Loading…
Glossary term
An AI agent that writes, edits and tests software.
A coding agent reads a codebase, plans changes, edits files, runs tests and iterates on the results. It works in a terminal or editor, often inside a sandbox.
Its output is judged by whether tests pass and whether a human accepts the change.
Coding agents are among the most widely adopted agents and are measured by benchmarks like SWE-bench.