| Devin AI | |
|---|---|
| Developer | Cognition Labs |
| License | Proprietary (SaaS), using open source software (Ubuntu for the sandboxes) in part Enterprise tiers only: Proprietary (SaaS or binary-only VPC image) using open source software (Ubuntu for the sandboxes). |
| Website |
|
Devin AI is an autonomousartificial intelligence assistant tool created byCognition Labs. Branded as an "AIsoftware developer",[1] the demo tool is designed to completesoftware development tasks. The tool has received praise, concern, and skepticism over implications surrounding thefuture of artificial intelligence and software development.
Devin AI was created by Cognition Labs, a startup company consisting of ten members including CEOScott Wu and chief technology officer Steven Hao, with funding fromPeter Thiel'sFounders Fund firm.[2][3] Several of the members had participated incompetitive coding contests before forming the company.[3] The members developed the software via a combination of traininglarge language models akin toOpenAI'sGPT-4 with aspects fromreinforcement learning.[3] According to aBloomberg article, Cognition Labs claimed that Devin AI represents a "breakthrough in acomputer's ability to reason."[3] Devin AI has also been considered part of a trend surrounding the advent of autonomousAI agents that cantake direct action to solve problems.[1]
Devin AI has been noted for its ability to perform software engineering tasks autonomously.[4][5] Compared to theGitHub Copilot tool,[3][4] the software can code, debug, plan and problem solve via machine learning techniques.[5] Devin AI works through a user prompting the software with a task innatural language, with the software responding by showing its plan while implementing the code.[3] It searches online resources during the process to learn to complete a task.[4] The software also takes prompts from users during the implementation process and adjusts its plans accordingly, such as when a user notices an issue or bug.[3][6]
One application of Devin AI is website creation. A test conducted byBloomberg revealed that the tool could create a website within ten minutes and could recreate aPong website in a similar timeframe.[3] In a demo from Cognition Labs, the tool also created a website based on theLlama 2 language model through plan, source code and benchmark testing generation.[1] Other examples include building a project to display images from a blog post, and compiling acomputer vision model from anUpwork project.[6] In a benchmark test for analyzing the performance of large language models on real world projects, Devin was found to fix 13.86 percent of encountered issues with no human assistance, compared to an average of 1.96 percent and 4.8 percent for an unassisted and assisted model, respectively.[5][6]
Later revisions of Devin got multi-agent operation capability, where one of the AI agents dispatch task to other AI agents.[7] Even later versions got self-assessed confidence evaluation, asking for clarification when it is not confident enough to perform the task as assigned.[8]
In early 2025, Devin got a machine generated software documentation feature called Devin Wiki, along with an interactive search&answer engine to query on the code, called Devin Search.[9] A later release opened up these two features to non-subscribers, and this non-subscription version is called DeepWiki.[10][11]
Devin AI has been met with praise, concern and skepticism from journalists and software engineers.[1][12][13] Its announcement onX led to praise from investors and software engineers while spawning various memes.[1] Along with the company, the tool has seen optimism amongst AI enthusiasts and anticipation for its public availability.[3] The tool has also been noted for potentially allowing users of a non-technical background to create projects, and aiding developers in solving more complex tasks.[4]The Indian Express claimed that its capabilities could streamline the software development process while avoiding human error.[5] CEOAravind Srinivas ofPerplexity.ai offered praise to Devin, claiming that it "seemed to be 'the first demo of any agent, leave alone coding, that seems to cross the threshold' of human capability."[12] After the release of Devin AI, Cognition Labs experienced increasing growth and interest. Earlier this year, the startup raised $21 million in a deal valuing it at $350 million. It then turned down offers valuing it at $1 billion. According to theWall Street Journal, the company has been in talks with investors for a deal that would value it at up to $2 billion.[14]
Concern for the software includes its implications for the future of AI and the software development industry.[3][12] In the wake of layoffs within the tech industry throughout 2023 and 2024,[12] discourse of the tool involves concerns that it may replace engineers and remove lower-level jobs.[4] On social media, various developers expressed criticism for the software's capabilities and potential to incite job layoffs.[1][12][13] Skepticism also emerged that the tool may struggle to complete tasks with more intricate requirements and scenarios that would necessitate human creativity, along with its efficiency.[5][12] Further skepticism regarding its accuracy has emerged following the tool's promotional videos, such as its performance of Devin AI's execution of the Upwork project; YouTube channels such asInternet of Bugs andComputer Vision Project criticized the tool for failing to deliver on the project request, instead writing, testing, and debugging code irrelevant to the Upwork request.[15] However, the tool has also been regarded to encourage software engineers to perform more creative work.[3][5] Following Devin's debut, various AI software engineering models have been released, such asfree and open source replacements like OpenDevin (now called OpenHands)[16] and Devika,[17] and Genie by San Francisco-based startup Cosine.[18]
When Devin doesn't have 🟢 confidence (i.e., 🟡 or 🔴), it will now wait for user approval before proceeding with its plan. If it's 🟢, it proceeds automatically.
