Blog

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. On Stack Overflow's 2025 survey only 14% of developers used agents daily.

Source: AI's impact on software development — Anthropic Economic Index

See the numbers behind this term: AI Agent Statistics 2026 · AI Coding Tools Statistics 2026.