Coding agent
An agent that reads a codebase, edits files, runs commands and tests, and iterates until a change works.
Also: AI coding assistant, agentic coding
Coding assistants began as autocomplete: GitHub Copilot, launched in 2021 on OpenAI's Codex model, suggested the next lines as a programmer typed. Coding agents go further, taking a task such as fixing a bug, exploring the repository, making changes across files and running the tests themselves. Claude Code, OpenAI's Codex agent, Google's Jules, Cursor and many open-source tools are examples. Benchmarks such as SWE-bench measure them on real software issues. Developers still review the changes, since agents can introduce subtle errors.