Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Antigravity 2.0 now features a dedicated planning mode, just like the Antigravity CLI. Type /plan and the agent steps back to think through the task, and conduct extensive research, before generating an implementation plan for your review. The agent will ask for your approval before it begins executing on... show more

Google Antigravity

190,920 subscribers

2,040,833 görüntüleme • 1 gün önce •via X (Twitter)

Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

35 Yorum

Andrius profil fotoğrafı

Andrius1 gün önce

Anthropic we are planning to remove plan mode, Google we are adding... ⚰️

Joel profil fotoğrafı

Joel1 gün önce

please bring the model even closer to opus 5.5 in terms of quality, so that plan mode will no longer be necessary

Google Antigravity profil fotoğrafı

Google Antigravity1 gün önce

Learn more

The Canasian profil fotoğrafı

The Canasian1 gün önce

yall just integrated a feature that is getting discontinuated

SolarFlare profil fotoğrafı

SolarFlare1 gün önce

Why can't you even handle the most basic command-line authorization? I've clearly authorized all Git commands and other commands for the entire project, yet I keep having to authorize everything again and again

Norbert profil fotoğrafı

Norbert1 gün önce

Bro, I don't know if you know, but practically everyone is getting rid of plan mode right now. But no wonder you're so far behind when you're still providing gpt-oss 120B and opus 4.6 in antigravity

Aditya Yadav profil fotoğrafı

Aditya Yadav1 gün önce

We'll be more happy if Opus 4.6 is replaced with Opus 5.5 than this feature

Pinku Swargiary profil fotoğrafı

Pinku Swargiary1 gün önce

where is /status or /context or /compact or /usage, where are the basic features which other tools like codex or claude are providing ? where is file browser in side ?? and this plan is should have come way way back, its been ages ?

EatMyTarts profil fotoğrafı

EatMyTarts1 gün önce

Incredible. Glad antigravity is catching up to last year.

VkDream profil fotoğrafı

VkDream1 gün önce

批准环节是真把关还是全民无脑点同意后者的话这功能等于没有

Kara Deku profil fotoğrafı

Kara Deku1 gün önce

I got a feature suggestion: the part in the UI where it has an option to pick Opus 4.6 - bump it up to Opus 5.5 👀

FerTech 🇨🇭 profil fotoğrafı

FerTech 🇨🇭1 gün önce

Are we able to use our own models within antigravity already ?

Flix Muller profil fotoğrafı

Flix Muller1 gün önce

This is a great upgrade for agentic coding. 🔥 Having the agent research, plan, and get approval before execution makes complex tasks much more structured and controlled.

ShadowAguy profil fotoğrafı

ShadowAguy1 gün önce

The example plan is offline first RSS with Node SQLite YAML MCP CLI. That's already a full spec. What is /plan actually adding?

RAZA | AI EXPLORER profil fotoğrafı

RAZA | AI EXPLORER1 gün önce

Planning before execution is a big upgrade.

Naveen Saradhi profil fotoğrafı

Naveen Saradhi1 gün önce

Bro never thinks about gemini 4 pro model ?

Grvnmael ‏יהוה profil fotoğrafı

Grvnmael ‏יהוה1 gün önce

Anyone facing this too “your account is not eligible for gemini code assist for individuals at this time”

Henrique Dalposso profil fotoğrafı

Henrique Dalposso1 gün önce

Changed the whole AI game

Jeremy Turner profil fotoğrafı

Jeremy Turner1 gün önce

Are we still talking about Google?

Ajay profil fotoğrafı

Ajay1 gün önce

One year after launch you noticed that coding agent need a planning mode? I guess what else you're missing.

Isqi profil fotoğrafı

Isqi1 gün önce

Hey, we don't know what happened, but your models No, it's slow and easy to disconnect.Please resolve this problem.

█████ profil fotoğrafı

█████1 gün önce

¿Alguna solución? You do not have a valid license of this product. Please contact your administrator to request a license. If you are not an enterprise user and believe you are receiving this message as an error, please try using the latest version and logging in again. (#3501)

Fernando Ruiz profil fotoğrafı

Fernando Ruiz1 gün önce

A dedicated /plan step before the agent runs is such a calm UX move. Asking for approval on the research and the plan turns agent work into a reviewable craft loop instead of a black box.

tudi99fyq profil fotoğrafı

tudi99fyq1 gün önce

厉害了，非常棒

yukonit profil fotoğrafı

yukonit1 gün önce

When will we see Google's compute power? Thats the question

John Rood profil fotoğrafı

John Rood1 gün önce

approval before execution is table stakes; what breaks at fleet scale is every run re-deriving a plan you already approved ten times. keep approved plans as per-task-class templates, so planning becomes diffing the template against the new situation. approval only scales when it's amortized.

Amaurys Figueroa profil fotoğrafı

Amaurys Figueroa1 gün önce

I did just that yesterday by asking the agent to pause for a moment and do some research

Az Vibe Coder profil fotoğrafı

Az Vibe Coder1 gün önce

kb shortcut for change model at agy would be nice

Avibe profil fotoğrafı

Avibe1 gün önce

When an agent goes straight into edits, most of the cleanup comes from paths nobody agreed to. The files change before anyone has seen the plan. The useful part of /plan is the order it forces. The agent finishes the research first, then shows an outline you can reject, and then it waits. Nothing gets written until you approve that outline. After one approval, it starts coding.

蓝色沉寂 profil fotoğrafı

蓝色沉寂1 gün önce

为什么要默认启用自带的几十个技能？这些技能大部分人不需要。占用上下文。或许有什么我不知道的？

Synapse keyboard profil fotoğrafı

Synapse keyboard1 gün önce

Why aren't they updating the Claude models? And why are the limits so low? If you're not going to bring anything new, just shut it down.

Sam Ongaro profil fotoğrafı

Sam Ongaro1 gün önce

Honestly, interesting approach; how granular can the plan be, and can you tweak it after the agent suggests one?

doubledimple profil fotoğrafı

doubledimple1 gün önce

请问4什么时候发布

Damilola Akinola profil fotoğrafı

Damilola Akinola1 gün önce

Make it a toggle

Alex profil fotoğrafı

Alex1 gün önce

curious whether /plan surfaces its research inline or just hands you the final proposal with sources buried

Benzer Videolar

We've added Plan Mode to Claude Code in Slack. When you give Claude a complex task it will ask you clarifying questions and show you an implementation plan before proceeding.

We've added Plan Mode to Claude Code in Slack. When you give Claude a complex task it will ask you clarifying questions and show you an implementation plan before proceeding.

Thariq is on vacation

188,110 görüntüleme • 7 ay önce

Planner mode in Cursor is SUPER helpful! With this prompt, agent mode will… ✅ Ask 4-6 clarifying questions ✅ Create a plan with multiple phases ✅ Ask for feedback + approval on the plan ✅ Implement each phase of the plan Steal this prompt down below ⬇️

Planner mode in Cursor is SUPER helpful! With this prompt, agent mode will… ✅ Ask 4-6 clarifying questions ✅ Create a plan with multiple phases ✅ Ask for feedback + approval on the plan ✅ Implement each phase of the plan Steal this prompt down below ⬇️

Ted Werbel

79,013 görüntüleme • 1 yıl önce

Don't let AI write code blindly. In Antigravity, request an "Implementation Plan" artifact first. Review the architecture, edit the markdown logic, and then approve execution. Control the outcome, don't just hope for it.

Don't let AI write code blindly. In Antigravity, request an "Implementation Plan" artifact first. Review the architecture, edit the markdown logic, and then approve execution. Control the outcome, don't just hope for it.

Google Antigravity

185,166 görüntüleme • 7 ay önce

Cline v3.2 has a new Plan/Act toggle 🚀 Plan mode turns Cline into an architect that gathers information, asks clarifying questions, and designs a solution for you to review. Switch back to Act mode to let him execute the plan! This gives you a chance to flush out task details before wasting time and tokens going down the wrong direction.

Cline v3.2 has a new Plan/Act toggle 🚀 Plan mode turns Cline into an architect that gathers information, asks clarifying questions, and designs a solution for you to review. Switch back to Act mode to let him execute the plan! This gives you a chance to flush out task details before wasting time and tokens going down the wrong direction.

Saoud Rizwan

75,455 görüntüleme • 1 yıl önce

The #1 problem with coding agents right now: Ask them to solve one problem, and they will make 10 other changes you didn't want. This happens to me every day. It happens to everyone I talk to as well. We have a solution for this now. The team Augment Code released a "Task List" feature for their coding assistant that solves this problem. Augment Code is partnering with me on this post. In case you haven't used them before: • Augment Code is a fully-fledged coding assistant • Their specialty are large projects • Fastest coding indexing I've seen • Has a free forever community edition Now, you can ask their coding agent to generate a Task List before doing anything. This will give you a plan you can review, edit, and augment if you need to. You can export this plan, load it on a different session, or even share it across projects. It makes a huge difference: The task list constrains the agent so you won't get any "unintended" changes anymore. It also puts you in control of everything the agent does. Check the video to see the agent working through a task list. You can also try this 100% free: (By the way, they also have support for remote agents. You can basically have those agents write your code while you are sleeping.)

The #1 problem with coding agents right now: Ask them to solve one problem, and they will make 10 other changes you didn't want. This happens to me every day. It happens to everyone I talk to as well. We have a solution for this now. The team Augment Code released a "Task List" feature for their coding assistant that solves this problem. Augment Code is partnering with me on this post. In case you haven't used them before: • Augment Code is a fully-fledged coding assistant • Their specialty are large projects • Fastest coding indexing I've seen • Has a free forever community edition Now, you can ask their coding agent to generate a Task List before doing anything. This will give you a plan you can review, edit, and augment if you need to. You can export this plan, load it on a different session, or even share it across projects. It makes a huge difference: The task list constrains the agent so you won't get any "unintended" changes anymore. It also puts you in control of everything the agent does. Check the video to see the agent working through a task list. You can also try this 100% free: (By the way, they also have support for remote agents. You can basically have those agents write your code while you are sleeping.)

Santiago

41,738 görüntüleme • 1 yıl önce

Working on a detailed prompt? 📝 Press Ctrl+X to open and edit the prompt in your preferred editor like Google Antigravity for example. When you are done, your prompt will be waiting for you back in Gemini CLI 🪄

Working on a detailed prompt? 📝 Press Ctrl+X to open and edit the prompt in your preferred editor like Google Antigravity for example. When you are done, your prompt will be waiting for you back in Gemini CLI 🪄

Gemini CLI

43,912 görüntüleme • 7 ay önce

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

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

91,849 görüntüleme • 10 ay önce

This is next level vibe coding. Google new IDE Antigravity is incredible when you combine Nano Banana Pro for layout and Gemini 3.0 Pro for coding. Process: - Antigravity creates the layout design and plan - You review it and provide feedback - Antigravity builds the webpage and creates relevant assets - Antigavity agent also test the webpage.

This is next level vibe coding. Google new IDE Antigravity is incredible when you combine Nano Banana Pro for layout and Gemini 3.0 Pro for coding. Process: - Antigravity creates the layout design and plan - You review it and provide feedback - Antigravity builds the webpage and creates relevant assets - Antigavity agent also test the webpage.

AshutoshShrivastava

203,890 görüntüleme • 10 ay önce

I gave Qoder a task instead of a prompt. And it actually did the work. It read the context, made a plan, used the tools it needed, executed the task, and verified the result before finishing. That’s the big difference with Qoder. It feels less like chatting with AI and more like handing a task to an AI agent on your computer. You describe the outcome you want. Qoder can then: • Read your workspace and context • Plan how to complete the task • Execute commands and make file changes • Use the browser or desktop when needed • Let you pause, adjust, or take over • Verify the result when it’s done And right now, Qwen3.8-Flash runs at 0.0x Credits through September 30. New users can also get 600 Credits in total. Try Qoder here: If you already use AI for coding or everyday computer work, this is worth experimenting with.

I gave Qoder a task instead of a prompt. And it actually did the work. It read the context, made a plan, used the tools it needed, executed the task, and verified the result before finishing. That’s the big difference with Qoder. It feels less like chatting with AI and more like handing a task to an AI agent on your computer. You describe the outcome you want. Qoder can then: • Read your workspace and context • Plan how to complete the task • Execute commands and make file changes • Use the browser or desktop when needed • Let you pause, adjust, or take over • Verify the result when it’s done And right now, Qwen3.8-Flash runs at 0.0x Credits through September 30. New users can also get 600 Credits in total. Try Qoder here: If you already use AI for coding or everyday computer work, this is worth experimenting with.

Shushant Lakhyani

139,779 görüntüleme • 10 saat önce

Built in Antigravity 2.0 and executing through the Antigravity SDK, the agent builds a full-stack collaborative Markdown editor with real-time multi agent state syncing and live previewing fast on 3.6 Flash. ⚡

Built in Antigravity 2.0 and executing through the Antigravity SDK, the agent builds a full-stack collaborative Markdown editor with real-time multi agent state syncing and live previewing fast on 3.6 Flash. ⚡

Google Antigravity

81,067 görüntüleme • 2 ay önce

Building an app isn’t one-size-fits-all. Watch two habit trackers built side-by-side in Antigravity using two different approaches: Fast Mode is for when the task is straightforward and you just need execution. It’s punchy, functional, and delivers at high velocity. Planning Mode is for taking a more thoughtful, scalable approach. It is designed for those who want to craft custom systems with deep, intricate logic or for follow-up tasks that require thorough context retrieval or reasoning. It may take longer, but in this mode, the Agent starts with thorough reasoning and planning, exposes implementation plan Artifacts, and focuses on self-verification.

Building an app isn’t one-size-fits-all. Watch two habit trackers built side-by-side in Antigravity using two different approaches: Fast Mode is for when the task is straightforward and you just need execution. It’s punchy, functional, and delivers at high velocity. Planning Mode is for taking a more thoughtful, scalable approach. It is designed for those who want to craft custom systems with deep, intricate logic or for follow-up tasks that require thorough context retrieval or reasoning. It may take longer, but in this mode, the Agent starts with thorough reasoning and planning, exposes implementation plan Artifacts, and focuses on self-verification.

Google Antigravity

89,391 görüntüleme • 8 ay önce

Preview of our DeepResearchSwarm™ It's incomprehensibly fast as it leverages a multi-agent architecture instead of just one agent. It utilizes a joint hierarchical-parallel architecture that creates a plan and then concurrently executes the plan with multiple search agents. Workflow: Task → Research Director → multiple search agents → final summary by summarization agent. Stay tuned for the release ↓

Preview of our DeepResearchSwarm™ It's incomprehensibly fast as it leverages a multi-agent architecture instead of just one agent. It utilizes a joint hierarchical-parallel architecture that creates a plan and then concurrently executes the plan with multiple search agents. Workflow: Task → Research Director → multiple search agents → final summary by summarization agent. Stay tuned for the release ↓

swarms

17,732 görüntüleme • 1 yıl önce

Your Plan SUCKS! 👀 Inspired by the legend Andrej Karpathy himself, I created a new skill: LLM Council. Create better plans, by committee. Supports: > Codex CLI > Gemini CLI > Claude Code > OpenCode Call the skill with your feature that you'd like to build. It will ask you some clarifying question, and then launch up to four parallel planning agents to create a detailed plan. Once the plans are in, all plans are anonymized and the "The Judge" will critique and choose the best plan *OR* the best parts from all of them. Finally, it will output a final-plan, which you can review and refine. I even created a nice UI for you to review and refine your plans. This Skill has been tested on Linux only, but should work on other platforms. Please report any bugs! Links in the comments.

Your Plan SUCKS! 👀 Inspired by the legend Andrej Karpathy himself, I created a new skill: LLM Council. Create better plans, by committee. Supports: > Codex CLI > Gemini CLI > Claude Code > OpenCode Call the skill with your feature that you'd like to build. It will ask you some clarifying question, and then launch up to four parallel planning agents to create a detailed plan. Once the plans are in, all plans are anonymized and the "The Judge" will critique and choose the best plan OR the best parts from all of them. Finally, it will output a final-plan, which you can review and refine. I even created a nice UI for you to review and refine your plans. This Skill has been tested on Linux only, but should work on other platforms. Please report any bugs! Links in the comments.

am.will

69,134 görüntüleme • 8 ay önce

New in Claude Code: /ultraplan Claude builds an implementation plan for you on the web. You can read it and edit it, then run the plan on the web or back in your terminal. Available now in preview for all users with CC on the web enabled.

New in Claude Code: /ultraplan Claude builds an implementation plan for you on the web. You can read it and edit it, then run the plan on the web or back in your terminal. Available now in preview for all users with CC on the web enabled.

Thariq

1,302,413 görüntüleme • 5 ay önce

AI agents can plan the work and Circle Agent Wallet helps them pay for it. This tutorial walks through how to: → Create your first wallet → Fund it with USDC → Pay for services → Return receipts as part of the task

AI agents can plan the work and Circle Agent Wallet helps them pay for it. This tutorial walks through how to: → Create your first wallet → Fund it with USDC → Pay for services → Return receipts as part of the task

Circle

24,586 görüntüleme • 1 ay önce

This is incredible I ask an AI agent to make me $10,000 It then did market research, built a business plan, and started executing on that plan Now ANYONE can use AI agents to build entire businesses for them autonomously (trust me, you want to bookmark this one)

This is incredible I ask an AI agent to make me $10,000 It then did market research, built a business plan, and started executing on that plan Now ANYONE can use AI agents to build entire businesses for them autonomously (trust me, you want to bookmark this one)

Alex Finn

135,437 görüntüleme • 1 yıl önce

Cursor can now fix your hardest bugs. Debug Mode instruments your code, spins up a server to capture logs, and streams runtime data to the agent. Also in 2.2: Plan Mode improvements, multi-agent judging, and more.

Cursor can now fix your hardest bugs. Debug Mode instruments your code, spins up a server to capture logs, and streams runtime data to the agent. Also in 2.2: Plan Mode improvements, multi-agent judging, and more.

Cursor

547,405 görüntüleme • 9 ay önce

We’re thrilled to announce the Antigravity CLI, a lightweight way to spin up the same Antigravity agents right from the terminal. 💻 It gives you the exact same harness and same models, with a product experience tailored for the command line. It adapts entirely to you: your keybindings, your themes, your workflows. Full Antigravity CLI Walkthrough:

We’re thrilled to announce the Antigravity CLI, a lightweight way to spin up the same Antigravity agents right from the terminal. 💻 It gives you the exact same harness and same models, with a product experience tailored for the command line. It adapts entirely to you: your keybindings, your themes, your workflows. Full Antigravity CLI Walkthrough:

Google Antigravity

202,435 görüntüleme • 4 ay önce