AI agent glossary
Coding agent
An AI agent specialized for software work: it reads code, edits files, runs commands and tests, and iterates until a programming task is done.
A coding agent pairs a strong model with tools for navigating and changing a codebase: searching files, reading them, editing them, and running shell commands. Because it can run tests and see errors, it can check and correct its own work in a loop.
Well-known coding agents include Claude Code, OpenAI Codex, Cursor, GitHub Copilot, and Gemini CLI. They differ in interface and defaults, but the core skills for using them well are the same: write tasks with a clear definition of done, give the agent project instructions, ask for a plan on bigger changes, and review what it produces.
Coding agents are also useful beyond programming. Anything that can be expressed as files and commands, like data analysis or document processing, is within reach.
Learn more in the course
Related terms
Go from definitions to doing
Learn to use and build AI agents in 65 practical lessons.