Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Perplexity Comet can automate any task in your browser This is the first time you REALLY have an AI agent working autonomously for you. Makes much more sense than n8n or Make. → Navigate websites → Click, type, scroll, etc. → No code only natural language You can delegate... show more

Paul Couvert

221,162 subscribers

81,497 views • 1 year ago •via X (Twitter)

Health & Wellness Science & Technology Education

Anya Rossi• Live Now

Private livecam show

10 Comments

Paul Couvert1 year ago

Prompt used: Navigate to the Google Trends website, then compare the worldwide search trends for "n8n", "Power Automate", "Copilot Studio" over the past 12 months using Google Trends. Then produce a short conclusion on how they currently compare and possible future developments.

Paul Couvert1 year ago

I'll give one invitation to Comet to someone in the comments of the first post (with the video). Not sponsored btw, I just love the browser!

Shawn Chauhan1 year ago

Natural language control is a total game changer

Paul Couvert1 year ago

Yes, you don't have to connect weird blocks or anything. Just plain english!

Jerrod Lew1 year ago

So damn good, I can't wait to get access to this.

Paul Couvert1 year ago

You'll love it. This is 100% the future of automation.

greg1 year ago

Excited to see what happens in the browser space

Paul Couvert1 year ago

Same. 100% the beginning of a new wave.

Shivang Soni1 year ago

Brother this looks so cool i am dying to try it can you give me invite

Paul Couvert1 year ago

You're in, Shivang! Would love to have more to send one to everyone but I shared the first with a close friend so I've just one remaining for now.

Related Videos

Gemini 2.5 Pro can automate your browser You can ask it to perform any task fully autonomously using this free and open source extension. No need for n8n, Make or Zapier. 00:00 - Presentation 01:10 - Settings 02:18 - First demo 04:11 - Benefits over n8n 04:46 - Second demo on X 06:19 - Conclusion This uses your own browser. You won't need to connect countless APIs or leak your credentials.

Gemini 2.5 Pro can automate your browser You can ask it to perform any task fully autonomously using this free and open source extension. No need for n8n, Make or Zapier. 00:00 - Presentation 01:10 - Settings 02:18 - First demo 04:11 - Benefits over n8n 04:46 - Second demo on X 06:19 - Conclusion This uses your own browser. You won't need to connect countless APIs or leak your credentials.

Paul Couvert

235,446 views • 1 year ago

Gemini CLI can automate your computer using MCP 🔥 Add Windows MCP (or macOS MCP) to Gemini CLI and you can tell it what to do autonomously. Gemini then takes control of your entire system to achieve the goal you've set. Links below

Gemini CLI can automate your computer using MCP 🔥 Add Windows MCP (or macOS MCP) to Gemini CLI and you can tell it what to do autonomously. Gemini then takes control of your entire system to achieve the goal you've set. Links below

Paul Couvert

131,661 views • 1 year ago

Wow Microsoft just announced Copilot Actions for local files 🤯 You can basically ask Copilot to perform any task on your machine autonomously. Yes. - Open Copilot in Windows - Assign a goal in natural language - Copilot launches a contained environment - It works autonomously for you Copilot can use both your desktop and any web app. And you can take back control at any time. This allows you to do whatever you want while the AI performs your tasks... or even do nothing at all. The entire OS becomes agentic. Impressive.

Wow Microsoft just announced Copilot Actions for local files 🤯 You can basically ask Copilot to perform any task on your machine autonomously. Yes. - Open Copilot in Windows - Assign a goal in natural language - Copilot launches a contained environment - It works autonomously for you Copilot can use both your desktop and any web app. And you can take back control at any time. This allows you to do whatever you want while the AI performs your tasks... or even do nothing at all. The entire OS becomes agentic. Impressive.

Paul Couvert

87,420 views • 9 months ago

Look, you've gotta take 15% of your salary or any money you make cutting the lawn or whatever it is and you've got to invest it. What my mother did was never let more than 5% into any one stock and no more than 20% into any one sector. She didn't have ETFs back then. Now you can do this easily with an ETF, you can download an app. The key is have the discipline to save 15% from your average salary and if you start in your mid-20s and you have the discipline not to buy more crap you will be wealthy by the time you retire.

Look, you've gotta take 15% of your salary or any money you make cutting the lawn or whatever it is and you've got to invest it. What my mother did was never let more than 5% into any one stock and no more than 20% into any one sector. She didn't have ETFs back then. Now you can do this easily with an ETF, you can download an app. The key is have the discipline to save 15% from your average salary and if you start in your mid-20s and you have the discipline not to buy more crap you will be wealthy by the time you retire.

Kevin O'Leary aka Mr. Wonderful

69,927 views • 1 year ago

THIS GUY ADDED A LIVE BROWSER TO CLAUDE CODE SO YOU CAN CLICK ANY ELEMENT AND EDIT IT INSTANTLY biggest issue with vibe coding UI is that you have to describe what you want to change. if you prompt it the wrong selector or wrong component, Claude can't find it. now you just click it. your app runs in an embedded browser with Claude Code. you can click any button, any text, any div. Claude instantly knows exactly what you're pointing at. click. instruct. done. no more "change the button in the top right corner of the second card component." all you have to do now is just click the button. AND its open source

THIS GUY ADDED A LIVE BROWSER TO CLAUDE CODE SO YOU CAN CLICK ANY ELEMENT AND EDIT IT INSTANTLY biggest issue with vibe coding UI is that you have to describe what you want to change. if you prompt it the wrong selector or wrong component, Claude can't find it. now you just click it. your app runs in an embedded browser with Claude Code. you can click any button, any text, any div. Claude instantly knows exactly what you're pointing at. click. instruct. done. no more "change the button in the top right corner of the second card component." all you have to do now is just click the button. AND its open source

Om Patel

152,749 views • 3 months ago

This makes the future way closer than you think. Director AI automates any tasks you can do in a browser. It interacts with web pages just like a person would. If you could use a browser to complete a task, you can have this AI do it for you. And it's free! Watch the video:

This makes the future way closer than you think. Director AI automates any tasks you can do in a browser. It interacts with web pages just like a person would. If you could use a browser to complete a task, you can have this AI do it for you. And it's free! Watch the video:

Santiago

36,273 views • 1 year ago

A browser that thinks for itself. I tried out the new Genspark AI Browser—and it changes the way you browse the web. In this example, I'll show you how you can display news directly as an AI podcast with a single click, summarize websites, and much more!

A browser that thinks for itself. I tried out the new Genspark AI Browser—and it changes the way you browse the web. In this example, I'll show you how you can display news directly as an AI podcast with a single click, summarize websites, and much more!

Chubby♨️

177,768 views • 10 months ago

ohhh my... Claude Code for Video Animations is insane. In 1 prompt you can create animated videos with Claude Code... w/ the new Remotion skill. And you can do this in the browser because vibecode.dev uses Claude Code as the default agent. (Full prompt below 👇)

ohhh my... Claude Code for Video Animations is insane. In 1 prompt you can create animated videos with Claude Code... w/ the new Remotion skill. And you can do this in the browser because vibecode.dev uses Claude Code as the default agent. (Full prompt below 👇)

Vibecoding Explained

40,260 views • 5 months ago

For the first time, you can vibe-code any AI agent. Meet — Computer Human AI by Langbase ☕ 🔹Prompt: "make an agent that…" 🔹Sip: chai builds any AI agent 🔹Ship: every agent gets a UI 🤯 Like your on-demand AI Engineer. What will you s(h)ip today?

For the first time, you can vibe-code any AI agent. Meet — Computer Human AI by Langbase ☕ 🔹Prompt: "make an agent that…" 🔹Sip: chai builds any AI agent 🔹Ship: every agent gets a UI 🤯 Like your on-demand AI Engineer. What will you s(h)ip today?

Ahmad Awais

149,221 views • 1 year ago

I built a FREE AI Agent that can browse the web, code websites, and automate tasks WITHOUT any technical setup I literally have my own AI assistant that works 24/7 In this video I'll show you how to easily set it up No coding experience required (Trust me, you want to bookmark this)

I built a FREE AI Agent that can browse the web, code websites, and automate tasks WITHOUT any technical setup I literally have my own AI assistant that works 24/7 In this video I'll show you how to easily set it up No coding experience required (Trust me, you want to bookmark this)

Julian Goldie SEO

47,804 views • 1 year ago

You can just ask Perplexity Comet to generate a video for you using Veo 3 inside Gemini 🙂 You can either give a detailed prompt with steps or just keep it simple like this, both work: Comet Prompt: You have access to the Gemini interface, use it to generate a video and wait for rendering to complete. Prompt: It figures out the rest. Where to paste the prompt, whether to click the video option, everything. Pretty smart.

You can just ask Perplexity Comet to generate a video for you using Veo 3 inside Gemini 🙂 You can either give a detailed prompt with steps or just keep it simple like this, both work: Comet Prompt: You have access to the Gemini interface, use it to generate a video and wait for rendering to complete. Prompt: It figures out the rest. Where to paste the prompt, whether to click the video option, everything. Pretty smart.

AshutoshShrivastava

35,501 views • 1 year ago

Genspark AI just released AI Browser. You can now have an AI agent in your browser to automate browsing, planning, and interacting with the web for you. 5 powerful use cases + how to try👇: 1. Download all papers talked in a YouTube video

Genspark AI just released AI Browser. You can now have an AI agent in your browser to automate browsing, planning, and interacting with the web for you. 5 powerful use cases + how to try👇: 1. Download all papers talked in a YouTube video

Alvaro Cintas

157,606 views • 1 year ago

today, on the DL, Notion released WORKERS. workers are a generic code execution environment that let you build interfaces within Notion the first interface we're exposing is the ability to make your own custom agent tools you can now make a tool for a custom agent that executes arbitrary code... and if you can execute arbitrary code, you can do pretty much anything!

today, on the DL, Notion released WORKERS. workers are a generic code execution environment that let you build interfaces within Notion the first interface we're exposing is the ability to make your own custom agent tools you can now make a tool for a custom agent that executes arbitrary code... and if you can execute arbitrary code, you can do pretty much anything!

Sam Catania

81,830 views • 4 months ago

OpenAI just launched Atlas, a browser that has AI agents as a native capability. Now you can let browser agents take over your software and automate anything. Here's the agent using Box to automate folder creation for an M&A due diligence process (sped up).

OpenAI just launched Atlas, a browser that has AI agents as a native capability. Now you can let browser agents take over your software and automate anything. Here's the agent using Box to automate folder creation for an M&A due diligence process (sped up).

Aaron Levie

353,829 views • 8 months ago

This morning at Retool Summit, we introduced application generation in Retool — where, for the first time, you can generate apps on top of your data (e.g. Salesforce, postgres, etc.) using natural language. Type what you want -> Have a working, production-ready app.

This morning at Retool Summit, we introduced application generation in Retool — where, for the first time, you can generate apps on top of your data (e.g. Salesforce, postgres, etc.) using natural language. Type what you want -> Have a working, production-ready app.

David Hsu

23,265 views • 9 months ago

You can now give AI agents the ability to interact with ANY website. This new MCP server lets Claude, Cursor, or any AI agent navigate, click, fill forms, and extract data from sites without APIs. Just connect it and give it a URL + goal. Here’s how to set it up:

You can now give AI agents the ability to interact with ANY website. This new MCP server lets Claude, Cursor, or any AI agent navigate, click, fill forms, and extract data from sites without APIs. Just connect it and give it a URL + goal. Here’s how to set it up:

Alvaro Cintas

77,654 views • 7 months ago

this is insane. just toggle this button and any coding agent can use your browser > no more Chrome extensions > One button, connect Claude Code to your browser all you need is the right harness... try it with the Browser Use CLI right now!

this is insane. just toggle this button and any coding agent can use your browser > no more Chrome extensions > One button, connect Claude Code to your browser all you need is the right harness... try it with the Browser Use CLI right now!

shawn

639,600 views • 4 months ago

Agentic Browser will be lived tomorrow! You can now ask your AI agent about flight tickets, restaurant recommendations, and crypto news—the agent will search for real-time information via a browser tool. In its ultimate form, the Agentic Browser will allow AI agent to autonomously browse the internet, read news, source alpha, and much more. We’re one step closer to fully sentient AI agents.

Agentic Browser will be lived tomorrow! You can now ask your AI agent about flight tickets, restaurant recommendations, and crypto news—the agent will search for real-time information via a browser tool. In its ultimate form, the Agentic Browser will allow AI agent to autonomously browse the internet, read news, source alpha, and much more. We’re one step closer to fully sentient AI agents.

delaunch

30,986 views • 1 year ago

You can now automate anything using Gemini in Chrome Just describe the task and that's it. - Nothing to configure - Works on tools without API - Fully integrated in Google's ecosystem And since 99% of tasks are now browser-based, there are no limits. Even if it's "slower than doing it manually" you can let it run in the background. Currently available for AI Pro and Ultra subs in the U.S.

You can now automate anything using Gemini in Chrome Just describe the task and that's it. - Nothing to configure - Works on tools without API - Fully integrated in Google's ecosystem And since 99% of tasks are now browser-based, there are no limits. Even if it's "slower than doing it manually" you can let it run in the background. Currently available for AI Pro and Ultra subs in the U.S.

Paul Couvert

49,528 views • 5 months ago

This should be illegal, and I'm not even kidding. How is this even possible?!? Developers have never had it this easy before. With this new Emergent AI agent (and Claude 4 integration), you can create fully functioning products with a prompt: 1. The front-end 2. The complete back-end 3. Bake an API, if you need it 4. 1-click deployment and integration with Stripe You can use this to clone entire websites or build complex applications without writing any code.

This should be illegal, and I'm not even kidding. How is this even possible?!? Developers have never had it this easy before. With this new Emergent AI agent (and Claude 4 integration), you can create fully functioning products with a prompt: 1. The front-end 2. The complete back-end 3. Bake an API, if you need it 4. 1-click deployment and integration with Stripe You can use this to clone entire websites or build complex applications without writing any code.

Santiago

99,577 views • 1 year ago