Devin 1.2: Updated AI engineer improves coding with smarter contextual thinking and language integration
Subscribe to our daily and weekly newsletters to receive the latest updates and exclusive content on industry-leading AI reporting. Learn more
Last year, knowledge started the AI agent wave with a product called Devin – the world first AI engineer. The offer was secret for several months, but now it is generally available and you can learn new aspects very quickly. Case in point: The Scott Wu-led startup just released Devin 1.2, which brings a slew of new features to take the AI engineer’s ability to handle entire development projects to a whole new level.
The biggest highlight of Devin 1.2 is the improved contextual thinking that improves the agent’s ability to handle and reuse code. It also includes the ability to receive voice messages via Slack, allowing users to more seamlessly tell Devin what to do.
The development comes at a time when AI-powered agents are being touted as the future of modern work. Experts predict that there will soon be a time when humans and agents will work together, with the former seamlessly completing repetitive tasks (which is already happening). Recently at CES, Nvidia boss Jensen Huang said that in the future, corporate IT departments would evolve into AI “HR departments,” responsible for commissioning and maintaining agents working in various functions within the company.
What does Devin 1.2 bring?
While it’s not a major upgrade, Devin 1.2 introduces some interesting features to improve the agent’s job. The most important feature here is the improved ability to reason in context in a code repository. This essentially means that Devin can now better understand the structure and content of a repository.
With this understanding, the agent can identify which file is relevant to a specific task, recognize and reuse existing code and patterns, and suggest more precise changes or create pull requests (PRs), reducing errors and manual adjustments.
For developers, this feature would mean accelerated workflows and reduced cognitive load from searching for files, understanding codebases, or fixing inconsistent code.
The other notable update with Devin 1.2 is the introduction of voice messaging. Devin can also take voice commands from users via Slack.
All you have to do is tag Devin in a Slack chat, click the “Record Audio Clip” button, and describe the task or feedback you want the AI engineer to complete. Devin prepares a step-by-step action and begins executing the command using his developer tools – his own shell, code editor and browser.
The move simplifies interaction with the agent and eliminates the hassle of typing natural language prompts into Devin’s chatbot-like interface.
Improved registration process, new company controls
Cognition has also made some usability improvements in Devin.
For example, in the new version, the company introduces machine snapshots to simplify the login process for Devin’s workspace.
“If you log in to Devin using Devin’s browser during onboarding, we will save the cookie for future sessions (if the cookie expires, you will also need to provide Devin login information in Secrets). This also unblocks authentication processes that require visiting a URL on Devin’s machine,” the company wrote in a statement Blog post.
Cognition is also introducing Enterprise Accounts, giving organization administrators a central console to manage multiple Devin workspaces, including members and their access controls, as well as billing.
Finally, the company is adding a usage-based billing model that allows users to pay for additional capacity beyond their subscription limits. This allows users, once they exhaust their monthly ACU quota, to continue building beyond that limit by paying for additional usage.
The model has been active since January 9th, with users able to set their additional usage budgets according to their needs. This allows users to stay in control of their spending while ensuring uninterrupted service when they need additional capacity.
Currently, Devin is generally available for technical support at a starting price of $500 per month – with no seat limits. Several companies are already integrating it into their workflows, including Lumos, OpenSea, Curai Health, Nu Bank and Ramp.
Devin’s new skills come at a time when competition in AI technology is heating up. Out of GitHub Copilots Widespread adoption of Magic and Poolside AI, raising significant funds to develop innovative capabilities, the race to create the ultimate AI coding assistant intensifies. Each player is striving to redefine software development, promising faster workflows, reduced cognitive load, and seamless collaboration between humans and AI.
As these AI-powered agents evolve, they are not only changing the way developers work, but also shaping the future of modern work itself, where efficiency and innovation are driven by a human-machine partnership.
Until 2028 Gardener It is estimated that 33% of enterprise software applications will contain agentic AI, enabling autonomous decision making in 15% of daily work.
Source link
