Loading video...

Video Failed to Load

Go Home

Devin and Devin Review now support GitHub Stacked PRs! They handle decomposition, rebases, conflicts, the CI, so you review a large feature as focused layers instead of one massive diff. Learn how it works!

dabit3's profile picture

nader dabit

190,911 subscribers

57,921 views • 11 days ago •via X (Twitter)

Science & TechnologyEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

You can now fix PRs without leaving Devin Review! Just ask Devin to fix any issues it found. Devin will propose inline code changes that you can apply with a single click. Swap github -> devinreview in any PR link to try Devin Review, no account needed.
0:35

You can now fix PRs without leaving Devin Review! Just ask Devin to fix any issues it found. Devin will propose inline code changes that you can apply with a single click. Swap github -> devinreview in any PR link to try Devin Review, no account needed.

Cognition

34,966 views • 5 months ago

Security review is now part of every Devin Review. Open a PR and Devin automatically finds the vulnerabilities scanners miss, explains each one, and drafts the fix.
0:38

Security review is now part of every Devin Review. Open a PR and Devin automatically finds the vulnerabilities scanners miss, explains each one, and drafts the fix.

Cognition

124,723 views • 1 month ago

Published my first agent skill today: Cloud Stacked Diffs ☁️ npx skills add dabit3/cloud-stacked-diffs It orchestrates cloud agents to deliver large long running tasks as a stack of small, dependent draft PRs, reviewed and merged bottom-up instead of one giant PR. Combined w/ Linear you can hand off large workflows and step away to a completely automated delivery loop: sub-issues become stacked PRs, tickets update as each one goes up, and you come back to a board in review and a stack ready to merge.
4:14

Published my first agent skill today: Cloud Stacked Diffs ☁️ npx skills add dabit3/cloud-stacked-diffs It orchestrates cloud agents to deliver large long running tasks as a stack of small, dependent draft PRs, reviewed and merged bottom-up instead of one giant PR. Combined w/ Linear you can hand off large workflows and step away to a completely automated delivery loop: sub-issues become stacked PRs, tickets update as each one goes up, and you come back to a board in review and a stack ready to merge.

nader dabit

63,671 views • 1 month 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

289,954 views • 16 days ago

I paid the $500 for Devin, the mega hyped AI coding agent, so you don't have to here's an in depth review of how it compares to Cursor:
9:40

I paid the $500 for Devin, the mega hyped AI coding agent, so you don't have to here's an in depth review of how it compares to Cursor:

Steve (Builder.io)

368,136 views • 1 year ago

This is how I’m currently running my startup with Devin + OpenClaw🦞 The browser testing in Devin is mind-blowing. I was trying to duct tape and jerry-rig all this stuff together with Playwright + uploading videos to PRs and all sorts of stuff and Devin just does it all e2e. Wild. I didn't show how I'm using Linear, which I am using for issue tracking. I have a "land" skill that I tell Devin to use whenever all the browser testing is done and all the CI goes green and it just merges the PR
3:50

This is how I’m currently running my startup with Devin + OpenClaw🦞 The browser testing in Devin is mind-blowing. I was trying to duct tape and jerry-rig all this stuff together with Playwright + uploading videos to PRs and all sorts of stuff and Devin just does it all e2e. Wild. I didn't show how I'm using Linear, which I am using for issue tracking. I have a "land" skill that I tell Devin to use whenever all the browser testing is done and all the CI goes green and it just merges the PR

Ryan Carson

28,230 views • 4 months ago

An influencer doing a food review is beaten and robbed mid review. A lot of blacks show love and support in my inbox because they are sick of the culture as well. Blacks are their number one victims.
0:37

An influencer doing a food review is beaten and robbed mid review. A lot of blacks show love and support in my inbox because they are sick of the culture as well. Blacks are their number one victims.

Amiri King

680,210 views • 1 month ago

If you're evaluating AI IDEs this week, here's what getting started with Windsurf looks like (links below): • Download and install from Import any existing IDE settings during onboarding, or start fresh. • Cascade is the agent panel on the right. Chat, generate, edit, run code. @-mention files, symbols, or docs to scope context. • Choose your model - Opus, Codex, SWE, Kimi, GLM and more (Kimi K2.6 is free for the next 2 weeks 👀) • DeepWiki: Cmd+Shift+Click any symbol for an in-depth explanation of what it does. Send it to Cascade with one click. • Codemaps: hierarchical view of how files and functions execute together. Click a node to jump to code. Shareable as links. • Devin in Windsurf: start and manage cloud sessions without leaving the editor. • Agent Command Center: Kanban board of every running agent, local (Cascade) and cloud (Devin). See what's in flight, blocked, or ready for review. • Spaces: group sessions, PRs, files, and context for one task or project into a single view. • Centralized review: handle diffs, PRs, and agent output in one place. • MCP servers, Memories, and Workflows extend Cascade. Set them up once; reuse across projects.
0:41

If you're evaluating AI IDEs this week, here's what getting started with Windsurf looks like (links below): • Download and install from Import any existing IDE settings during onboarding, or start fresh. • Cascade is the agent panel on the right. Chat, generate, edit, run code. @-mention files, symbols, or docs to scope context. • Choose your model - Opus, Codex, SWE, Kimi, GLM and more (Kimi K2.6 is free for the next 2 weeks 👀) • DeepWiki: Cmd+Shift+Click any symbol for an in-depth explanation of what it does. Send it to Cascade with one click. • Codemaps: hierarchical view of how files and functions execute together. Click a node to jump to code. Shareable as links. • Devin in Windsurf: start and manage cloud sessions without leaving the editor. • Agent Command Center: Kanban board of every running agent, local (Cascade) and cloud (Devin). See what's in flight, blocked, or ready for review. • Spaces: group sessions, PRs, files, and context for one task or project into a single view. • Centralized review: handle diffs, PRs, and agent output in one place. • MCP servers, Memories, and Workflows extend Cascade. Set them up once; reuse across projects.

nader dabit

16,694 views • 3 months ago

I built a Claude skill that helps you review a report as an analyst. Now, it thinks like a senior analyst for you. The readme file will explain how to use it as a skill on Claude or Copilot or Chatgpt Use & let me how it works. My gift to U
3:45

I built a Claude skill that helps you review a report as an analyst. Now, it thinks like a senior analyst for you. The readme file will explain how to use it as a skill on Claude or Copilot or Chatgpt Use & let me how it works. My gift to U

David Abu _

41,904 views • 5 months ago

Sovereign Syndicate is Available Now on Steam and GOG! Want to know how you can support us? Buy the game! Play the game! Leave a review! Tell your friends! Thanks so much for all your support.
1:23

Sovereign Syndicate is Available Now on Steam and GOG! Want to know how you can support us? Buy the game! Play the game! Leave a review! Tell your friends! Thanks so much for all your support.

CrimsonHerringStudios

147,407 views • 2 years ago

Most engineering processes were built for teams shipping 10 to 15 PRs a month. Kun Chen, ex-Meta L8 engineer, is now shipping 40+ PRs a day with agents. That breaks a lot of existing processes behind: → Code review & QA → Merge gates and team handoffs When output jumps 10x, the old workflows starts to crack. The answer is to build systems that streamline planning, validation, review, and merging as much as possible. 📌 Watch him talk more about it here:
0:42

Most engineering processes were built for teams shipping 10 to 15 PRs a month. Kun Chen, ex-Meta L8 engineer, is now shipping 40+ PRs a day with agents. That breaks a lot of existing processes behind: → Code review & QA → Merge gates and team handoffs When output jumps 10x, the old workflows starts to crack. The answer is to build systems that streamline planning, validation, review, and merging as much as possible. 📌 Watch him talk more about it here:

Peter Yang

15,566 views • 2 months ago

Reviewing AI-generated code is the new bottleneck. Writing code was slow before. Now, in a few minutes, you can generate virtually unlimited lines of code using AI. But developers are now spending 70% of their time checking that code. That's the new bottleneck. I've been using Cline, and they have a feature that actually helps with this: You can click a button and have Cline generate an inline explanation for every single line of AI-generated code. Take a look at the attached video. What it does: 1. You can read the code and the explanation together 2. You don't lose context while reviewing code 3. You understand the "why" behind each change And here is the best part: It works on any git diff. You can use it to review PRs, understand commits from other people, or catch up on a codebase you haven't touched in a while.
3:25

Reviewing AI-generated code is the new bottleneck. Writing code was slow before. Now, in a few minutes, you can generate virtually unlimited lines of code using AI. But developers are now spending 70% of their time checking that code. That's the new bottleneck. I've been using Cline, and they have a feature that actually helps with this: You can click a button and have Cline generate an inline explanation for every single line of AI-generated code. Take a look at the attached video. What it does: 1. You can read the code and the explanation together 2. You don't lose context while reviewing code 3. You understand the "why" behind each change And here is the best part: It works on any git diff. You can use it to review PRs, understand commits from other people, or catch up on a codebase you haven't touched in a while.

Santiago

64,425 views • 8 months ago

Auto manufacturers are now engineering cars in a way they if you break one small thing, a massive repair is needed Example: This door handle on the inside of this new 2023 vehicle broke, you would think you just need a new door handle. Wrong You now have to replace the entire door panel because they have manufactured it so that the door handle can not be removed So now instead of paying a small amount of money for a new door handle, you have pay insane amounts of money for a whole door panel This should be illegal. We need much stronger right to repair laws in America
2:54

Auto manufacturers are now engineering cars in a way they if you break one small thing, a massive repair is needed Example: This door handle on the inside of this new 2023 vehicle broke, you would think you just need a new door handle. Wrong You now have to replace the entire door panel because they have manufactured it so that the door handle can not be removed So now instead of paying a small amount of money for a new door handle, you have pay insane amounts of money for a whole door panel This should be illegal. We need much stronger right to repair laws in America

Wall Street Apes

642,490 views • 1 month ago

Three moves to set yourself up for a better 2026. Review one regret and use it as data. Break the year into focused 90-day seasons. Remove friction so starting becomes easy. Small structure beats big intentions.
1:02

Three moves to set yourself up for a better 2026. Review one regret and use it as data. Break the year into focused 90-day seasons. Remove friction so starting becomes easy. Small structure beats big intentions.

Daniel Pink

13,568 views • 7 months ago

📣 now works with GitHub Copilot chat! You can also filter development prompts with a new toggle 🥳 A big P.S.: I collaborated with the GitHub Copilot team on this, and they added a prompt injection feature to Copilot Chat for — it was the best pair-programming experience I’ve ever had! 🥹
0:38

📣 now works with GitHub Copilot chat! You can also filter development prompts with a new toggle 🥳 A big P.S.: I collaborated with the GitHub Copilot team on this, and they added a prompt injection feature to Copilot Chat for — it was the best pair-programming experience I’ve ever had! 🥹

fatih kadir akın

63,640 views • 1 year ago

Old way of using Claude Code: Prompt → wait → review → prompt → wait → review → repeat 20 times. You are the loop. You are the condition check. You are the reason it keeps going. New way: /goal all tests pass and lint is clean Claude works. You do something else. You come back to a result. Here's exactly how to set it up — and how to write conditions that actually work ↓
0:24

Old way of using Claude Code: Prompt → wait → review → prompt → wait → review → repeat 20 times. You are the loop. You are the condition check. You are the reason it keeps going. New way: /goal all tests pass and lint is clean Claude works. You do something else. You come back to a result. Here's exactly how to set it up — and how to write conditions that actually work ↓

Rahul

38,114 views • 3 months ago

💬: Can you review yourself in the future? EF: I'd ask for good health and time to travel to places that I want to go. I think that's all. 💬: Isn't it supposed to be a review? EF: I really don't know. I can give a review once it happened but no one knows what the future will be, so I can't give a review. Now I can only make a wish. #EngfaWaraha #อิงฟ้ามหาชน
0:38

💬: Can you review yourself in the future? EF: I'd ask for good health and time to travel to places that I want to go. I think that's all. 💬: Isn't it supposed to be a review? EF: I really don't know. I can give a review once it happened but no one knows what the future will be, so I can't give a review. Now I can only make a wish. #EngfaWaraha #อิงฟ้ามหาชน

Me_Myself_and_I

25,852 views • 10 months ago

Import large data sets in seconds! With Appwrite’s new CSV imports feature, you can import documents into your Appwrite collections using a simple CSV file. And the best part, you don’t even need a custom script. Check out this video to learn how it works.
2:23

Import large data sets in seconds! With Appwrite’s new CSV imports feature, you can import documents into your Appwrite collections using a simple CSV file. And the best part, you don’t even need a custom script. Check out this video to learn how it works.

Appwrite

44,969 views • 1 year ago

Now all buses are being turned into political playground by organised gang, all because you ArasuBus let the first one escape as if it was some kind of hack. All they do is insert a USB, format it and update the text. TN72 N2551 🎥rams. review
0:25

Now all buses are being turned into political playground by organised gang, all because you ArasuBus let the first one escape as if it was some kind of hack. All they do is insert a USB, format it and update the text. TN72 N2551 🎥rams. review

Dravidian Insights

25,509 views • 4 months ago

Different AI models find different bugs. So why not use all of them? Try this out in Copilot CLI: 1. Run /review 2. Ask it to use multiple model providers at once for a multi-agent code review 3. Get the highest possible signal and catch bugs before anyone else Evan Boyle shows how it's done. ▶️
0:39

Different AI models find different bugs. So why not use all of them? Try this out in Copilot CLI: 1. Run /review 2. Ask it to use multiple model providers at once for a multi-agent code review 3. Get the highest possible signal and catch bugs before anyone else Evan Boyle shows how it's done. ▶️

GitHub

47,741 views • 5 months ago