and the typed relationships between them, enabling multi-hop and temporal queries — "…
x402
x402 is an HTTP-native payment protocol that lets AI agents pay for an API call in USDC per request, using the HTTP 402…
llms.txt
llms.txt is a proposed standard file at a website’s root that gives AI crawlers a concise, machine-readable map of the…
Context engineering
Context engineering is the practice of curating exactly what an AI model sees at inference — retrieval, memory, and pro…
AI harness (coding agent)
An AI harness is the tooling wrapped around a model — Claude Code, Cursor, Cline — that manages context, tools, files,…
E-E-A-T
E-E-A-T (Experience, Expertise, Authoritativeness, Trust) is Google’s framework for assessing content quality and the c…
Put these ideas to work
Generate a Claude Code skill from any source and run it in your agent.