ModelRefs / Coding Agent — AI Glossary
Coding Agent — AI Glossary
An AI agent that writes, executes, debugs, and iterates on code using a code interpreter tool and version-control integration.
Overview
Coding agents (Devin, Claude Code, GitHub Copilot Workspace) operate in a code execution environment with shell access, file system tools, and browser for documentation lookup. They follow a plan-code-test-fix loop. Evaluate on SWE-Bench (real GitHub issues). Performance: frontier models resolve 40–60% of SWE-Bench verified issues.
Reference details
| Topic | agents |
|---|---|
| Also known as | software agent, software engineering agent |
| Last reviewed | 2026-06-24 |
Related terms
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Coding Agent — AI Glossary.
Frequently asked questions
What is Coding Agent?
An AI agent that writes, executes, debugs, and iterates on code using a code interpreter tool and version-control integration.
Is Coding Agent the same as software agent?
Yes — software agent, software engineering agent are common aliases for Coding Agent.
What concepts are related to Coding Agent?
Closely related concepts include code generation, tool agent, swe bench.