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.

Been quietly building a browser based live audiovisual studio app for commercial use in Framer It listens to your music, analyses it in real time, then turns the frequency into visuals, type, glitches, motion, scene changes, FX, and more. It’s node based. Connect audio, MIDI, visuals and behaviours together... show more

Lee Black

14,090 subscribers

14,040 views • 6 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Still relying on AI tools that can’t turn your ideas into real, working apps? Most can write code snippets but fall apart when it’s time to actually build something complete. That’s where Replit ⠕ changes everything. I simply asked it: “Build a responsive calculator app with a clean UI in light/dark mode.” Within minutes, it built the entire app with a beautiful UI, logic, light/dark mode, animations, and full responsiveness. Literally no setup. No debugging headache. Just vibe coding. Here’s why Replit stands out 👇 ✅ Build in Plain English: Just describe what you want and Replit turns it into a production-ready app. ✅ All-in-One Platform: Code, AI help, hosting, auth, and database, everything you need, already built in. ✅ Vibe Code Anywhere: Build on the go with the Replit mobile app for iOS & Android. ✅ Connected Ecosystem: Integrate with tools you already use like Notion, Slack, Google Drive, Dropbox, and more. ✅ Design to Live App: Import directly from Figma and bring your ideas to life in minutes. No micromanaging. No chaos. Just you, your idea, and Replit doing the heavy lifting. 👉 Try it now: 🎁 Get $10 credit when you purchase Replit Core via my referral link. → #Replit #VibeCoding #AIApps #NoCode #BuildWithReplit #AItools #ReplitCore

Still relying on AI tools that can’t turn your ideas into real, working apps? Most can write code snippets but fall apart when it’s time to actually build something complete. That’s where Replit ⠕ changes everything. I simply asked it: “Build a responsive calculator app with a clean UI in light/dark mode.” Within minutes, it built the entire app with a beautiful UI, logic, light/dark mode, animations, and full responsiveness. Literally no setup. No debugging headache. Just vibe coding. Here’s why Replit stands out 👇 ✅ Build in Plain English: Just describe what you want and Replit turns it into a production-ready app. ✅ All-in-One Platform: Code, AI help, hosting, auth, and database, everything you need, already built in. ✅ Vibe Code Anywhere: Build on the go with the Replit mobile app for iOS & Android. ✅ Connected Ecosystem: Integrate with tools you already use like Notion, Slack, Google Drive, Dropbox, and more. ✅ Design to Live App: Import directly from Figma and bring your ideas to life in minutes. No micromanaging. No chaos. Just you, your idea, and Replit doing the heavy lifting. 👉 Try it now: 🎁 Get $10 credit when you purchase Replit Core via my referral link. → #Replit #VibeCoding #AIApps #NoCode #BuildWithReplit #AItools #ReplitCore

Manish Kumar Shah

52,314 views • 9 months ago

Today, the future of IT support 𝘴𝘱𝘦𝘢𝘬𝘴 for itself! We’ve just launched Atomicwork’s Universal Agent, now available right from your browser with built-in Voice, Vision, Chat and Work AI capabilities! This isn’t just another update; it’s a revolutionary leap toward contextual, intelligent, real-time support. Atom understands what’s on your screen, listens to what you need, and guides you through tasks step by step. For years, IT support has meant navigating portals, raising tickets, and just waiting for help. @ Atom, the Universal Agent, changes that. It works where you work—in your browser, inside business apps you use at work like Salesforce or Jira to offer proactive and intuitive support with zero context-switching. 🗣️ Talks to you in natural language using Voice AI - Whether it’s fixing an access issue or fetching a sales report, just say it. Atom listens, responds, and walks you through the next-best actions in real time. 👁️ Sees what you can see using Vision AI – Finding it tough to explain what’s broken? Atom sees your screen, understands the issue you're facing and steps in to guide you. 💻 Works where you work using Work AI. The browser extension ensures that it’s available wherever you are and get help in whatever mode you prefer. This launch is just the beginning of a smarter, more seamless way to support employees and service teams alike. Support now can truly be accessed from anywhere, anytime! 💪 We can't wait for you to try out our Universal Agent for your varied enterprise support use cases 🚀 Sign up now to see it in action 🔗 🎦 Watch our team, Denin Siby, Bhavya Vats, Arkajit Datta, and Aishwarya 👾 Hariharan, take you through the core capabilities of the Universal Agent: . . . Vijay Rayapati Parsuram Vijayasankar Aparna Chugh Denin Siby Arkajit Datta

Today, the future of IT support 𝘴𝘱𝘦𝘢𝘬𝘴 for itself! We’ve just launched Atomicwork’s Universal Agent, now available right from your browser with built-in Voice, Vision, Chat and Work AI capabilities! This isn’t just another update; it’s a revolutionary leap toward contextual, intelligent, real-time support. Atom understands what’s on your screen, listens to what you need, and guides you through tasks step by step. For years, IT support has meant navigating portals, raising tickets, and just waiting for help. @ Atom, the Universal Agent, changes that. It works where you work—in your browser, inside business apps you use at work like Salesforce or Jira to offer proactive and intuitive support with zero context-switching. 🗣️ Talks to you in natural language using Voice AI - Whether it’s fixing an access issue or fetching a sales report, just say it. Atom listens, responds, and walks you through the next-best actions in real time. 👁️ Sees what you can see using Vision AI – Finding it tough to explain what’s broken? Atom sees your screen, understands the issue you're facing and steps in to guide you. 💻 Works where you work using Work AI. The browser extension ensures that it’s available wherever you are and get help in whatever mode you prefer. This launch is just the beginning of a smarter, more seamless way to support employees and service teams alike. Support now can truly be accessed from anywhere, anytime! 💪 We can't wait for you to try out our Universal Agent for your varied enterprise support use cases 🚀 Sign up now to see it in action 🔗 🎦 Watch our team, Denin Siby, Bhavya Vats, Arkajit Datta, and Aishwarya 👾 Hariharan, take you through the core capabilities of the Universal Agent: . . . Vijay Rayapati Parsuram Vijayasankar Aparna Chugh Denin Siby Arkajit Datta

Atomicwork

15,053 views • 1 year ago

I make games, and one of the hardest part is always the world. A map that feels real, coherent, alive. So I'm introducing Bmap. Draw a box anywhere on Earth, and it rebuilds that place as a clean 3D world: terrain, every street and building, the coast, the parks, the rivers. A real city, 1:1, in your browser, in seconds. But the map is just the first piece. Real cities are already the perfect game maps, the layout, the density, the logic of a place that actually works. Bmap's mission is to unlock them: take any real place and turn it into a living world you can shape and play in. The generator is live today. Where it goes next is the part I'm most excited about. 👀 It's free. Everyone who joined the waitlist is already in. New here? Sign in too and you're on the list, I'm opening the rest in waves. Building in public. Come watch real cities become worlds. →

I make games, and one of the hardest part is always the world. A map that feels real, coherent, alive. So I'm introducing Bmap. Draw a box anywhere on Earth, and it rebuilds that place as a clean 3D world: terrain, every street and building, the coast, the parks, the rivers. A real city, 1:1, in your browser, in seconds. But the map is just the first piece. Real cities are already the perfect game maps, the layout, the density, the logic of a place that actually works. Bmap's mission is to unlock them: take any real place and turn it into a living world you can shape and play in. The generator is live today. Where it goes next is the part I'm most excited about. 👀 It's free. Everyone who joined the waitlist is already in. New here? Sign in too and you're on the list, I'm opening the rest in waves. Building in public. Come watch real cities become worlds. →

Playda

14,785 views • 1 month ago

n8n vs cursor, building a keyword research workflow Plus I'll give you my code no strings attached... you can use my version, my code, or try to use the logic to build it as a node-based workflow...whatever! what you need: - firecrawl API key - perplexity API key - dataforseo API key goal: - input a URL - use Firecrawl to scrape the site - use Perplexity to generate seed keywords and understand the target market, competitors - use DataforSEO to research the keywords and associated data my process: 1) used claude code to build the n8n workflow to go from 0-1, then debug (still debugging after an hour) - structure was good but too many nodes and some errors. - debugging was a pain. building it manually would have taken a long time. - I much prefer natural language w/ an agent. 2) used claude code to just build a simple app where I input a couple API keys (working in 30 minutes) - a few tweaks during the testing process, mostly just around output formatting. - working from the first go, debugging was way easier. - I can easily expand on the functionality. - I have a simple and clean UX out of the gate, no need to use google docs, airtable, etc etc conclusion: OPTION 2 IS MUCH MORE EFFICIENT AND FUN. I've attached a video demo. I'm also going to share a link for you to test it, and the GitHub repo -- it's all yours!

n8n vs cursor, building a keyword research workflow Plus I'll give you my code no strings attached... you can use my version, my code, or try to use the logic to build it as a node-based workflow...whatever! what you need: - firecrawl API key - perplexity API key - dataforseo API key goal: - input a URL - use Firecrawl to scrape the site - use Perplexity to generate seed keywords and understand the target market, competitors - use DataforSEO to research the keywords and associated data my process: 1) used claude code to build the n8n workflow to go from 0-1, then debug (still debugging after an hour) - structure was good but too many nodes and some errors. - debugging was a pain. building it manually would have taken a long time. - I much prefer natural language w/ an agent. 2) used claude code to just build a simple app where I input a couple API keys (working in 30 minutes) - a few tweaks during the testing process, mostly just around output formatting. - working from the first go, debugging was way easier. - I can easily expand on the functionality. - I have a simple and clean UX out of the gate, no need to use google docs, airtable, etc etc conclusion: OPTION 2 IS MUCH MORE EFFICIENT AND FUN. I've attached a video demo. I'm also going to share a link for you to test it, and the GitHub repo -- it's all yours!

The Boring Marketer

33,377 views • 1 year ago

Mira Murati says the next AI interface is not a chatbot. It is a model that can listen, see, interrupt, and respond in real time. "The models that we work with today, they're very turn-based." "You talk, they talk, then they go off and think." "While they're thinking, it's almost like they're deaf and blind. They cannot perceive anything else about what's going on." Her new frame: interaction models. "They're not turn-based. They're more like time-based interaction." "They're continuously taking in audio, text, video, and continuously providing output." "We cut this up in chunks of 20 milliseconds... this enables you to catch things like interruptions and simultaneous speech." That is the product shift: from AI as a prompt box to AI as a high-bandwidth collaborator.

Mira Murati says the next AI interface is not a chatbot. It is a model that can listen, see, interrupt, and respond in real time. "The models that we work with today, they're very turn-based." "You talk, they talk, then they go off and think." "While they're thinking, it's almost like they're deaf and blind. They cannot perceive anything else about what's going on." Her new frame: interaction models. "They're not turn-based. They're more like time-based interaction." "They're continuously taking in audio, text, video, and continuously providing output." "We cut this up in chunks of 20 milliseconds... this enables you to catch things like interruptions and simultaneous speech." That is the product shift: from AI as a prompt box to AI as a high-bandwidth collaborator.

Karl Mehta

191,627 views • 1 month ago

🚨 Electrical engineers are going to hate this. Someone just turned React into a circuit board factory. Write code. Get a real PCB manufactured and delivered to your door. It's called tscircuit. React for Electronics. No Altium. No $10,000/year licenses. No 6-month learning curve. You write React components. But instead of and , you write , , and . The same way you build a website. That's how you build a circuit board now. Here's what this thing actually does: → Design real circuit boards using TypeScript and React → Edit code in your IDE, watch the circuit update in real time → Auto-generates schematics, PCB layouts, and 3D previews from your code → Automatic part selection and bill of materials generation → Built-in autorouting algorithm for PCB traces → Export to Gerber files and send directly to a manufacturer → Online playground. Design circuits in your browser right now. Here's the wildest part: The creator wrote 40 lines of TypeScript. From that he got a full PCB, a schematic, and a 3D preview. Then he exported it, sent it to a manufacturer, and got a real working circuit board delivered. 40 lines of code. A real physical product. This is free. Write React. Get hardware. $20K+ in bounties already paid to contributors. 8 years in the making. 100% Open Source. MIT License.

🚨 Electrical engineers are going to hate this. Someone just turned React into a circuit board factory. Write code. Get a real PCB manufactured and delivered to your door. It's called tscircuit. React for Electronics. No Altium. No $10,000/year licenses. No 6-month learning curve. You write React components. But instead of and , you write , , and . The same way you build a website. That's how you build a circuit board now. Here's what this thing actually does: → Design real circuit boards using TypeScript and React → Edit code in your IDE, watch the circuit update in real time → Auto-generates schematics, PCB layouts, and 3D previews from your code → Automatic part selection and bill of materials generation → Built-in autorouting algorithm for PCB traces → Export to Gerber files and send directly to a manufacturer → Online playground. Design circuits in your browser right now. Here's the wildest part: The creator wrote 40 lines of TypeScript. From that he got a full PCB, a schematic, and a 3D preview. Then he exported it, sent it to a manufacturer, and got a real working circuit board delivered. 40 lines of code. A real physical product. This is free. Write React. Get hardware. $20K+ in bounties already paid to contributors. 8 years in the making. 100% Open Source. MIT License.

Nav Toor

380,629 views • 4 months ago

how to use Google's NEW open source Design.md + AI Skills to make your startup look like a $100 million company in 1 hour: 1. Design.md is an open source file from Google that captures the soul of a design. Typography, colors, spacing, all in one markdown file. You attach it to your prompt and your agent builds beautiful things every time. 2. Think of it this way. The HTML is the finished dish. The design.md is the recipe. The skills are the ingredients. Put them together and everything you build looks consistent and professional. 3. Don't create a design system from scratch. Find a brand you love. Linear, Stripe, Vercel, whatever resonates. Study it. Use ChatGPT or Claude to help you extract the design language into your own design.md file. 4. Build skills on top of your design.md. A landing page skill. A mobile app skill. A motion design skill. A slide deck skill. Each one references the same design.md so everything looks like it came from the same designer. 5. The biggest mistake people make: they nail one screen and then everything else looks generic. Design.md solves this. One file keeps every page, every format, every medium consistent. 6. Use it across everything. Your landing page. Your app. Your pitch deck. Your promo videos. Same DNA. Same taste. Same system. That's what separates a startup that looks real from one that looks vibe-coded. 7. Build a second brain for design inspiration. When you see something beautiful in the real world or online, capture it. Save it. When you're building something new, reference it. Taste is developed, not downloaded. 8. It's obvious but the difference between a product people trust and a product people bounce from is how it looks and feels. Design.md gives you that edge. you can watch below shoutout to Meng To for coming on The Startup Ideas Podcast (SIP) 🧃 and walking through his full workflow. if you want to use AI to actually build gorgeous designs, you'll want to use see this. watch

GREG ISENBERG

508,512 views • 3 months ago

You don’t need a dev team anymore. You need one prompt. Zoer takes your idea and turns it into a fully working app, not just code, but a real product you can use. Here’s what it handles for you: • Database (already structured) • Backend (logic + APIs) • Frontend (clean, production-ready UI) • Auth (Google + email login) • Deployment (live in one click) Most AI tools stop at “here’s your code.” Zoer goes further: It builds the entire system and puts it live. From: “build me a CRM / SaaS / tool” To: A real, working product you can open, test, and share. Try it → No setup. No configs. No extra tools. This is what building should feel like in 2026.

You don’t need a dev team anymore. You need one prompt. Zoer takes your idea and turns it into a fully working app, not just code, but a real product you can use. Here’s what it handles for you: • Database (already structured) • Backend (logic + APIs) • Frontend (clean, production-ready UI) • Auth (Google + email login) • Deployment (live in one click) Most AI tools stop at “here’s your code.” Zoer goes further: It builds the entire system and puts it live. From: “build me a CRM / SaaS / tool” To: A real, working product you can open, test, and share. Try it → No setup. No configs. No extra tools. This is what building should feel like in 2026.

Tanvir

18,160 views • 3 months ago

Everyone is sleeping on MiniMax Agent. It's like Clawdbot + Claude Cowork + Agent Skills combined. But more polished. I tested it by feeding an AI paper and asking it to create a presentation. I expected something basic. The output was actually usable. Good structure, relevant visuals, clean export. Watch the demo below. But presentations are just the start. Here's what else you can do with it: - Deep research via search, browser use, and MCPs - Build Full-stack apps with auth, DB, and Stripe - Connect to GitHub, Figma, Slack out of the box - Custom MCPs for your specific workflows - Multimodal, supports videos, audio, and images Just describe what you need, and it gets it done for you. One feature I really liked is the ability to roll back and re-run from any step using checkpoint restore if you make a wrong turn. Link to download the desktop app in the next tweet.

Everyone is sleeping on MiniMax Agent. It's like Clawdbot + Claude Cowork + Agent Skills combined. But more polished. I tested it by feeding an AI paper and asking it to create a presentation. I expected something basic. The output was actually usable. Good structure, relevant visuals, clean export. Watch the demo below. But presentations are just the start. Here's what else you can do with it: - Deep research via search, browser use, and MCPs - Build Full-stack apps with auth, DB, and Stripe - Connect to GitHub, Figma, Slack out of the box - Custom MCPs for your specific workflows - Multimodal, supports videos, audio, and images Just describe what you need, and it gets it done for you. One feature I really liked is the ability to roll back and re-run from any step using checkpoint restore if you make a wrong turn. Link to download the desktop app in the next tweet.

Akshay 🚀

23,124 views • 6 months ago

Forget trying to design everything in Figma. You can build your own design tools with AI. Introducing Toolcraft - a starter kit and UI library for building beautiful creative apps. It's free and available for you today. npx @pixel-point/toolcraft create Use it to build apps to stylize images, create WebGL shaders, Three.js scenes, animations, photo editing tools, or whatever else needs a canvas and controls. Toolcraft gives you the full architecture in a single solution. It comes with: - plenty of UI components: sliders, pickers, timelines, curves, and more - built-in canvas, export, and toolbar setup - AI instructions to help the agent deliver a great result to you With Toolcraft, you don’t need an extensive prompt. Just explain what type of visuals you want to build, attach references, and wait. It’s been a game changer for our design process. Watch the full video on our YouTube channel with all the details and examples.

Forget trying to design everything in Figma. You can build your own design tools with AI. Introducing Toolcraft - a starter kit and UI library for building beautiful creative apps. It's free and available for you today. npx @pixel-point/toolcraft create Use it to build apps to stylize images, create WebGL shaders, Three.js scenes, animations, photo editing tools, or whatever else needs a canvas and controls. Toolcraft gives you the full architecture in a single solution. It comes with: - plenty of UI components: sliders, pickers, timelines, curves, and more - built-in canvas, export, and toolbar setup - AI instructions to help the agent deliver a great result to you With Toolcraft, you don’t need an extensive prompt. Just explain what type of visuals you want to build, attach references, and wait. It’s been a game changer for our design process. Watch the full video on our YouTube channel with all the details and examples.

Alex Barashkov

270,751 views • 1 month ago

Theo Von & Duncan Trussell just exposed algorithm mind control in real time: Public assassinations create massive cultural trauma → you disassociate in a foggy state → the algorithm immediately floods you with propaganda, “solutions,” and targeted ads (while your phone listens to your conversations). Duncan Trussell: “Public assassinations create trauma, cultural trauma. Charlie Kirk… everyone saw it before they shut it down. This produces trauma. The trauma response opens you up to conditioning. It’s the same shit kidnappers use… They freak you the fuck out so that you kind of disassociate… And then in that place, they show you the commercial. In that place, they give you some propaganda… This is a known technique for mind controlling people.” “Your phone is the f--ing vampire, and you’re inviting it in every time you stare at it.”

Theo Von & Duncan Trussell just exposed algorithm mind control in real time: Public assassinations create massive cultural trauma → you disassociate in a foggy state → the algorithm immediately floods you with propaganda, “solutions,” and targeted ads (while your phone listens to your conversations). Duncan Trussell: “Public assassinations create trauma, cultural trauma. Charlie Kirk… everyone saw it before they shut it down. This produces trauma. The trauma response opens you up to conditioning. It’s the same shit kidnappers use… They freak you the fuck out so that you kind of disassociate… And then in that place, they show you the commercial. In that place, they give you some propaganda… This is a known technique for mind controlling people.” “Your phone is the f--ing vampire, and you’re inviting it in every time you stare at it.”

Defiant Ghost

50,941 views • 1 month ago

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Santiago

46,142 views • 1 year ago

Last week-end I built a watercolor simulator based on real physics (as much as possible). A lot of you asked to play with it so i improved it and it's now live. New since the prototype: - More pigments (52), based on the best research out there to predict color mixes (Kubelka-Munk). - More luminous / glassy feel - Some fun experimental stuff like the salt and alcohol techniques to alter the texture, a backlight effect and a few more. - I also added a Code mode where the simulator prints its real function calls next to the sheet while you paint 🤓♥️ It's still largely based on the same physics model as my prototype: Curtis et al.'s "Computer-Generated Watercolor". All in the browser. Current status: building and implementing a kid-friendly version for Marble App. Plenty of awesome things to learn with watercolor painting!

Last week-end I built a watercolor simulator based on real physics (as much as possible). A lot of you asked to play with it so i improved it and it's now live. New since the prototype: - More pigments (52), based on the best research out there to predict color mixes (Kubelka-Munk). - More luminous / glassy feel - Some fun experimental stuff like the salt and alcohol techniques to alter the texture, a backlight effect and a few more. - I also added a Code mode where the simulator prints its real function calls next to the sheet while you paint 🤓♥️ It's still largely based on the same physics model as my prototype: Curtis et al.'s "Computer-Generated Watercolor". All in the browser. Current status: building and implementing a kid-friendly version for Marble App. Plenty of awesome things to learn with watercolor painting!

Lionel Mora

272,943 views • 5 days ago

New short course: Practical Multi AI Agents and Advanced Use Cases with crewAI. Learn to build and deploy advanced agent-based systems in real applications in this course, created with CrewAI and taught by its founder, João Moura! (Disclosure: I've made a small seed investment in CrewAI.) In this course, you’ll learn how to create advanced agent-based apps that use external tools, do performance testing, can be trained with human feedback, and perform multiple tasks with different large language models. You will build several practical agentic apps that provide real business value, such as an automated project planning system, lead scoring and engagement pipeline, customer support data analysis, and a robust content creation system. In detail, you will learn how to: - Create these multi-agent systems with the building blocks of tasks, agents, and crews, along with the different things that make them work, such as caching, memory, and guardrails. - Integrate your multi-agent application with internal and external systems. - Connect multiple agents in complex setups, including parallel, sequential, and hybrid configurations, and create flows involving multiple agentic applications working together. - Test your agentic workflow and train it using human feedback to optimize its performance for better and more consistent results. - Work with multiple LLMs in your multi-agent system, using the appropriate model sizes and providers to fit each agent’s specific task. - Start a project from scratch in your environment and prepare it for deployment. You’ll also learn from an interview between João and Jacob Wilson, the Commercial GenAI Principal at PwC , in which they discuss deploying agentic workflows in real industry use cases. By the end of this course, you will be equipped to start building custom multi-agentic systems for your work. Please sign up here!

New short course: Practical Multi AI Agents and Advanced Use Cases with crewAI. Learn to build and deploy advanced agent-based systems in real applications in this course, created with CrewAI and taught by its founder, João Moura! (Disclosure: I've made a small seed investment in CrewAI.) In this course, you’ll learn how to create advanced agent-based apps that use external tools, do performance testing, can be trained with human feedback, and perform multiple tasks with different large language models. You will build several practical agentic apps that provide real business value, such as an automated project planning system, lead scoring and engagement pipeline, customer support data analysis, and a robust content creation system. In detail, you will learn how to: - Create these multi-agent systems with the building blocks of tasks, agents, and crews, along with the different things that make them work, such as caching, memory, and guardrails. - Integrate your multi-agent application with internal and external systems. - Connect multiple agents in complex setups, including parallel, sequential, and hybrid configurations, and create flows involving multiple agentic applications working together. - Test your agentic workflow and train it using human feedback to optimize its performance for better and more consistent results. - Work with multiple LLMs in your multi-agent system, using the appropriate model sizes and providers to fit each agent’s specific task. - Start a project from scratch in your environment and prepare it for deployment. You’ll also learn from an interview between João and Jacob Wilson, the Commercial GenAI Principal at PwC , in which they discuss deploying agentic workflows in real industry use cases. By the end of this course, you will be equipped to start building custom multi-agentic systems for your work. Please sign up here!

Andrew Ng

341,204 views • 1 year ago

AI will replace the chrome in the coming year 🤯 Meet Neo by Norton Neo Browser — the first AI-native browser that doesn’t just open tabs… it thinks with you. You’re not searching anymore. You’re collaborating. Neo reads what’s on your screen, summarizes it instantly, and tells you what to do next. It understands context — your tasks, your flow, your intent. No more bouncing between Google and ChatGPT. Neo merges them into one seamless workspace where you ask, explore, and act in real time. It plugs into your apps too — turns your emails into to-dos, meetings into reminders, research into insight. And because it’s built by Norton, the global cybersecurity giant, it’s smarter, safer, and ad-free. This isn’t just a browser. It’s your intelligent co-pilot for the internet. Welcome to the future of browsing. Smarter. Safer. Simpler. 👉 Join the waitlist:

AI will replace the chrome in the coming year 🤯 Meet Neo by Norton Neo Browser — the first AI-native browser that doesn’t just open tabs… it thinks with you. You’re not searching anymore. You’re collaborating. Neo reads what’s on your screen, summarizes it instantly, and tells you what to do next. It understands context — your tasks, your flow, your intent. No more bouncing between Google and ChatGPT. Neo merges them into one seamless workspace where you ask, explore, and act in real time. It plugs into your apps too — turns your emails into to-dos, meetings into reminders, research into insight. And because it’s built by Norton, the global cybersecurity giant, it’s smarter, safer, and ad-free. This isn’t just a browser. It’s your intelligent co-pilot for the internet. Welcome to the future of browsing. Smarter. Safer. Simpler. 👉 Join the waitlist:

Hamza Khalid

90,523 views • 10 months ago

We just shipped a completely new concept for web interaction. Live on three․ws, we are thrilled to showcase this demo of persistent, interactive 3D AI Agents that live right in your browser. As the first mover in this space, we are achieving what hasn't been done before: seamlessly bridging the gap between traditional flat web pages and fully immersive, spatial 3D environments. We are fundamentally shifting how humans experience the internet. Here's how. Intelligent AI Agents. Your 3D companion drops right into the screen, tracks your cursor, and interacts with you based on the exact page you are viewing. Context-Aware Guide. Knows exactly where visitors are. It can point out and encourage clicks on the most important parts of a site. Highly Interactive. Turns to follow your cursor in real-time, waves when you navigate, and idles naturally. Playground Mode. Click your avatar and it seamlessly detaches into a full-page 3D stroll or platformer right in the browser. Use keyboard arrows on desktop and joystick on mobile. Choose Your Avatar. Pick exactly who walks the web with you from a fully customizable, hot-swappable roster. Polite & Lightweight. Built with smart compression and shared animation files. It monitors browser memory to guarantee zero slowdowns and respects "reduced motion" accessibility settings. Flat websites will be gone before you know it. The future is interactive, the future is intelligent. It's time to break AI out the chatbox. three․ws

three.ws

22,706 views • 1 month ago

this one was built over time, through patience, persistence, and purpose. from late night studio sessions to the quiet in between, we were there throughout the process, watching an idea turn into something real. this project taught me patience in a different way… trusting timing, staying locked in through the unseen hours, and understanding that not everything needs to be rushed to be powerful. it taught me vision, and what it means to build something that lasts. m$ney is more than music to me. it’s growth, it’s sacrifice, it’s understanding that real wealth goes beyond what you see. MR M$NEY your sound, your intention, your discipline… is different. thank you for bringing me this close to the journey. seeing it all unfold is something i’ll never take for granted. to everyone who poured into this, thank you. this one means something. m$ney out now.

this one was built over time, through patience, persistence, and purpose. from late night studio sessions to the quiet in between, we were there throughout the process, watching an idea turn into something real. this project taught me patience in a different way… trusting timing, staying locked in through the unseen hours, and understanding that not everything needs to be rushed to be powerful. it taught me vision, and what it means to build something that lasts. m$ney is more than music to me. it’s growth, it’s sacrifice, it’s understanding that real wealth goes beyond what you see. MR M$NEY your sound, your intention, your discipline… is different. thank you for bringing me this close to the journey. seeing it all unfold is something i’ll never take for granted. to everyone who poured into this, thank you. this one means something. m$ney out now.

ᵀᴬ

70,770 views • 3 months ago

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

The Peel

51,632 views • 5 months ago