Plain-English definitions of the AI and LLM terms that actually matter for developers building with Claude, GPT-4, Gemini, and open-source models.
RAG is a technique that feeds relevant documents to an LLM at query time, so the model generates answers grounded in your actual data instead of relying on training knowledge alone.
Chain-of-thought prompting is a technique where you instruct an LLM to break down its reasoning into explicit steps before producing a final answer, dramatically improving accuracy on complex problems.
MCP is an open protocol created by Anthropic that standardizes how AI models connect to external tools, databases, and APIs — giving models access to real-world capabilities through a universal interface.
An AI hallucination occurs when a language model generates text that sounds confident and plausible but is factually incorrect, fabricated, or unsupported by its training data.
Fine-tuning is the process of continuing to train a pre-trained language model on a smaller, domain-specific dataset to specialize its behavior for particular tasks or knowledge domains.
Prompt engineering is the practice of crafting inputs (prompts) that guide AI language models to produce accurate, relevant, and useful outputs for specific tasks.
The context window is the maximum number of tokens (words and word fragments) that a language model can read and generate in a single conversation turn.
Embeddings are dense numerical vectors that represent text (or images, audio) in a high-dimensional space where semantically similar items are positioned close together.
Few-shot learning is a prompting technique where you provide a small number of input-output examples in the prompt to teach the model the desired behavior without any fine-tuning.
A system prompt is a set of instructions given to an AI model before the user conversation begins, defining the model's role, personality, constraints, and behavior rules.
