coding agent
In plain wordsAn AI agent that writes and fixes software by itself: it reads a codebase, edits files, runs commands and tests, and keeps working until a feature is built or a bug is fixed.
An AI agentAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done. specialized for software engineering that operates on a code repository with tools to read and search files, edit them, run shell commands, builds and tests, and use version control, iterating until a task — implementing a feature, fixing a bug, writing tests, migrating code — passes its checks. Coding agents run in several settings: in the terminal or editor beside a developer (interactive), in cloud sandboxessandbox, n.: A sealed-off computer space where an AI agent can run programs and change files without being able to harm the real system, reach private data or contact the outside world unless allowed. that return pull requests (background agentsbackground agent, n.: An AI agent you hand a task to and then leave alone: it works by itself in the cloud, often for many minutes or hours, and reports back with finished work for you to review.), or in automated pipelines triggered by issues or failing builds. They differ from earlier code-completion assistants in acting over many steps with code executioncode execution, n.: Letting an AI write a small program and actually run it — to do math, analyze a spreadsheet or test its own code — then use the real output instead of guessing. feedback, which lets them test and correct their own work. Their abilities are measured on benchmarks such as SWE-benchSWE-bench, prop. n.: A test that asks AI to fix real bugs and add features in real open-source Python projects, checked by running each project's own tests; the best-known yardstick for AI coding agents. and Terminal-BenchTerminal-Bench, prop. n.: A test of AI agents working in a computer's command line — building software, analyzing data, securing or repairing systems — with each task checked automatically inside a sealed-off container. and by time-horizonMETR time horizon, n.: A way of measuring AI progress by asking how long a task — timed by how long it takes a skilled human — an AI agent can complete with even odds of success. studies; open problems include review burden, subtle bugs, the security of executed commands and keeping agents within project conventions (see agent instruction fileagent instruction file, n.: A plain-text file kept in a software project that tells AI coding agents how the project works — how to build and test it, which conventions to follow, what to avoid — read at the start of every session.).
I gave the coding agent the failing test and took a coffee break; it came back with a fix and two new tests.
Origin
Cognition's DevinDevin, prop. n.: A commercial AI 'software engineer' from the startup Cognition, unveiled in 2024, that takes on programming tasks in its own cloud workspace, complete with a web browser, a code editor and a command line. (March 2024) and the research system SWE-agentSWE-agent, prop. n.: An open-source research system from Princeton that turns a language model into a software-fixing agent by giving it a specially designed set of commands for browsing, editing and testing code. (May 2024) defined the category. In 2025 terminal-based agents — Anthropic's Claude CodeClaude Code, prop. n.: A coding assistant from Anthropic that works as an agent: given a programming task, it explores the project, changes the code and runs programs to check its work, from the web, a desktop app, an editor or a terminal. (February), OpenAI's CodexCodex, prop. n.: A name OpenAI has used twice: first for a 2021 AI model that wrote code and powered the original GitHub Copilot, then from 2025 for its family of coding agents. CLI (April) and Google's Gemini CLI (June) — and cloud agents from OpenAI, GitHub and Google made coding agents among the most widely used kinds of AI agent.
Usage note
Usage varies: 'coding assistant' often means autocomplete or chat help, while 'coding agent' implies autonomous multi-step action. Working through such agents is agentic codingagentic coding, n.: Writing software by directing AI agents that plan, edit and test code themselves, with the human acting more as a reviewer and manager than as the person typing every line.; the casual, review-light style is vibe codingvibe coding, n.: Programming by conversation: you ask an AI for what you want, try out what it produces and ask again until it works, trusting the code without really reading it..
Related
- agentic codingagentic coding, n.: Writing software by directing AI agents that plan, edit and test code themselves, with the human acting more as a reviewer and manager than as the person typing every line.
- background agentbackground agent, n.: An AI agent you hand a task to and then leave alone: it works by itself in the cloud, often for many minutes or hours, and reports back with finished work for you to review.
- SWE-agentSWE-agent, prop. n.: An open-source research system from Princeton that turns a language model into a software-fixing agent by giving it a specially designed set of commands for browsing, editing and testing code.
- SWE-benchSWE-bench, prop. n.: A test that asks AI to fix real bugs and add features in real open-source Python projects, checked by running each project's own tests; the best-known yardstick for AI coding agents.
- Claude CodeClaude Code, prop. n.: A coding assistant from Anthropic that works as an agent: given a programming task, it explores the project, changes the code and runs programs to check its work, from the web, a desktop app, an editor or a terminal.
- CodexCodex, prop. n.: A name OpenAI has used twice: first for a 2021 AI model that wrote code and powered the original GitHub Copilot, then from 2025 for its family of coding agents.
- vibe codingvibe coding, n.: Programming by conversation: you ask an AI for what you want, try out what it produces and ask again until it works, trusting the code without really reading it.
- code generationcode generation, n.: Having an AI write computer code from a description in plain language, from finishing a single line as you type to building whole programs.
- copilotcopilot, n.: An AI assistant built into software that works alongside a person — suggesting code, drafting text or answering questions — while the person stays in charge, like a co-pilot beside the captain.
Sources
- Yang, J. et al. (2024). SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering. NeurIPS 2024. arxiv.org/abs/2405.15793
- Cognition (2024). Introducing Devin, the first AI software engineer. 12 March 2024. cognition.com/blog/introducing-devin
Mentioned in
AI agentAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done., GitHub CopilotGitHub Copilot, prop. n.: An AI assistant from GitHub, built into programmers' code editors, that suggests code as they type, answers questions about code and can carry out coding tasks on its own., Model Context ProtocolModel Context Protocol, prop. n.: An open standard that lets AI assistants plug into outside apps and data — files, calendars, databases, business software — through one common connector instead of a custom link for every pairing; often likened to a USB-C port for AI., SWE-benchSWE-bench, prop. n.: A test that asks AI to fix real bugs and add features in real open-source Python projects, checked by running each project's own tests; the best-known yardstick for AI coding agents., vibe codingvibe coding, n.: Programming by conversation: you ask an AI for what you want, try out what it produces and ask again until it works, trusting the code without really reading it., agent instruction fileagent instruction file, n.: A plain-text file kept in a software project that tells AI coding agents how the project works — how to build and test it, which conventions to follow, what to avoid — read at the start of every session., agentic codingagentic coding, n.: Writing software by directing AI agents that plan, edit and test code themselves, with the human acting more as a reviewer and manager than as the person typing every line., AI coding assistantAI coding assistant, n.: AI software that helps people write computer programs — suggesting the next lines, explaining code, finding bugs or making changes on request — inside the tools programmers already use., AI-enabled cyberattackAI-enabled cyberattack, n.: A computer attack in which criminals or spies use AI to help — writing convincing scam messages, finding weak spots, producing malicious code, or even running much of the hacking by itself., AutoMLAutoML, n.: Software that automates the trial-and-error parts of building a machine-learning model, such as choosing the algorithm, its settings and the data-preparation steps, so less expert effort is needed., background agentbackground agent, n.: An AI agent you hand a task to and then leave alone: it works by itself in the cloud, often for many minutes or hours, and reports back with finished work for you to review., Claude CodeClaude Code, prop. n.: A coding assistant from Anthropic that works as an agent: given a programming task, it explores the project, changes the code and runs programs to check its work, from the web, a desktop app, an editor or a terminal., code executioncode execution, n.: Letting an AI write a small program and actually run it — to do math, analyze a spreadsheet or test its own code — then use the real output instead of guessing., code generationcode generation, n.: Having an AI write computer code from a description in plain language, from finishing a single line as you type to building whole programs., CodexCodex, prop. n.: A name OpenAI has used twice: first for a 2021 AI model that wrote code and powered the original GitHub Copilot, then from 2025 for its family of coding agents., compactioncompaction, n.: Like replacing a stack of rough notes with a one-page digest: when an AI's conversation grows too long for its memory, the history is condensed into a summary and the work continues from there., HumanEvalHumanEval, prop. n.: A set of 164 small programming exercises, each described in plain English and checked by hidden tests, used to see whether an AI can write working Python code., one-shotone-shot, v.: Slang for an AI completing a whole task correctly on the first try from a single request — 'it one-shotted the app' — with no corrections or follow-up needed., Terminal-BenchTerminal-Bench, prop. n.: A test of AI agents working in a computer's command line — building software, analyzing data, securing or repairing systems — with each task checked automatically inside a sealed-off container., agent–computer interfaceagent–computer interface, n.: The commands, tools and feedback designed for an AI agent to work with a computer — the agent's version of a user interface, shaped around how language models read and act., agentic reinforcement learningagentic reinforcement learning, n.: Training an AI assistant by rewarding success on long, multi-step jobs where it must use tools, browse, run code and react to what happens, rather than answer in one go., AI-assisted vulnerability discoveryAI-assisted vulnerability discovery, n.: Using AI to find security holes in software — and often to suggest fixes — faster than human experts alone, so that defenders, or attackers, can act on them., ChatGPT pluginsChatGPT plugins, prop. n.: Add-ons, launched in 2023 and retired in 2024, that let ChatGPT use outside services — web browsing, a code runner, travel booking or shopping sites — while answering a user., CursorCursor, prop. n.: A code editor built around AI, in which programmers can ask a model to write, change or explain code across a whole project, or hand it tasks to finish on its own.