AI coding assistant
In plain wordsAI 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.
A software tool that uses language modelslarge language model, n.: A computer program trained on enormous amounts of text to predict the words that come next. At vast scale, that simple skill lets it chat, answer questions, translate, summarize and write code. trained or adapted for code to help developers write, understand, test and change software. Capabilities range along a spectrum of autonomy: inline completion that predicts the next tokens, lines or edits as the developer types; chat that answers questions about a codebase and drafts snippets; commands that apply edits across files; automated code review and test generation; and agent modes in which the assistant plans a task, runs commands and tests, and iterates until done, shading into fully autonomous coding agentscoding agent, n.: An 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.. Assistants gather context from open files, an index of the repository, documentation and instruction filesagent 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., and run in editors, terminals and code-hosting platforms. Prominent examples include 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., 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. and 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., alongside assistants from other model providers and open-source tools. Debates concern productivity, code quality and security, the licensing of training code, and effects on learning and employment.
Our policy allows an AI coding assistant, but every generated change still needs human review.
Origin
Rule-based code completion goes back to integrated development environment features such as Microsoft's IntelliSense (late 1990s), and completers such as Kite and TabNine used early neural models in the late 2010s. GitHub Copilot (2021), built on 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., made language-model assistants mainstream, and agentic assistants spread in 2024–2025.
Usage note
Overlaps with coding agentcoding agent, n.: An 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 assistant usually works interactively with the developer, while an agent carries out whole tasks with less supervision. See also 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
- 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.
- 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.
- coding agentcoding agent, n.: An 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.
- 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.
- 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.
- 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.