AI Agent Glossary
Plain-English definitions of AI agent terminology. Every term explains not just what it means, but how it differs from what people confuse it with.
Core Concepts (13)
Agentic AI
AI that operates autonomously over extended tasks, making decisions without step-by-step human direction.
Read definition →AI Agent
An autonomous AI system that takes actions on your behalf to accomplish a goal.
Read definition →AI Agent Memory
The mechanisms by which an AI agent retains and recalls information across sessions and tasks.
Read definition →AI Copilot
An AI assistant embedded in a product that helps users complete tasks within that product's context.
Read definition →AI Guardrails
Constraints and safety mechanisms that limit what an AI agent can do to prevent unintended actions.
Read definition →AI Hallucination
When an AI model generates factually incorrect information with apparent confidence.
Read definition →AI Orchestration
The coordination and management of multiple AI agents or LLM calls within a system.
Read definition →AI Workflow
A predetermined sequence of steps with AI embedded at specific points — as opposed to an autonomous agent.
Read definition →Autonomous Agent
An AI agent that operates without human intervention to complete multi-step tasks.
Read definition →Generative AI
AI systems that generate new content — text, images, code, audio — rather than only classifying or analyzing input.
Read definition →Human-in-the-Loop (HITL)
An AI system design pattern where humans review or approve key agent decisions before they're executed.
Read definition →LLM (Large Language Model)
A deep learning model trained on large text corpora that can generate, understand, and reason with language.
Read definition →Multi-Agent System
An architecture where multiple specialized AI agents collaborate to complete complex tasks.
Read definition →Technical (22)
Agentic RAG
A RAG system where an AI agent controls the retrieval strategy adaptively, rather than following a fixed pipeline.
Read definition →Chain-of-Thought (CoT)
A prompting technique that asks an AI model to reason step-by-step before producing a final answer.
Read definition →Composio
An integration platform that provides 900+ OAuth-managed tool connections for AI agents.
Read definition →Context Window
The maximum amount of text an LLM can process in a single interaction.
Read definition →Embeddings
Numerical vector representations of text that encode semantic meaning.
Read definition →Few-Shot Prompting
Including a small number of input-output examples in a prompt to guide an AI model's behavior.
Read definition →Fine-Tuning
Additional training of a pre-trained LLM on domain-specific data to specialize its behavior.
Read definition →Function Calling
A model capability that allows LLMs to request calls to predefined functions with structured arguments.
Read definition →Inference
The process of running a trained AI model to generate output from a given input.
Read definition →LangChain
An open-source framework for building LLM-powered applications and AI agents in Python and JavaScript.
Read definition →MCP (Model Context Protocol)
Anthropic's open standard for connecting AI models to external tools and data sources.
Read definition →MCP Server
A process that exposes tools, resources, and prompts to MCP-compatible AI clients.
Read definition →OAuth
An open authorization standard that lets apps access user data from other services without sharing passwords.
Read definition →Prompt Engineering
The practice of designing inputs to AI models to reliably produce desired outputs.
Read definition →RAG (Retrieval-Augmented Generation)
A technique that grounds AI responses in retrieved documents rather than relying solely on training data.
Read definition →Semantic Search
Search that finds results by meaning rather than exact keyword matching.
Read definition →System Prompt
Instructions provided to an LLM before the conversation begins, setting its role, behavior, and constraints.
Read definition →Tool Call
A specific invocation of an external tool by an AI agent during task execution.
Read definition →Tool Use
An AI model's ability to call external functions, APIs, or services during reasoning.
Read definition →Vector Database
A database optimized for storing and searching high-dimensional vector embeddings.
Read definition →Webhook
A mechanism for one system to notify another system in real time when an event occurs.
Read definition →Zero-Shot Prompting
Asking an AI model to complete a task with no examples of the desired output.
Read definition →Business & Use Cases (3)
AI SDR
An AI agent that handles outbound sales development tasks — research, outreach, and follow-up — autonomously.
Read definition →AIOps
The use of AI and machine learning to automate and enhance IT operations, monitoring, and incident management.
Read definition →Knowledge Base (AI)
A collection of documents indexed for retrieval by an AI agent to answer questions accurately.
Read definition →Ready to put these concepts to work?
Shogo lets you deploy AI agents without knowing all the jargon. Describe what you want in plain English — the agent handles the rest.
Build Your First Agent Free →