---
title: "Glossary: AI & LLMs"
type: "glossary-category"
canonical_url: "https://www.graphcanon.com/glossary/ai-and-llms"
---

# AI & LLMs

_The model-layer vocabulary you meet across tool pages, comparisons, and stacks - what the words mean before you pick a tool._

Key concepts: Models, Prompting, Retrieval, Agents

## AI agent

An AI agent is a system that uses a language model to decide and take actions - calling tools, running steps in a loop - toward a goal, rather than just answering once.

[Read more](/glossary/ai-and-llms/ai-agent.md)

## Context window

The context window is the maximum amount of text (measured in tokens) a language model can consider at once, including your prompt and its own reply.

[Read more](/glossary/ai-and-llms/context-window.md)

## Embedding

An embedding is a list of numbers (a vector) that represents the meaning of a piece of text, image, or code so that similar things sit close together.

[Read more](/glossary/ai-and-llms/embedding.md)

## Fine-tuning

Fine-tuning further trains a pretrained model on your own examples so it adapts to a specific task, tone, or format.

[Read more](/glossary/ai-and-llms/fine-tuning.md)

## Hallucination

A hallucination is when a language model produces confident but false or unsupported output - a made-up fact, citation, or API.

[Read more](/glossary/ai-and-llms/hallucination.md)

## Large language model (LLM)

A large language model is a neural network trained on huge amounts of text to predict the next token, which lets it generate and reason over language.

[Read more](/glossary/ai-and-llms/large-language-model.md)

## Model Context Protocol (MCP)

MCP is an open protocol that lets AI agents discover and call external tools and data sources over a standard interface, instead of every app inventing its own.

[Read more](/glossary/ai-and-llms/model-context-protocol.md)

## Retrieval-augmented generation (RAG)

RAG fetches relevant documents at query time and feeds them to a language model as context, so answers are grounded in your data instead of only the model's training.

[Read more](/glossary/ai-and-llms/retrieval-augmented-generation.md)

## Semantic search

Semantic search matches on meaning instead of exact keywords, usually by combining embeddings with traditional text ranking.

[Read more](/glossary/ai-and-llms/semantic-search.md)

## Token

A token is the small chunk of text (roughly a word-piece) that language models read and generate; usage and limits are counted in tokens, not characters.

[Read more](/glossary/ai-and-llms/token.md)

## Vector search

Vector search finds the items whose embeddings are closest to a query embedding, ranking by meaning rather than exact word matches.

[Read more](/glossary/ai-and-llms/vector-search.md)

[All glossary terms](/glossary.md)

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon`](/api/graphcanon)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_