Glossary
Plain-English definitions of the terms behind AI coding agents and modern terminal workflows.
Agentic Coding
A workflow where an autonomous AI agent plans and executes multi-step coding tasks, not just single completions.
AI Coding Agent
An AI program that autonomously reads, writes, and runs code to complete development tasks.
Context Window
The maximum amount of text (tokens) a model can consider at once.
MCP Server
A program that exposes tools and data to AI agents over the Model Context Protocol.
Model Context Protocol (MCP)
An open standard that lets AI agents connect to tools, data sources, and actions through a common interface.
Multi-Agent Orchestration
Coordinating several AI agents toward one goal by splitting it into tasks across parallel sessions.
Persistent Terminal Session
A terminal session that survives disconnects and restarts, preserving running processes and state.
Prompt Engineering
Structuring instructions and context so an AI model produces reliable, useful output.
SSH Port Forwarding
Tunneling network traffic over an SSH connection to securely reach remote services.
Terminal Multiplexer
A tool like tmux or Zellij that runs multiple persistent terminal sessions inside one window.
Try Agents UI
A native terminal for AI coding agents with persistent sessions, SSH workflows, and built-in editing.