AI Glossary

Understand core AI concepts, from basics to practice. Plain-language explanations of trending terms like Agent, RAG, MCP, and more.

Application

Agent

The essence of an Agent is iterative execution — perceive → plan → act → observe → replan, repeating until the task is complete or a termination condition is met.

Read More
Tool

Chain of Thought (CoT)

CoT (Chain of Thought) is a method that guides models to展开 reasoning step by step, making intermediate judgments explicit to reduce skipping and guesswork.

Read More
Application

Computer Use

Computer Use is the ability for an AI model to recognize interface elements by taking screenshots and simulate mouse clicks and keyboard input to control a computer.

Read More
Model

Context Window

Context Window is the maximum number of tokens a model can process in a single request, including input content, conversation history, system prompts — with space typically reserved for output as well.

Read More
Model

Cosine Similarity

Cosine Similarity measures how close two vectors are in "direction," with values closer to 1 indicating greater similarity.

Read More
Model

Embedding

The essence of Embedding is converting text into a sequence of numbers (vectors), so that semantically similar content has close distances in the numeric space.

Read More
Model

Embedding Model

An Embedding Model is a model specifically designed to convert text into vectors, and it determines "how good the converted vectors are.

Read More
Methodology

Fine-tuning

Fine-tuning is the technique of continuing to train an already-trained large model on domain-specific or task-specific data, so the model performs better in that scenario.

Read More
Protocol

Function Schema

Function Schema is a structured description of a tool's capabilities, serving as the "parameter contract" when the model calls a tool.

Read More
Methodology

Harness Engineering

Harness Engineering is an Agent development methodology with the core idea of "harnessing Agent behavior through carefully designed systems, enabling maximum efficiency within boundaries.

Read More
Protocol

MCP (Model Context Protocol)

MCP (Model Context Protocol) is an open protocol that enables AI applications to connect to external capabilities in a unified way.

Read More
Application

Memory (Agent Memory)

Memory is an Agent's ability to save and reuse information, enabling it to maintain coherence across multiple interactions and complex tasks.

Read More
Application

OpenClaw

OpenClaw is a local-first personal AI assistant that runs on your own device and communicates with you through multiple channels.

Read More
Application

Prompt

A Prompt is the input content given to the model, and the direct basis for the model to understand the task — it's not just "one sentence of instruction," but a task description that simultaneously includes goals, context, materials, constraints, and output requirements.

Read More
Application

Prompt Engineering

Prompt Engineering is the process of designing, testing, comparing, and iteratively optimizing Prompts around model output effectiveness.

Read More
Tool

RAG

RAG (Retrieval Augmented Generation) is an architecture of "retrieve external materials first, then generate answers based on those materials.

Read More
Tool

ReAct

ReAct (Reasoning + Acting) is a working mode that makes models alternate between "think, act, observe" cycles.

Read More
Tool

Retrieval

Retrieval is the process of finding the most relevant information from large amounts of data for the current question.

Read More
Application

SKILL (Agent Skill)

SKILL is a specific capability unit that an Agent can execute, defining "what it can do" and "how to do it.

Read More
Protocol

Structured Output

Structured Output is the ability to have models return results in a predefined structure, such as JSON, object fields, or fixed enumerated values, rather than free-form text.

Read More
Application

System Prompt

System Prompt is the global rule layer set for the model before a conversation starts, defining role, goals, boundaries, and default behavior.

Read More
Model

Temperature

Temperature controls the randomness of model output.

Read More
Model

Token

A Token is the smallest unit of measurement when a model processes text, not equal to "character" or "word," but rather text fragments segmented by a tokenizer.

Read More
Protocol

Tool Calling

Tool Calling is the ability that enables models to convert "what should I do" into "which tool should I call, what parameters should I pass.

Read More
Model

Top-p

Top-p limits the sampling candidate range, selecting only from the smallest set of words whose cumulative probability reaches the threshold.

Read More
Foundation

Transformer Architecture

Transformer is a deep learning architecture proposed by Google in 2017 that uses "Self-Attention Mechanism" to enable models to simultaneously process relationships between any positions in a sequence.

Read More
Tool

Vector Database

A Vector Database is a database specifically designed to store high-dimensional vectors and support semantic similarity retrieval.

Read More
Application

Zero-shot / Few-shot

Zero-shot and Few-shot are ways to complete tasks through Prompt without training the model — essentially "learning through context" (In-context Learning).

Read More