Devin
In plain wordsA 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.
An autonomous 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. product from the startup Cognition that works on software tasks inside an isolated cloud machine equipped with a browser, an editor and a terminal, planning and executing multi-step work, reporting progress through a chat interface and delivering changes as pull requests. Its launch announcement, which billed it as 'the first AI software engineer', reported resolving 13.86% of a random 25% subset of 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. issues unassisted, against 1.96% for the previous best system, and helped make autonomous coding agents a mainstream idea. Critics argued that some demonstrations overstated its abilities, and Devin became a reference point in debates about AI replacing programmers.
We trialed Devin on dependency upgrades, where its pull requests needed only light review.
Origin
Announced by Cognition, led by chief executive Scott Wu, on 12 March 2024; it became generally available to paying teams in December 2024.
Usage note
A product name, not a generic term, though it is sometimes used as shorthand for fully autonomous coding agents.
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.
- 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-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.
- 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 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.
Sources
- Wu, S. / Cognition (2024). Introducing Devin, the first AI software engineer. 12 March 2024. cognition.com/blog/introducing-devin
Mentioned in
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., 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.