@dabit3: Automated UI testing feels like AGI in Devin 10 examples (running macOS + Linux Cloud Agents) What happens (automatic f…
Summary
Devin's automated UI testing feature autonomously creates test plans, runs tests on macOS and Linux environments, and generates video artifacts, making testing feel like AGI.
View Cached Full Text
Cached at: 09/10/26, 08:59 AM
Automated UI testing feels like AGI in Devin
10 examples (running macOS + Linux Cloud Agents) 🧵
What happens (automatic for any update): • Creates programmatic test plan • Boots the app with secrets & credentials (auth, etc.) • Autonomously clicks, types, and checks the UI like a human using a computer would • Records a test • Edits the video, attaches step by step walkthrough of the actions it took • Sends you a concise video artifact
As we move away from reading every line of code, new advanced ways of testing become more valuable.
-
Testing a platform for signing documents electronically
-
E-commerce automated UI testing and in-browser bug reporting (end to end)
-
Testing a 2-player native iOS and Android game playing side by side simultaneously (macOS environment)
-
Testing a native macOS screen recording app with most features
-
End to end testing of a flow-chart app
-
Testing a native macOS, native iOS, and web-based multi-player chess game simultaneously
-
Running terminal apps and walking through the commands and file system
-
Building a native SwiftUI app, code-sign it, notarize with Apple via notarytool, staple the ticket, and package a signed DMG with drag-to-Applications window.
-
Testing slideshow app by creating, editing, and playing an entire slide deck
-
Testing and playing a native iOS game on real macOS hardware
Learn more about @devinai computer use here:
hey @dabit3 you never really finished giving out the 50 devin max accounts
Similar Articles
@dabit3: Underrated feature of advanced cloud agents like @devinai: Infinitely parallelizable human-grade UI testing. They - Sta…
This tweet highlights that advanced cloud agents like Devinai can perform infinitely parallelizable human-grade UI testing by setting up environments, inspecting code, planning e2e tests, handling authentication, using computer vision and mouse-and-keyboard control, and returning annotated video proof, with reusable skills for faster future verification.
@dabit3: New experiment: can my cloud agent build and test multiplayer iOS games? Devin connects to a Mac in the cloud, boots an…
Devin, a cloud AI agent, automates building and testing multiplayer iOS games by booting Xcode, launching iPhone simulators, and verifying with computer vision and programmatic signals.
@dabit3: https://x.com/dabit3/status/2104576471515779520
Using the Devin AI agent to automate the creation of pixel-perfect product tutorials at scale, achieving results superior to human-made tutorials with improved consistency and parallel processing capabilities.
@dabit3: Devin is not just a coding agent. It is an AI Engineering platform for the full SDLC: → plan → build → test → ship → mo…
Devin is positioned as an AI Engineering platform covering the entire software development lifecycle, from planning to documentation, with integrations and features that enhance developer experience.
@dabit3: Steer Cloud Agents from the CLI (not just on Web). ssh directly into it. PRs tested in a real VM, real browser / device…
Cognition introduces new CLI and SSH access for Devin Cloud, enabling developers to manage AI coding sessions directly from the terminal and interact with a dedicated VM.