Loading video...

Video Failed to Load

Go Home

Underrated feature of advanced cloud agents like Devin: Infinitely parallelizable human-grade UI testing. They - Stand up a live environment with secrets - Inspect code changes - Plan a comprehensive end-to-end test - Handle real authentication + identity - Use computer vision + mouse-and-keyboard control to test the app...

dabit3's profile picture

nader dabit

190,252 subscribers

104,717 views • 3 months ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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. 1. Testing a platform for signing documents electronically
0:42

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. 1. Testing a platform for signing documents electronically

nader dabit

1,603,475 views • 1 month ago

Introducing Computer Use in TREX. TREX now spins up the relevant services for your changes and uses computer use to test them end to end. It can test desktop apps, click through a web app in a browser to simulate user flows, or use a terminal to test your CLI.
1:15

Introducing Computer Use in TREX. TREX now spins up the relevant services for your changes and uses computer use to test them end to end. It can test desktop apps, click through a web app in a browser to simulate user flows, or use a terminal to test your CLI.

Greptile

15,567 views • 4 days ago

Devin Cloud Agents can now build and ship a real macOS release end-to-end, all in a real Mac environment (with full computer use). In this demo, the agent builds a native SwiftUI app, code-signs it, notarizes with Apple via notarytool, staples the ticket, and packages a signed DMG with the classic drag-to-Applications window. With computer use, it installs its own app like a real user: mount, drag, eject, launch with zero Gatekeeper warnings. It even verified notifications fired by checking the macOS notification database on screen, with a full recording and release report delivered for review. This entire workflow now takes about 60 seconds to spin up and tear down with Devin and Namespace. You can choose multiple versions of macOS of Xcode for your environment!
0:47

Devin Cloud Agents can now build and ship a real macOS release end-to-end, all in a real Mac environment (with full computer use). In this demo, the agent builds a native SwiftUI app, code-signs it, notarizes with Apple via notarytool, staples the ticket, and packages a signed DMG with the classic drag-to-Applications window. With computer use, it installs its own app like a real user: mount, drag, eject, launch with zero Gatekeeper warnings. It even verified notifications fired by checking the macOS notification database on screen, with a full recording and release report delivered for review. This entire workflow now takes about 60 seconds to spin up and tear down with Devin and Namespace. You can choose multiple versions of macOS of Xcode for your environment!

nader dabit

147,071 views • 2 months ago

Today, we launched browser use inside Codex to further close the build & verify loop for local development! Now, you can ask Codex to build your front end, and test it like a user would by clicking through the app. Codex sees everything a user sees through vision & checks the network/console logs to help debug & fix any issues that it finds. This change brings us closer to fully autonomous coding agents that delivers high quality and tested changes. Watch Codex test my app in the browser, catch & fix a real bug, and doing that loop again with a brand new feature.
0:37

Today, we launched browser use inside Codex to further close the build & verify loop for local development! Now, you can ask Codex to build your front end, and test it like a user would by clicking through the app. Codex sees everything a user sees through vision & checks the network/console logs to help debug & fix any issues that it finds. This change brings us closer to fully autonomous coding agents that delivers high quality and tested changes. Watch Codex test my app in the browser, catch & fix a real bug, and doing that loop again with a brand new feature.

James Sun

227,571 views • 6 months ago

Introducing Devin 2.2 – the autonomous agent that can test with computer use, self-verify, and auto-fix its work. Try it for free! We’ve also overhauled Devin from the ground up: - 3x faster startup - fully redesigned interface - computer use + virtual desktop ...and hundreds more UX and functionality improvements.
0:30

Introducing Devin 2.2 – the autonomous agent that can test with computer use, self-verify, and auto-fix its work. Try it for free! We’ve also overhauled Devin from the ground up: - 3x faster startup - fully redesigned interface - computer use + virtual desktop ...and hundreds more UX and functionality improvements.

Cognition

541,944 views • 8 months ago

Codex can now use the in-app browser to test your app at different viewport sizes! It will control the device tool bar and click through your app at different breakpoints to validate & iterate. If it's a long run, Codex will take screenshots at key moments during testing and show them to you at the end of the turn, so you can verify its work. To speed up testing, Codex can hide the IAB to disable animations, and accelerate testing by 1-2x. Separately, we also made annotations send faster and consume less tokens. Hope you enjoy the updates and let us know what you think!
0:24

Codex can now use the in-app browser to test your app at different viewport sizes! It will control the device tool bar and click through your app at different breakpoints to validate & iterate. If it's a long run, Codex will take screenshots at key moments during testing and show them to you at the end of the turn, so you can verify its work. To speed up testing, Codex can hide the IAB to disable animations, and accelerate testing by 1-2x. Separately, we also made annotations send faster and consume less tokens. Hope you enjoy the updates and let us know what you think!

James Sun

229,193 views • 5 months ago

You can't build iOS apps without a Mac, so we gave Devin one. Devin Cloud Agents now run macOS, with Xcode, iOS simulator, and your signing setup, all in a real macOS environment (with full computer use). In this demo, Devin builds a native iOS game, then plays and tests it with computer use. Devin then sends a screen recording of the gameplay along with a test report for my review. With Namespace you get as many macOS environments as you'd like, configurable with many major versions of macOS operating system and Xcode.
1:23

You can't build iOS apps without a Mac, so we gave Devin one. Devin Cloud Agents now run macOS, with Xcode, iOS simulator, and your signing setup, all in a real macOS environment (with full computer use). In this demo, Devin builds a native iOS game, then plays and tests it with computer use. Devin then sends a screen recording of the gameplay along with a test report for my review. With Namespace you get as many macOS environments as you'd like, configurable with many major versions of macOS operating system and Xcode.

nader dabit

304,018 views • 3 months ago

Waiting months for API access? Give Claude a computer instead. Use E2B with Claude's new computer and browser use toolset, and Claude gets an isolated cloud machine where every action becomes a click or keystroke. Use it to automate the work an API can't reach, like testing your own UI end to end or entering data into a legacy app. Docs: Cookbook Example:
0:39

Waiting months for API access? Give Claude a computer instead. Use E2B with Claude's new computer and browser use toolset, and Claude gets an isolated cloud machine where every action becomes a click or keystroke. Use it to automate the work an API can't reach, like testing your own UI end to end or entering data into a legacy app. Docs: Cookbook Example:

E2B

16,578 views • 25 days ago

Shipping code shouldn’t mean hours of manual testing. Simulithic (YC F26) (YC F26) sends AI agents through your app like real users, across browsers, devices, and account types. It tells you what broke without you writing a single test script. The teams that ship fastest will be the ones that can verify as fast as they build. Get started today:
1:22

Shipping code shouldn’t mean hours of manual testing. Simulithic (YC F26) (YC F26) sends AI agents through your app like real users, across browsers, devices, and account types. It tells you what broke without you writing a single test script. The teams that ship fastest will be the ones that can verify as fast as they build. Get started today:

Satyam

46,230 views • 11 days ago

Uber had entire floors of people doing manual testing and manually clicking through the app, checking whether the app worked. It still wasn't enough, and it was too expensive They used deterministic script frameworks like Appium and XCUITest, but engineers ended up spending 50% of their time just maintaining test cases because of their brittle nature. This is a clip from a conversation with one of my DragonCrawl teammates and the overall goat, Juan Lopez Marcano, discussing the problems Uber faced at scale with end to end mobile testing.
3:35

Uber had entire floors of people doing manual testing and manually clicking through the app, checking whether the app worked. It still wasn't enough, and it was too expensive They used deterministic script frameworks like Appium and XCUITest, but engineers ended up spending 50% of their time just maintaining test cases because of their brittle nature. This is a clip from a conversation with one of my DragonCrawl teammates and the overall goat, Juan Lopez Marcano, discussing the problems Uber faced at scale with end to end mobile testing.

Anam Hira

245,094 views • 11 months ago

I let ChatGPT take FULL CONTROL of my computer. Super scary! It used the mouse and keyboard just like a human user. Here's a preview of what happened. Full video coming soon!
0:49

I let ChatGPT take FULL CONTROL of my computer. Super scary! It used the mouse and keyboard just like a human user. Here's a preview of what happened. Full video coming soon!

Matthew Berman

291,073 views • 2 years ago

Introducing Bud. The first AI Human Emulator. Bud has a full computer with storage, compute, and memory to build and code, sms and telegram to communicate, a full browser to use, can create/store/edit files, connect and use your tools, learn custom skills, work fully autonomously, and complete any task end to end just like a human. Text the number below or try free at bud [dot] app. Comment for 100k free credits.
1:06

Introducing Bud. The first AI Human Emulator. Bud has a full computer with storage, compute, and memory to build and code, sms and telegram to communicate, a full browser to use, can create/store/edit files, connect and use your tools, learn custom skills, work fully autonomously, and complete any task end to end just like a human. Text the number below or try free at bud [dot] app. Comment for 100k free credits.

Bud

717,702 views • 6 months ago

🎮 Computer Use Agent Arena is LIVE! 🚀 🔥 Easiest way to test computer-use agents in the wild without any setup 🌟 Compare top VLMs: OpenAI Operator, Claude 3.7, Gemini 2.5 Pro, Qwen 2.5 vl and more 🕹️ Test agents on 100+ real apps & webs with one-click config 🔒 Safe & free access on cloud-hosted machines Page: Leaderboard (tentative): Blog: Data & Code (coming soon): ⭐️Why Computer Agent Arena? 1️⃣Beyond Static Benchmarks: We use computers to perform enormous tasks and workflows every day, and AI agents have the potential to automate these tasks. However, existing benchmarks are very limited (e.g., only 369 tasks in OSWorld and 812 tasks in WebArena). To better measure their capabilities, we introduce Computer Agent Arena for users to easily compare & test AI agents on all kinds of crowdsourced real-world computer use tasks. 2️⃣Cloud Testing, Simplified: As agents like OpenAI’s Operator and Claude 3.7 sonnet release, users face configuration challenges and privacy hurdles to deploy on their own computers. Our platform integrates these agents with cloud-hosted machines, providing users with quick and secure access. 3️⃣Unified Embodied Digital Environment: Unlike Chatbot Arena, we provide users with a real embodied environment—computers—where all agents are grounded in real computer tasks and environments. Led by @XLANG_Lab [1/🧵]
0:32

🎮 Computer Use Agent Arena is LIVE! 🚀 🔥 Easiest way to test computer-use agents in the wild without any setup 🌟 Compare top VLMs: OpenAI Operator, Claude 3.7, Gemini 2.5 Pro, Qwen 2.5 vl and more 🕹️ Test agents on 100+ real apps & webs with one-click config 🔒 Safe & free access on cloud-hosted machines Page: Leaderboard (tentative): Blog: Data & Code (coming soon): ⭐️Why Computer Agent Arena? 1️⃣Beyond Static Benchmarks: We use computers to perform enormous tasks and workflows every day, and AI agents have the potential to automate these tasks. However, existing benchmarks are very limited (e.g., only 369 tasks in OSWorld and 812 tasks in WebArena). To better measure their capabilities, we introduce Computer Agent Arena for users to easily compare & test AI agents on all kinds of crowdsourced real-world computer use tasks. 2️⃣Cloud Testing, Simplified: As agents like OpenAI’s Operator and Claude 3.7 sonnet release, users face configuration challenges and privacy hurdles to deploy on their own computers. Our platform integrates these agents with cloud-hosted machines, providing users with quick and secure access. 3️⃣Unified Embodied Digital Environment: Unlike Chatbot Arena, we provide users with a real embodied environment—computers—where all agents are grounded in real computer tasks and environments. Led by @XLANG_Lab [1/🧵]

Bowen Wang

93,360 views • 1 year ago

ICP's National Messenger App Is Making Progress... Internet Computer (DFINITY Foundation) is accelerating the launch of Pakistan’s sovereign national messenger, now running on a localized cloud computing platform and in the testing stage with a smaller group. According to ICP's CBO, Pierre (Pierre), the application is "making great progress." Based on his comment on X, the app also includes built-in audio/video calls. The technology uses a tamper-proof, round-the-clock design to seamlessly integrate on-chain identity and end-to-end encryption into native iOS and Android apps. The team behind the messenger is relying on years of experience with OpenChat ∞ innovations to guarantee scalability for the national user base.
0:30

ICP's National Messenger App Is Making Progress... Internet Computer (DFINITY Foundation) is accelerating the launch of Pakistan’s sovereign national messenger, now running on a localized cloud computing platform and in the testing stage with a smaller group. According to ICP's CBO, Pierre (Pierre), the application is "making great progress." Based on his comment on X, the app also includes built-in audio/video calls. The technology uses a tamper-proof, round-the-clock design to seamlessly integrate on-chain identity and end-to-end encryption into native iOS and Android apps. The team behind the messenger is relying on years of experience with OpenChat ∞ innovations to guarantee scalability for the national user base.

BSCN

19,496 views • 2 months ago

Devin now has a Mac  Here are 11 experiments I've run over the past week, as well as open source code for over 100 more native apps. Build, test, deploy iOS, iPad, and macOS apps in the cloud with just a prompt. ⚡ 1. Build and test a multi-platform, multiplayer app in the cloud (iOS, iPad, web)
0:55

Devin now has a Mac  Here are 11 experiments I've run over the past week, as well as open source code for over 100 more native apps. Build, test, deploy iOS, iPad, and macOS apps in the cloud with just a prompt. ⚡ 1. Build and test a multi-platform, multiplayer app in the cloud (iOS, iPad, web)

nader dabit

733,928 views • 1 month ago

Cline now uses Anthropic's new "Computer Use" feature to launch a browser, click, type, and scroll. This gives him more autonomy in runtime debugging, end-to-end testing, and even general web use!
2:53

Cline now uses Anthropic's new "Computer Use" feature to launch a browser, click, type, and scroll. This gives him more autonomy in runtime debugging, end-to-end testing, and even general web use!

Saoud Rizwan

66,657 views • 2 years ago

Introducing /ui-test Give your agent a PR, and it'll test your feature in a real browser, generating an HTML report with UI fixes The planner agent generates adversarial test cases to break your app, assigns them to subagents, and evaluates the page using the Browserbase CLI We reviewed a merged PR on Cal.com and found a bunch of small UI nits:
0:35

Introducing /ui-test Give your agent a PR, and it'll test your feature in a real browser, generating an HTML report with UI fixes The planner agent generates adversarial test cases to break your app, assigns them to subagents, and evaluates the page using the Browserbase CLI We reviewed a merged PR on Cal.com and found a bunch of small UI nits:

Shrey Pandya

57,971 views • 7 months ago

What is ICP's National Messenger App? With the hype still around the product and it still in testing, it makes more sense to explore what it means... Simply put, the National Messenger App is a sovereign messenger application being built in Pakistan. The application is being developed in partnership between Pakistan Digital Authority (PDA) and DFINITY Foundation. 1.) A dedicated Pakistan subnet AKA Pakistan Cloud Engine of ICP, will power the app. It will feature the following: - Effortless chatting - Integrated audio/video calling - On-chain identity integration - End-to-end encryption 2.) Native iOS and Android apps are already available in the current testing phase and are being utilized by a small number of people. 3.) The app has been designed with experience and learnings from OpenChat ∞, ICP's existing decentralized messenger, to scale to support a larger user base. As of writing, the app is live on the Pakistan subnet, with the full rollout expected in the near future. When it goes live, the application will demonstrate ICP's ability to power secure tools at the government level while ensuring digital sovereignty, privacy, and resilience.
0:30

What is ICP's National Messenger App? With the hype still around the product and it still in testing, it makes more sense to explore what it means... Simply put, the National Messenger App is a sovereign messenger application being built in Pakistan. The application is being developed in partnership between Pakistan Digital Authority (PDA) and DFINITY Foundation. 1.) A dedicated Pakistan subnet AKA Pakistan Cloud Engine of ICP, will power the app. It will feature the following: - Effortless chatting - Integrated audio/video calling - On-chain identity integration - End-to-end encryption 2.) Native iOS and Android apps are already available in the current testing phase and are being utilized by a small number of people. 3.) The app has been designed with experience and learnings from OpenChat ∞, ICP's existing decentralized messenger, to scale to support a larger user base. As of writing, the app is live on the Pakistan subnet, with the full rollout expected in the near future. When it goes live, the application will demonstrate ICP's ability to power secure tools at the government level while ensuring digital sovereignty, privacy, and resilience.

BSCN

23,053 views • 2 months ago

you don't have to keep your laptop open for your agents to keep running just type /handoff and send your agent to the cloud with Devin (and close your laptop) from there, your agent gets: - its own Linux VM - shell, IDE, browser - full desktop Computer Use - end-to-end test recordings - ready-to-review PRs - it's own review agent you can continue your session from your phone, computer, or anywhere with an internet connection and you can send as many sessions as you'd like in parallel.
0:35

you don't have to keep your laptop open for your agents to keep running just type /handoff and send your agent to the cloud with Devin (and close your laptop) from there, your agent gets: - its own Linux VM - shell, IDE, browser - full desktop Computer Use - end-to-end test recordings - ready-to-review PRs - it's own review agent you can continue your session from your phone, computer, or anywhere with an internet connection and you can send as many sessions as you'd like in parallel.

nader dabit

61,479 views • 6 months ago