Build apps, debug repos and set up CI/CD with Devin
A review lists Devin building a full-stack to-do app, debugging a public repo with a PR, and doing Docker setup, deployment and CI/CD.
Done withDevin
- What they did
- The reviewer did not run Devin. They relied on Cognition's demo videos and early-access user reports. In those, Devin works in a Linux shell with a browser and GitHub. It built a React and Express to-do app, debugged a public repo and submitted a pull request, and set up Docker, deployment and CI/CD pipelines.
- How it went
- The review calls Devin strong on boilerplate and clearly specced features. It is weaker on legacy refactoring, complex logic and vague instructions. One beta tester said Devin did 90% of a Node.js backend setup, leaving cleanup.
- Worth knowing
- These results come from demos and second-hand reports, not hands-on testing. At publication Devin was closed beta with no pricing, and the review says its code still needs checking.
Try it yourself with Devin
In my repo [repo link], set up Docker so the app builds and runs locally, then add a CI/CD pipeline using [GitHub Actions or other CI] that runs tests and deploys to [hosting target]. You're done when the pipeline passes on a test branch and I can follow your README steps to run it. Pause and show me the deployment config before anything is deployed to production.
Source: fritz.ai · Undated
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
Hand narrow code changes to Devin for pull requests
A team used Devin for a month on small fixes like chart formatting and API edge cases, with tests and PRs; a complex full-stack task went poorly.
Try Devin on research tasks (mostly failed)
Answer.AI had Devin fetch an author's recent papers and research transcript summarization; it got stuck parsing HTML and returned generic results, rated a failure.
Build a Pong game and website from scratch
A tester asked Devin to create a basic Pong-style game and a website, and it finished both in under 20 minutes.
- Claude
Build a C compiler with a team of parallel agents
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
- Custom agent
Audit a codebase for redundant dependencies and polyfills
An MCP server lets an agent check a codebase for redundant dependencies and polyfills, usable remotely or as a local stdio server.
Build a budgeting app from a single prompt
A low-coder used Replit Agent to build a 'Budget Buddy' with category budgets, a spending dashboard and expense log in about 20 minutes, using half their monthly credits.