AI Glossary

Agent-to-Agent Communication

Agentic AI

AI systems that can autonomously plan, reason, and execute multi-step tasks with minimal human intervention.

Agentic AI

**Agentic AI** refers to AI systems that can autonomously plan, reason, use tools, and execute multi-step tasks to achieve goals with minimal human intervention. Unlike traditional chatbots that respo

AI Agent Bootstrap

AI Agent Cron Jobs

AI Agent Heartbeat

AI Agent Hooks

AI Agent Memory

AI Agent Soul File (SOUL.md)

AI Agent Webhooks

AI Agents

Autonomous AI systems that can perceive their environment, make decisions, and take actions to achieve specific goals.

AI Hallucination

When an AI model generates information that sounds plausible but is factually incorrect, fabricated, or nonsensical.

AI Lead Generation

AI Orchestration

The coordination of multiple AI models, tools, and workflows to accomplish complex tasks that no single model could handle alone.

AI Safety

The field focused on ensuring AI systems behave as intended, avoid harmful outputs, and remain under human control.

AI Voice Agents

Answer Engine Optimization (AEO)

The practice of optimizing content to appear in AI-generated answers from search engines, chatbots, and AI assistants rather than traditional search result listings.

API

Application Programming Interface—a set of rules that allows different software applications to communicate and share data.

Attention Mechanism

A technique that allows AI models to focus on relevant parts of input when processing, enabling better understanding of context and relationships.

Chain of Thought

A prompting technique that improves AI reasoning by asking the model to show its step-by-step thinking process.

Chatbot

A software application designed to simulate conversation with human users, ranging from simple rule-based systems to advanced AI assistants.

Claude Code

Clawdbot

Context Window

The maximum amount of text (measured in tokens) that a language model can process in a single interaction.

Context Window

The **context window** is the maximum number of tokens a large language model can accept as input and generate as output in a single interaction. It determines how much information the model can "see"

Conversational AI

AI systems designed to engage in natural dialogue with humans, understanding context and generating relevant responses.

Deep Learning

A subset of machine learning that uses neural networks with many layers to learn complex patterns from large amounts of data.

Embeddings

Numerical representations of text, images, or other data that capture semantic meaning in a format AI models can process.

Few-Shot Learning

Teaching AI models to perform tasks by providing a small number of examples (typically 1-10) in the prompt.

Fine-tuning

The process of further training a pre-trained AI model on a specific dataset to improve its performance on particular tasks.

Foundation Model

Large AI models trained on broad data that can be adapted to many downstream tasks, serving as a base for specialized applications.

Function Calling

The ability of AI models to identify when a user request requires an external function and generate the structured data needed to call it.

Generative AI

AI systems that can create new content—text, images, audio, video, or code—rather than just analyzing existing data.

GPT (Generative Pre-trained Transformer)

A series of large language models by OpenAI that generate text by predicting the next word, powering ChatGPT and many AI applications.

HIPAA-Compliant AI

Inference

The process of using a trained AI model to make predictions or generate outputs from new inputs.

Knowledge Base

A structured collection of information that AI systems can search and reference to provide accurate, grounded responses.

Large Language Model (LLM)

A neural network trained on massive text datasets that can understand and generate human-like language.

Machine Learning

A type of artificial intelligence where systems learn patterns from data to make predictions or decisions without explicit programming.

MCP (Model Context Protocol)

Mixture of Experts (MoE)

**Mixture of Experts (MoE)** is a neural network architecture where input is routed to a subset of specialized "expert" sub-networks. This enables models with trillions of parameters while only activa

Model Context Protocol (MCP)

An open protocol that standardizes how AI assistants connect to external data sources, tools, and systems.

Moltbook

Multi-Agent Systems

Multimodal AI

AI systems that can process and generate multiple types of data—text, images, audio, and video—within a single model.

Natural Language Processing (NLP)

The field of AI focused on enabling computers to understand, interpret, and generate human language.

Neural Network

A computing system inspired by the human brain, using interconnected nodes (neurons) to learn patterns from data.

No-Code AI

Platforms and tools that enable users to build AI applications through visual interfaces without writing code.

OpenClaw

Pre-training

The initial phase of training AI models on large datasets to learn general patterns before specializing for specific tasks.

Prompt Engineering

The practice of designing and refining inputs to AI models to get better, more accurate, and more useful outputs.

Prompt Injection

A security vulnerability where malicious inputs manipulate AI systems into ignoring their instructions or performing unintended actions.

QMD (Query Markup Documents)

**QMD** is an on-device search engine created by Tobi Lutke (Shopify CEO) that indexes and searches markdown files, meeting transcripts, documentation, and knowledge bases using a hybrid approach comb

Retrieval-Augmented Generation (RAG)

A technique that enhances AI responses by retrieving relevant information from external knowledge sources before generating an answer.

Semantic Search

Search that understands meaning and intent rather than just matching keywords, using AI to find conceptually similar content.

System Prompt

Special instructions given to an AI model that define its behavior, personality, and constraints before any user interaction.

Temperature

A parameter that controls the randomness and creativity of AI model outputs, with lower values being more deterministic.

Token Optimization

**Token optimization** refers to strategies and techniques for reducing the number of tokens consumed when interacting with large language models (LLMs), directly impacting both cost and performance.

Tokens

The basic units that language models use to process text, typically representing parts of words, whole words, or punctuation.

Transformer

The neural network architecture that powers most modern AI language models, using attention mechanisms to process sequences efficiently.

Vector Database

A specialized database designed to store and efficiently search high-dimensional vectors, enabling semantic search and AI applications.

Webhook

An automated HTTP callback that sends data to another application when a specific event occurs, enabling real-time integration between systems.

Zero-Shot Learning

The ability of AI models to perform tasks without any task-specific training examples, using only instructions.