Loading video...

Video Failed to Load

Go Home

Better feedback = Better code. Artifacts are the agent’s proof of work. Review plans, screen recordings, and code changes. Then, leave feedback to keep the agent on track. Try it today:

antigravity's profile picture

Google Antigravity

170,767 subscribers

82,520 views • 7 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

In Antigravity, we’ve reimagined how you collaborate with Agents using Artifacts. Artifacts go beyond text. They are dynamic intermediates to communicate agentic progress like screen recordings, diagrams, or markdown. And you can leave feedback right on the artifact itself.
4:03

In Antigravity, we’ve reimagined how you collaborate with Agents using Artifacts. Artifacts go beyond text. They are dynamic intermediates to communicate agentic progress like screen recordings, diagrams, or markdown. And you can leave feedback right on the artifact itself.

Google Antigravity

66,726 views • 7 months ago

👀 Ever want a second set of eyes on your code? GitHub Copilot code review can help! Available in preview, Copilot code review offers fast, AI-powered feedback on your code as you write it. You can quickly apply any feedback that Copilot suggests, directly in the editor.
0:26

👀 Ever want a second set of eyes on your code? GitHub Copilot code review can help! Available in preview, Copilot code review offers fast, AI-powered feedback on your code as you write it. You can quickly apply any feedback that Copilot suggests, directly in the editor.

Visual Studio Code

75,224 views • 1 year ago

We built Claude Code into a browser & whiteboard! It's called Decode Decode It’s the fastest & best way to give UX feedback to Claude Code while coding locally & enables it to review & test changes itself See thread👇to learn how whiteboards makes it an even better browser
0:25

We built Claude Code into a browser & whiteboard! It's called Decode Decode It’s the fastest & best way to give UX feedback to Claude Code while coding locally & enables it to review & test changes itself See thread👇to learn how whiteboards makes it an even better browser

Francois Laberge

162,509 views • 9 months ago

"The work is done, and here’s the video to prove it." 🎥 Watching these agents run their own browser tests and provide screen recordings of the finished task is a massive win for transparency. It's not just about writing code; it's about closing the feedback loop automatically.
1:02

"The work is done, and here’s the video to prove it." 🎥 Watching these agents run their own browser tests and provide screen recordings of the finished task is a massive win for transparency. It's not just about writing code; it's about closing the feedback loop automatically.

Google Antigravity

72,241 views • 5 months ago

Meet Clicky, the browser use subagent in Amp, which records live screencasts with voiceovers of its changes, to prove the correctness of its work to you. Clicky gives Amp another powerful feedback loop to write code better and more autonomously. WIP, will ship when ready.
1:25

Meet Clicky, the browser use subagent in Amp, which records live screencasts with voiceovers of its changes, to prove the correctness of its work to you. Clicky gives Amp another powerful feedback loop to write code better and more autonomously. WIP, will ship when ready.

Quinn Slack

26,284 views • 7 months ago

i'm a little sick of chatgpt giving me obviously broken code i've found a "micro agent" approach to LLM code generation can work much better the LLM first generates a *test*, and then enters a loop where it generates and iterates on the code until the tests pass source below
0:23

i'm a little sick of chatgpt giving me obviously broken code i've found a "micro agent" approach to LLM code generation can work much better the LLM first generates a *test*, and then enters a loop where it generates and iterates on the code until the tests pass source below

Steve (Builder.io)

544,171 views • 2 years ago

Supercharge your development experience with JetBrains IDEs and the ChatGPT app on macOS! 🎉 ChatGPT can now analyze your code in the IDE to deliver better answers. Try the early beta now and share your feedback!
0:30

Supercharge your development experience with JetBrains IDEs and the ChatGPT app on macOS! 🎉 ChatGPT can now analyze your code in the IDE to deliver better answers. Try the early beta now and share your feedback!

JetBrains

97,367 views • 1 year ago

A live look at Planning Mode in action with Andy Zhang on the Flutter show. 📄 Implementation Plan – the agent’s logic ✍️ Feedback – leaving comments on that plan 🧾 Walkthrough – proof of the agent’s work
6:07

A live look at Planning Mode in action with Andy Zhang on the Flutter show. 📄 Implementation Plan – the agent’s logic ✍️ Feedback – leaving comments on that plan 🧾 Walkthrough – proof of the agent’s work

Google Antigravity

91,720 views • 7 months ago

Linear Diffs brings code review into Linear. Learn how to manage and review PRs, implement feedback with agents, and ship code without switching tools.
2:38

Linear Diffs brings code review into Linear. Learn how to manage and review PRs, implement feedback with agents, and ship code without switching tools.

Linear

22,000 views • 1 month ago

🚀Launching: LangSmith Engine LangSmith Engine is an agent that sits on top of your traces It runs in the background and automatically identifies issues It then proactively suggests action items (code changes, evaluators to add) Try it today:
1:11

🚀Launching: LangSmith Engine LangSmith Engine is an agent that sits on top of your traces It runs in the background and automatically identifies issues It then proactively suggests action items (code changes, evaluators to add) Try it today:

Harrison Chase

143,570 views • 2 months ago

Using LLaMA 3 70B on Groq Inc to instantly refactor and document code. The implications for software engineering are wild. Gone are the days of waiting on an LLM for suggestions or code changes. Now, it's an instant feedback loop. Demo link in the comments:
0:21

Using LLaMA 3 70B on Groq Inc to instantly refactor and document code. The implications for software engineering are wild. Gone are the days of waiting on an LLM for suggestions or code changes. Now, it's an instant feedback loop. Demo link in the comments:

Matt Shumer

442,695 views • 2 years ago

New agentic code review workflow unlocked! Before: You review a diff. Drop some comments. The agent makes changes but they're mixed with old changes. So you re-read everything. Give more feedback. Repeat. After: Diffs only show what's new since your last review, in realtime.
4:02

New agentic code review workflow unlocked! Before: You review a diff. Drop some comments. The agent makes changes but they're mixed with old changes. So you re-read everything. Give more feedback. Repeat. After: Diffs only show what's new since your last review, in realtime.

José Valim

12,996 views • 3 months ago

I’ve been working on dunk. It’s a terminal diff reviewer where you mark issues inline, then let a coding agent fix them. It started as a fork of hunk, but I stripped it down to the loop I need: review → my comments → agent fixes I’m spending time reviewing code and leaving comments for agents rather than writing code myself. But in most tools, that feedback loop still feels broken. dunk is a simple way to make it work across Claude Code, Codex, Pi, etc.
3:48

I’ve been working on dunk. It’s a terminal diff reviewer where you mark issues inline, then let a coding agent fix them. It started as a fork of hunk, but I stripped it down to the loop I need: review → my comments → agent fixes I’m spending time reviewing code and leaving comments for agents rather than writing code myself. But in most tools, that feedback loop still feels broken. dunk is a simple way to make it work across Claude Code, Codex, Pi, etc.

Amir Salihefendić

13,134 views • 2 months ago

CodiumAI PR-Agent is an open-source tool that assists developers in streamlining pull-request creation and review. It automatically analyzes the PR and can provide several types of feedback, including Auto-Description, PR Review, Q&A, Code Suggestion, and more.
0:25

CodiumAI PR-Agent is an open-source tool that assists developers in streamlining pull-request creation and review. It automatically analyzes the PR and can provide several types of feedback, including Auto-Description, PR Review, Q&A, Code Suggestion, and more.

Qodo

12,114,705 views • 2 years ago

Alien Fingers are out today! Check your local Alienlabs store to try them out and then drop some feedback on the thread
1:03

Alien Fingers are out today! Check your local Alienlabs store to try them out and then drop some feedback on the thread

Ted

25,275 views • 1 year ago

> Send code from Claude > Explore on the canvas > Prototype with AI > Work through feedback > Roundtrip back to code All in Figma
0:29

> Send code from Claude > Explore on the canvas > Prototype with AI > Work through feedback > Roundtrip back to code All in Figma

Figma

357,142 views • 4 months ago

Launch day! 🎉 Rolling out our first series of updates to the AI Studio UI with cleaner navigation, contextual actions, and a visual refresh. Next: improved prompt box, model cards, history, better code views, and much more. Keep the feedback coming—we'll keep shipping! 🚀
0:23

Launch day! 🎉 Rolling out our first series of updates to the AI Studio UI with cleaner navigation, contextual actions, and a visual refresh. Next: improved prompt box, model cards, history, better code views, and much more. Keep the feedback coming—we'll keep shipping! 🚀

Ammaar Reshi

74,861 views • 1 year ago

🌊The `ViewTransition` demo and its source code are now live! 🔗 Feel free to test it out, feedback is welcome!
0:20

🌊The `ViewTransition` demo and its source code are now live! 🔗 Feel free to test it out, feedback is welcome!

Jiachi

14,954 views • 1 year ago

You can decide how much autonomy you give to the agent in Google Antigravity Drop asynchronous feedback within artifacts and the agent folds it in when the time is right.
0:45

You can decide how much autonomy you give to the agent in Google Antigravity Drop asynchronous feedback within artifacts and the agent folds it in when the time is right.

Google Antigravity

81,962 views • 7 months ago