Section
Glossary
Every fast-moving industry accumulates a vocabulary faster than anyone can keep up with. This is Forkast’s running record of it — short, precise definitions for the protocols, infrastructure, and market terms that come up across our coverage.
A
- Agent Compliance The set of regulatory, legal, and governance obligations that organizations must meet when developing, deploying, or operating autonomous…
- Agent Evaluation and Benchmarking The systematic process of testing and measuring AI agent performance across multiple dimensions, including task completion, reasoning quality,…
- Agent Exploitation Agent exploitation is the offensive discipline of identifying and weaponizing vulnerabilities within AI agents — including credential exfiltration,…
- Agent Identity Agent identity is the set of credentials, characteristics, and records that allow an autonomous AI agent to be…
- Agent Infrastructure AI agent infrastructure is the specialized, production-grade platform layer that sits beneath agent frameworks and provides the runtime,…
- Agent Memory Agent memory is the set of mechanisms that allow an AI agent to retain, organize, and retrieve information…
- Agent-to-Agent Protocol (A2A) The Agent-to-Agent Protocol (A2A) is an open standard that enables AI agents built by different vendors or frameworks…
- Agentic AI Agentic AI refers to autonomous, goal-driven AI systems that perceive their environment, plan multi-step actions, invoke external tools,…
- Agentic Commerce Protocol (ACP)
- AI Agent Security AI agent security is the practice of protecting AI agents, their users, data, tools, identities, communications, and environments…
- AI alignment AI alignment is the field of AI safety focused on ensuring that AI systems behave consistently with human…
- AI Supply Chain Security AI supply chain security is the practice of protecting the infrastructure that AI systems depend on — model…
- AI Tokenization The process of converting raw text into numerical tokens—small, reusable subword units—that a large language model can process.
- API (Application Programming Interface) A set of defined rules, protocols, and tools that allows different software applications to communicate with each other.…
- Artificial Intelligence (AI) Artificial intelligence (AI) is the field of computer science focused on building systems that can perform tasks normally…
- Attention Mechanism An attention mechanism is a component in neural networks that computes weighted relevance scores between elements of an…
- Autonomy The degree of independence an AI agent has in making decisions and executing tasks without requiring human input,…
B
- Backpropagation Backpropagation is an algorithm for efficiently computing the gradient of a loss function with respect to a neural…
- Bias in Artificial Intelligence AI bias refers to systematic and unfair skewing in an artificial intelligence system's outputs that results from flawed…
- Blockchain
C
- Capture-the-Flag (CTF) Exercises A Capture-the-Flag (CTF) exercise is a hands-on cybersecurity competition or training format where individuals or teams solve security…
- Chain-of-thought (CoT) Chain-of-thought (CoT) is a prompting technique that instructs a large language model to produce intermediate reasoning steps—explaining its…
- Computer Vision A field of artificial intelligence that gives machines the ability to interpret and understand visual information—images, video, and…
- Context Engineering The systematic practice of designing, managing, and optimizing all the information an AI model or agent receives during…
- Context window
- Cryptocurrency A form of digital money that uses cryptography to secure transactions, verify ownership, and control the creation of…
- Cybersecurity Benchmarks Cybersecurity benchmarks are standardized testing frameworks used to evaluate the security capabilities and vulnerabilities of AI models and…
D
- Data Labeling The process of annotating raw data—text, images, audio, video—with meaningful tags or labels that machine learning models use…
- Data poisoning A type of attack where someone deliberately corrupts or manipulates the data used to train an AI model,…
- Deep Learning A subset of machine learning that uses artificial neural networks with many layers — typically three or more…
- Deepfakes and Synthetic Media
E
- Embeddings / Vector databases
- EU AI Act: The World's First Comprehensive AI Law Explained
- Explainability (XAI) Explainability (XAI) is the ability of an AI system to provide clear, understandable reasons for its outputs, enabling…
F
G
- General Data Protection Regulation (GDPR) The General Data Protection Regulation (GDPR) is a European Union regulation that governs how organizations collect, process, store,…
- GENIUS Act
- Gradient descent Gradient descent is an iterative optimization algorithm that adjusts a neural network's parameters by computing the gradient (direction…
- Guardrails
H
- High-Bandwidth Memory (HBM) High-Bandwidth Memory (HBM) is a specialized, 3D-stacked computer memory architecture designed to provide massive data throughput by placing…
- Human-in-the-loop (HITL)
I
J
- Jailbreaking (LLM) A form of adversarial prompting designed to bypass a large language model's built-in safety policies, ethical constraints, or…
L
- LangGraph LangGraph is an open-source orchestration framework built by LangChain for building stateful, multi-step AI agent applications using a…
- Large Language Model (LLM) A Large Language Model (LLM) is a neural network with billions of parameters or more, trained on vast…
M
- Machine Learning Machine learning is a branch of artificial intelligence in which systems improve their performance on a task by…
- Machine Payments Protocol (MPP) A payment infrastructure protocol developed by Stripe and Tempo that enables AI agents and automated systems to execute…
- MLOps: Machine Learning Operations Explained MLOps (Machine Learning Operations) is a set of practices that unifies machine learning system development (Dev) with ML…
- Model Context Protocol (MCP) Model Context Protocol (MCP) is an open, JSON-RPC 2.0-based wire protocol that standardizes how AI applications (called hosts…
- Model Distillation Model distillation is a machine learning technique in which a smaller student model is trained to replicate the…
- Multi-agent attacks
- Multi-agent systems
N
- Natural Language Processing (NLP) Natural Language Processing (NLP) is a field at the intersection of linguistics, computer science, and artificial intelligence that…
- Neural networks A neural network is a computing architecture made of layers of interconnected nodes (neurons) that process data by…
- Non-Human Identity (NHI) A non-human identity (NHI) is any digital credential that authenticates and authorizes a machine or software system rather…
O
- Open-Weights Models Open-weights models are artificial intelligence systems where the trained parameters—the internal mathematical values known as weights and biases…
P
R
- Reasoning models
- Red Teaming A structured, proactive testing effort designed to identify flaws, security vulnerabilities, and potential risks within an AI system,…
- Reinforcement learning Reinforcement learning is a machine learning approach where an agent learns to make decisions by receiving rewards for…
- Responsible AI A set of principles, practices, and governance structures that guide the design, development, deployment, and use of AI…
- Retrieval-Augmented Generation (RAG) Retrieval-Augmented Generation (RAG) is an architecture pattern that enhances a large language model's responses by first retrieving relevant…
S
- Sandbox Escape A sandbox escape in AI occurs when a model breaks out of its designated, isolated evaluation or containment…
- Smart Contract A smart contract is a self-executing program stored on a blockchain that automatically enforces and executes the terms…
- Smart home payments Smart home payments are payments initiated by connected devices in a home environment without manual checkout. They span…
- Speech Recognition An AI capability that converts spoken language into text by analyzing audio signals, identifying phonemes and words, and…
- Stablecoins Stablecoins are cryptocurrencies designed to maintain a stable value by pegging to an external reference asset, most commonly…
- Swarm Intelligence Swarm Intelligence is a design philosophy within multi-agent systems where groups of simple agents, each following basic local…
- SWE-bench SWE-bench is the standard benchmark for evaluating large language models and autonomous coding agents on real-world software engineering…
- Synthetic Data Synthetic data is artificially generated information that mimics the statistical properties, structure, and patterns of real-world data without…
T
- Token (AI) The fundamental unit of text that a large language model processes, created by breaking text into smaller pieces…
- Tokenization
- Training data
U
V
- Virtuals Protocol Virtuals Protocol is an AI agent launchpad built on the Base blockchain that allows users to create, co-own,…
- Visa Stablecoin Settlement Platform (VSP) The Visa Stablecoin Settlement Platform (VSP) is infrastructure that allows financial institutions to store and access stablecoins, issue…
W
- What are adversarial attacks?
- What Are Zero-Knowledge Proofs? | Forkast Learn A cryptographic method where one party (the prover) demonstrates to another party (the verifier) that a statement is…
- What is a digital wallet? A digital wallet is software (or occasionally hardware) that stores the cryptographic keys needed to access, manage, and…
- What is Agent Governance? Agent governance is the system of policies, controls, technical mechanisms, and oversight structures that determine what autonomous AI…
- What Is AI Hallucination? Definition, Causes, and Mitigation
- What is an AI Agent?
- What is Delegation in AI Agents? Delegation is the process by which an AI agent assigns a task to another agent, tool, or human—transferring…
- What is Orchestration in AI?
- What is Transformer Architecture?