GitHub Copilot
In plain wordsAn 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.
An AI coding assistant from GitHub, a Microsoft subsidiary, available in code editors and development environments (among them JetBrains IDEs, Xcode and Microsoft's own Visual Studio and Visual Studio Code), on GitHub's website and at the command line. It began as inline code completion: 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., a large language modellarge 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 on code, predicted the next lines or whole functions from the surrounding file and comments, shown as grey 'ghost text' that the developer accepts with a keystroke. Later versions added chat about code, multi-file editing, an agent mode that runs commands and iterates on errors, automated code review, and a 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. that works on assigned issues in a cloud environment and opens pull requests; users can choose among models from several providers. Copilot made AI pair programming mainstream and became the reference point in debates over productivity, code quality, security flaws in suggested code and the use of public code for training.
GitHub Copilot wrote most of the test boilerplate; I only fixed the edge cases.
Origin
Announced by GitHub as a technical preview on 29 June 2021, built with OpenAI on its Codex model and marketed as 'your AI pair programmer'; it became generally available to individual developers in June 2022. Chat followed in 2023, a choice of models from several providers in 2024, and agent mode and an autonomous coding agent in 2025.
Usage note
Productivity evidence is mixed: in a 2023 experiment developers finished a set task about 55 percent faster with Copilot, but a 2025 randomized trial by METRMETR, prop. n.: A nonprofit research group that checks new AI systems for dangerous skills, best known for tracking how long the tasks are that AI agents can now finish on their own. found experienced open-source developers slower with AI tools. Most claims in a 2022 class action over training on public code were dismissed; in September 2026 the Ninth Circuit upheld dismissal of its DMCA claim, leaving contract claims pending. Distinct from Microsoft's general-purpose Copilot assistant.
Related
- 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.
- 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.
- 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.
- 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.
Sources
- Chen, M. et al. (2021). Evaluating Large Language Models Trained on Code. arXiv:2107.03374.
- Peng, S., Kalliamvakou, E., Cihon, P. & Demirer, M. (2023). The Impact of AI on Developer Productivity: Evidence from GitHub Copilot. arXiv:2302.06590. arxiv.org/abs/2302.06590
- Doe v. GitHub, Inc., No. 24-7700 (9th Cir. 16 September 2026).
Mentioned in
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., 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., 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., completioncompletion, n.: The text an AI language model writes in response to a prompt — literally, its continuation of the text it was given., 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., 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., fill-in-the-middlefill-in-the-middle, n.: A training trick that teaches a text-writing AI to fill a gap using what comes both before and after it — essential for coding assistants that insert code in the middle of a file.