Home / Glossary
AI Coding Glossary
Key terms in AI-assisted development, explained clearly with practical context.
Agentic Coding
Agentic coding is a software development approach where an AI agent autonomously reads your codebase, writes code, runs commands, and iterates on results without manual copy-paste. Unlike chat-based AI, the agent takes direct action in your development environment to complete multi-step tasks.
Claude Code
Claude Code is Anthropic's terminal-based AI coding agent that operates directly in your development environment. It reads your entire project, writes code across multiple files, runs shell commands, manages git workflows, and iterates on errors autonomously—all from the command line.
Model Context Protocol (MCP)
The Model Context Protocol (MCP) is an open standard created by Anthropic that provides a universal way to connect AI models to external tools, data sources, and APIs. It acts as a standardized interface—like USB for AI—so any MCP-compatible tool can work with any MCP-compatible AI agent.
CLAUDE.md
CLAUDE.md is a markdown configuration file placed in your project root that provides Claude Code with persistent, project-specific instructions. It tells the agent about your coding conventions, architecture, common commands, and rules—acting as a form of long-term memory that applies to every session in that project.
AI Pair Programming
AI pair programming is a development workflow where a human developer works alongside an AI tool to write code collaboratively in real-time. The developer provides direction, context, and judgment while the AI contributes code suggestions, catches bugs, and handles repetitive implementation tasks.
Context Window
A context window is the maximum number of tokens (words, code characters, and symbols) that an AI model can process in a single interaction. It defines the upper limit of how much information—including your prompt, code, and the model's response—the AI can hold in memory at once.
Coding Agent
A coding agent is an AI-powered tool that can autonomously read files, write code, execute terminal commands, and iterate on results to complete programming tasks. Unlike passive code suggestion tools, a coding agent takes independent action in your development environment to achieve a stated goal.
Vibe Coding
Vibe coding is an informal approach to software development where a developer describes what they want in natural language and lets an AI tool handle the implementation details. Instead of writing precise specifications, the developer communicates intent through casual conversation and iterates based on results.
AI Code Review
AI code review is the process of using artificial intelligence to automatically analyze source code for bugs, security vulnerabilities, style inconsistencies, and quality issues. AI reviewers can examine pull requests, suggest improvements, and catch problems that human reviewers might miss due to fatigue or time pressure.
Prompt Engineering for Code
Prompt engineering for code is the practice of crafting clear, specific instructions that help AI coding tools produce accurate, relevant output. It involves structuring your requests with the right level of context, constraints, and examples so the AI understands both what you want and how you want it done.
Headless AI Agent
A headless AI agent is a coding agent that runs without a human-facing interface or real-time interaction. It executes tasks autonomously in background processes, CI/CD pipelines, or scheduled jobs—reading code, making changes, running tests, and reporting results without waiting for human input at any step.
Sub-Agents
Sub-agents are parallel child processes spawned by a main AI coding agent to handle independent parts of a complex task simultaneously. Instead of processing everything sequentially, the main agent delegates sub-tasks to specialized child agents that run in parallel and report results back to the parent.