Devin is an autonomous AI software engineer that can write, run and test code.

Devin can refactor code, handle small bugs and user requests before they end up in your backlog, review PRs, write unit tests, repro bugs, build your internal tools, and a lot more!

​

Already Signed Up? Get Started Now:

​

What are Devin’s strengths?

Here are the types of tasks where Devin excels:

1. Tackling many small tasks in parallel, before they end up in your backlog

   • Targeted refactors
   • Small user feature requests, frontend tasks, bug fixes, and edge cases
   • Improving test coverage
   • Investigating and fixing CI failures
   • Addressing lint/static analysis errors

2. Code migrations, refactors, and modernization

   • Language migrations (e.g. JavaScript to TypeScript)
   • Framework upgrades (e.g. Angular 16 -> 18)
   • Monorepo to submodule conversions
   • Removing unused feature flags
   • Extracting common code into libraries

3. Common, repetitive engineering tasks

   • PR Review
   • Codebase Q&A
   • Reproducing & fixing bugs
   • Writing unit tests
   • Maintaining documentation

4. Customer engineering support

   • Building new integrations and working with unfamiliar APIs
   • Creating customized demos
   • Prototyping solutions
   • Building internal tools

The most successful Devin tasks are typically:

• Quick for you to verify correctness - e.g. checking that CI passes or testing an automatic deployment
• Junior engineer level complexity. Think through (1) judgement calls (2) potential failure routes and assign Devin tasks which an intern could figure out, if provided with sufficient instructions!
• Follow our best practices and pre-task checklist

The most successful workflows include:

• Tagging Devin on a Slack thread about a bug you’re discussing with coworkers
• Delegating a more complex task via the web application and taking over in Devin’s IDE once it gives you a good first draft.
• Delegate a task in your IDE to save you from context switching
• Carving out tasks from your todo list at the start of your day and returning to draft PRs waiting for review.

Devin is most effective when it’s part of your team and your existing workflow.

​

Getting Access

To access Devin, you can sign up for a Teams account at app.devin.ai.

If your company is already working with Cognition, you can request permissions with your Administrator or Cognition directly and access Devin via the web application app.devin.ai.

​

General Product Features

​

The Devin Interface

Devin is designed to be a conversational user interface, and allows you to follow and take over Devin’s development process in the embedded IDE. Devin is also available via the Devin API.

In Devin’s Workspace, you’ll find:

​

Limitations

Devin is a junior engineer and has lots to learn. The Cognition team is working hard to improve Devin’s breadth of capabilities.

As you use Devin, keep in mind tasks that will be harder for it to execute successfully:

• Large-scale challenges: Devin generally performs better on smaller, clearly scoped tasks. For more complex edits, we recommend breaking up the project into smaller, isolated tasks that you can run in separate sessions that build on each other. If you need to frequently run multiple sessions in parallel, you can use the Devin API to create sessions and retrieve structured results programmatically.
• Reliability: Devin will sometimes get off-track. Sometimes you’ll be able to nudge Devin back on track, other times it’s better to take over from Devin in the IDE. Giving Devin clear completion criteria in the initial prompt and collaborating on the plan with Devin are both ways to improve Devin’s reliability.
• UI-related aesthetics: Devin can build functional frontends, but will need your help with aesthetics. Devin doesn’t have great eyesight.
• Mobile development: Devin can help with mobile applications, but doesn’t have a phone to test with.
• Security: This is our top priority at Cognition, but we ask all users to exercise caution when sharing credentials with Devin or granting access to specific platforms. Any time you are sharing credentials with Devin, make sure you use the Secrets Manager or via the secure credential-sharing channel provided by Devin in the chat.

​

Feedback

We’re learning and our customers’ input is crucial! You can share your feedback to support@cognition.ai, via Slack Connect (available to Teams users), or directly via the “Feedback” button on the far right edge of the web app.

We log all feedback provided by customers and use it to make quick improvements to Devin and inform our product priorities and roadmap.

​

Demo

To learn more check out our blog.

​

About Cognition

We are an applied AI lab building end-to-end software agents.

We’re building AI software engineers that help ambitious engineering teams crush their backlogs.