AI- & Vibe-Coding-Glossar
10 klare Definitionen der AI-Coding-Begriffe, die dir wirklich begegnen. Kein Marketing-Geschwafel, keine Buzzword-Parade — was der Begriff bedeutet und warum er zählt.
AI workflows
Vibe coding
Vibe coding is the practice of building software by describing intent to an AI in natural language and letting the AI write, refactor, and ship the code.
Definition lesen →Prompt engineering
Prompt engineering is the discipline of structuring instructions to language models — including context, constraints, and output format — to get reliably high-quality results.
Definition lesen →Agentic coding
Agentic coding is vibe coding done by an autonomous AI agent that reads context, plans steps, calls tools, and ships changes without you typing each instruction.
Definition lesen →Context engineering
Context engineering is the practice of choosing exactly what information goes into the model's context window — files, snippets, specs — so the AI has the right knowledge without noise.
Definition lesen →Pillar page
A pillar page is the long, evergreen guide at the center of a topic cluster — broad enough to rank for the head term, with internal links out to deeper supporting articles.
Definition lesen →AI concepts
AI tools
Model Context Protocol (MCP)
MCP is an open protocol from Anthropic that lets language models connect to external tools and data sources through a standard interface — the USB-C of LLM tool use.
Definition lesen →Cursor
Cursor is a VS Code-based AI code editor that bakes language models into the editing loop — completions, multi-file edits, codebase chat, and autonomous agents.
Definition lesen →Frontend
Design system
A design system is the shared set of reusable components, tokens, and rules a product uses to keep its UI consistent at scale.
Definition lesen →shadcn/ui
shadcn/ui is a copy-paste component library — Tailwind + Radix primitives — that has become a de facto standard for AI-generated React UIs.
Definition lesen →