AI Agent Glossary · AI Coding Tools Glossary
Coding agent
An LLM system that plans, edits files, runs commands and tests in a loop until a software task is done, with little or no human input per step.
A coding agent takes a task description — a GitHub issue, a bug report, a feature request — and works through it autonomously: reads the repository, decides which files to change, edits them, runs the build and tests, reads the errors and iterates. Examples are Claude Code, OpenAI Codex, GitHub Copilot coding agent, Cursor's agent mode, Devin and open-source SWE-agent. In Anthropic's analysis of 500,000 coding conversations, 79% of Claude Code sessions were automation (the agent does the work) versus 49% for chat-based coding. By September 2026 more than 40% of pull requests on GitHub started with an agent's first draft, up from 17% in March (Octoverse 2026).