Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Prediction: You’ll soon control everything from one interface 🔥 Opening different apps for different tasks feels super old school. Instead, you’ll have one interface to send emails, book flights, shop, and trigger countless services from. The apps themselves won’t disappear, but their interfaces will. Recently, I’ve been using several... agents entirely through a chat. The interface is almost nonexistent, or “invisible,” you could say. But the underlying technology is more powerful than ever. Using a text interface alone won’t be enough. So I built one that is more dynamic, fluid, and visual. Here, the chat becomes the control layer, while “dynamic widgets” appear whenever you need them and disappear when the task is done. In this example, I ask my agent to plan my upcoming Japan trip, and several visual elements appear with options, prices, and dates. They help me make a decision and then get out of the way. Super easy and seamless to use. I don't think I'll ever go back to using overloaded booking platforms. And this goes far beyond travel. Instead of adapting to hundreds of different interfaces, the interface will adapt to whatever you’re trying to do. The future of interfaces is a persistent conversation surrounded by temporary, dynamic components.show more

Felix Haas

19,171 subscribers

71,118 Aufrufe • vor 1 Monat •via X (Twitter)

Wissenschaft & Technologie Bildung Reisen

Anya Rossi• Live Now

Private livecam show

40 Kommentare

Profilbild von Max Ropohl

Max Ropohlvor 1 Monat

I think it’s gonna be a mix of conversational like in your example and this

Profilbild von Felix Haas

Felix Haasvor 1 Monat

yeah love this

Profilbild von VeWorld.ai

VeWorld.aivor 1 Monat

We’ve been thinking a lot about what the interface for agents should actually look like, and persistent conversation + temporary UI feels much closer to the right abstraction than forcing every task into a fixed app experience. Mobile is probably where this becomes obvious first.

Profilbild von Felix Haas

Felix Haasvor 1 Monat

yes!

Profilbild von Eduard

Eduardvor 1 Monat

clean!

Profilbild von Felix Haas

Felix Haasvor 1 Monat

ty!

Profilbild von Ben Blumenrose

Ben Blumenrosevor 1 Monat

i think this is true for some tasks but like for email as an example - i could see a tool that summarizes and then lets me drill down to individual emails so it's not email as we know it today but still a more robust interface than just chat. So i think true for some tasks but there is still a category of work that will require a more robust interface i think than just chat with embedded "widgets" no?

Profilbild von Felix Haas

Felix Haasvor 1 Monat

yeah it’s quite interesting. Personally I haven’t opened Superhuman since I started working with my agents. They just ping me when something important comes in and take care of sorting, replies etc. I mainly use my chat interface to read and approve.

Profilbild von Ben Blumenrose

Ben Blumenrosevor 1 Monat

dang - how many emails a day do you do this with? All with grok bot? i'd be curious to try it as i just can't imagine that being faster + maintaining quality

Profilbild von Salesforce

Salesforcevor 1 Monat

Ok, this is very cool. And, you know, enterprise software is trending in the same direction: people choose the interface they want, whether that's a single chat for everything, a command line, or something like... Slack. 😌

Profilbild von vasanth

vasanthvor 1 Monat

That's the interstellar moment, we are moving towards. 😎

Profilbild von Felix Haas

Felix Haasvor 1 Monat

lfg

Profilbild von Andrey

Andreyvor 1 Monat

@kai_brokering this looks awfully similar

Profilbild von Alhwyn

Alhwynvor 1 Monat

Bullish on iMessage extensions

Profilbild von Siddharth Jaiswal

Siddharth Jaiswalvor 1 Monat

I needed this, taking as design input :)

Profilbild von Laura Modiano

Laura Modianovor 1 Monat

prediction on point

Profilbild von Walker

Walkervor 1 Monat

chat isn't really that optimal, ui is nice bc i don't have to memorize every small feature i want to use

Profilbild von Ritten

Rittenvor 1 Monat

It should be an operating system level , like gnome-shell

Profilbild von steve

stevevor 1 Monat

no thanks

Profilbild von Breana Patel

Breana Patelvor 1 Monat

China did this long time back with WeChat super app.

Profilbild von Rob Phillips

Rob Phillipsvor 1 Monat

Clean! We did this 10+ yrs ago on Viv and doing parts of this already using dynamic, native UI on Agree re: one orchestrator / interface to rule them all Happy to chat

Profilbild von Alex

Alexvor 1 Monat

looks like @interfaceclub

Profilbild von Rob Swift

Rob Swiftvor 1 Monat

I'll raise you that you'll control everything from 2 interfaces. Visual chat and voice chat.

Profilbild von Shane Brown

Shane Brownvor 1 Monat

Just have to say, if you are in Tokyo, there are some communities that would love to collaborate with you here.

Profilbild von Bo Brainerd

Bo Brainerdvor 1 Monat

Agreed

Profilbild von Prajwal

Prajwalvor 1 Monat

Conversation is definitely not a perfect ux for shopping

Profilbild von Niklas Weber

Niklas Webervor 1 Monat

with you, just think keyboard shortcuts need to be part of that prediction as well

Profilbild von Nav

Navvor 1 Monat

lowk, i just use @AsideAI for everything

Profilbild von Doron Katz

Doron Katzvor 1 Monat

@grok does Skyscanner have an MCP server

Profilbild von Kyle G

Kyle Gvor 1 Monat

Love your minimalist approach and visual design. But with travel, users often want to compare many options because preferences vary so much. How do you keep it this simple without narrowing the choices too early?

Profilbild von Marco Ancona

Marco Anconavor 1 Monat

I like this hybrid, but I wonder if widgets will be enough for all use cases. Just seeing my calendar there would be hard, all squashed in little spaces. Editing an email (assuming I want some human touch in it) also hard in a tiny widget

Profilbild von John Savage

John Savagevor 1 Monat

You don’t want to work at lovable anymore eh

Profilbild von Francis

Francisvor 1 Monat

Basically, the intent-based UI isn't? We're getting closer every day.

Profilbild von Sreeram Garlapati

Sreeram Garlapativor 1 Monat

the idea of interfaces appearing only when you need them feels much closer to how AI should actually work.

Profilbild von Daniel Ek / Chairman 🇸🇪 @spotify / parody

Daniel Ek / Chairman 🇸🇪 @spotify / parodyvor 1 Monat

voice for everything?

Profilbild von ModelCaddy

ModelCaddyvor 1 Monat

Agreed! This is the #OpenAI dream for their super app. I think everyone will want that - but @Apple controls the OS so they will be the ones to actually make it happen... The new #SiriAI takes more steps towards that. We built our app towards that future.

Profilbild von John Helmuth

John Helmuthvor 1 Monat

Looks looks like new Siri’s interface. Maybe they’re onto something.

Profilbild von Aron k

Aron kvor 1 Monat

It’s already happening…

Profilbild von Ralph Theodori

Ralph Theodorivor 1 Monat

Agreed

Profilbild von S

Svor 1 Monat

Be careful with your trip. I almost trusted the model, I searched after and it almost totally screwed me over. Wrong airports, weird connections, timing on trips wrong.

Ähnliche Videos

"I do not think a chatbot is the right interface for travel or e-commerce." - Brian Chesky "I think the future is not apps. The future is agents, but I don't think they're going to be text-forward. I think they're going to be really rich user interfaces." "Imagine using iMessage to do everything, when in fact every other app has a unique interface." "With e-commerce, you want a very rich user interface. It would be agentic. You can have a conversation with it, but the point is that it has to be more visual."

"I do not think a chatbot is the right interface for travel or e-commerce." - Brian Chesky "I think the future is not apps. The future is agents, but I don't think they're going to be text-forward. I think they're going to be really rich user interfaces." "Imagine using iMessage to do everything, when in fact every other app has a unique interface." "With e-commerce, you want a very rich user interface. It would be agentic. You can have a conversation with it, but the point is that it has to be more visual."

TBPN

655,131 Aufrufe • vor 5 Monaten

In my CNBC interview, Jon Fortt asked what happens to SaaS in an AI-agent world. I’ll be bold: the way we work and interact with compute is about to change. We’re moving from apps to agents. From dashboards to prompts. From human workflows to autonomous orchestration. At HUMAIN , we’re building this now. HUMAIN OS (to be revealed at LEAP) and HUMAIN ONE reimagine the enterprise when AI agents become the primary interface. You can’t deploy agents and keep legacy processes. SaaS won’t disappear overnight, but many will become obsolete interfaces.

In my CNBC interview, Jon Fortt asked what happens to SaaS in an AI-agent world. I’ll be bold: the way we work and interact with compute is about to change. We’re moving from apps to agents. From dashboards to prompts. From human workflows to autonomous orchestration. At HUMAIN , we’re building this now. HUMAIN OS (to be revealed at LEAP) and HUMAIN ONE reimagine the enterprise when AI agents become the primary interface. You can’t deploy agents and keep legacy processes. SaaS won’t disappear overnight, but many will become obsolete interfaces.

Tareq Amin

16,199 Aufrufe • vor 8 Monaten

Airbnb CEO Brian Chesky says the chatbot is a "pre-AI interface," rather than the end-state interface for artificial intelligence: "We're in the MS-DOS phase of AI." "The future AI interface will have a reference to chat, but it's probably going to be much more visual. Most people aren't completely text-based." "The chatbot is really a pre-AI interface that we've plugged onto this incredibly powerful engine." "I really think the models are even more powerful than people realize, because we have hardly harnessed them." From Brian Chesky's January 2025 appearance on the show.

Airbnb CEO Brian Chesky says the chatbot is a "pre-AI interface," rather than the end-state interface for artificial intelligence: "We're in the MS-DOS phase of AI." "The future AI interface will have a reference to chat, but it's probably going to be much more visual. Most people aren't completely text-based." "The chatbot is really a pre-AI interface that we've plugged onto this incredibly powerful engine." "I really think the models are even more powerful than people realize, because we have hardly harnessed them." From Brian Chesky's January 2025 appearance on the show.

TBPN

31,493 Aufrufe • vor 7 Monaten

a16z's Anish Acharya on why consumer AI is where the iPhone was in 2010, and the three reasons the biggest companies in the category haven't been built yet: "What's held us back is three things. One is that the models have been expensive, so if you want to do a free-to-use product, that hasn't been easy." "The second is that we've kind of had an interface problem. Chat makes sense if you're the highest agency person in the world, which is Elon and Sam. But for the average consumer, their ideal interface is TikTok. So we need to find something between chat and TikTok." "And then the technology has been so much more focused on productivity than things like human connection and entertainment." "All those things are up for grabs. The open weight models mean things are way cheaper... Founders like Eugenia Kuyda are thinking really ambitiously about user interfaces, Brian Chesky from Airbnb started a foundation lab focused on next-gen user interfaces." "I think all of those problems will get solved, or they're at least in a better position to be solved than they were two years ago." Anish Acharya w/ Lenny Rachitsky

a16z's Anish Acharya on why consumer AI is where the iPhone was in 2010, and the three reasons the biggest companies in the category haven't been built yet: "What's held us back is three things. One is that the models have been expensive, so if you want to do a free-to-use product, that hasn't been easy." "The second is that we've kind of had an interface problem. Chat makes sense if you're the highest agency person in the world, which is Elon and Sam. But for the average consumer, their ideal interface is TikTok. So we need to find something between chat and TikTok." "And then the technology has been so much more focused on productivity than things like human connection and entertainment." "All those things are up for grabs. The open weight models mean things are way cheaper... Founders like Eugenia Kuyda are thinking really ambitiously about user interfaces, Brian Chesky from Airbnb started a foundation lab focused on next-gen user interfaces." "I think all of those problems will get solved, or they're at least in a better position to be solved than they were two years ago." Anish Acharya w/ Lenny Rachitsky

a16z

37,517 Aufrufe • vor 1 Monat

I see a lot of negative feedback about Apple’s new UI updates. But you are missing the point. It’s not about glass effects or making every UI element transparent / shiny. It’s about liquidity, depth, and movement. UI that feels alive. We are entering a new era of interface design. What was once static, flat, and fixed is becoming dynamic, adaptive, dimensional. Flat design is over. And flat screens will be too. Sooner than you think. I think Apple’s new UI system is less about a visual update. It’s the first real step toward multimodal interfaces. Where components aren’t bound to a rigid screen but float, shift, and respond. They appear where you need them, and disappear where you don’t. It’s about removing unnecessary clutter and making human-computer interaction feel… well, more human. Just because we’ve spent the last decade staring at opaque UI components doesn’t mean it’s the optimal way to interact with computers. Sure, it’s not perfect, but it’s the first real step into a new era of UI. The future is screenless. And dynamic components are the new screens.

I see a lot of negative feedback about Apple’s new UI updates. But you are missing the point. It’s not about glass effects or making every UI element transparent / shiny. It’s about liquidity, depth, and movement. UI that feels alive. We are entering a new era of interface design. What was once static, flat, and fixed is becoming dynamic, adaptive, dimensional. Flat design is over. And flat screens will be too. Sooner than you think. I think Apple’s new UI system is less about a visual update. It’s the first real step toward multimodal interfaces. Where components aren’t bound to a rigid screen but float, shift, and respond. They appear where you need them, and disappear where you don’t. It’s about removing unnecessary clutter and making human-computer interaction feel… well, more human. Just because we’ve spent the last decade staring at opaque UI components doesn’t mean it’s the optimal way to interact with computers. Sure, it’s not perfect, but it’s the first real step into a new era of UI. The future is screenless. And dynamic components are the new screens.

Felix Haas

654,078 Aufrufe • vor 1 Jahr

.Amjad Masad : Creating software is going to be one of the most exciting areas. The average person will soon be as capable as what a senior software engineer is today, as we shift from doing the work to directing it. Instead of coding line by line, you’ll run multiple agents in parallel, building the frontend, refactoring the database, shipping features, all in the background. On top of that, you’ll have a clean interface to design and interact with AI more creatively. Software creation is moving from execution to orchestration, and soon, it won’t be a specialised skill, it’ll be the baseline.

.Amjad Masad : Creating software is going to be one of the most exciting areas. The average person will soon be as capable as what a senior software engineer is today, as we shift from doing the work to directing it. Instead of coding line by line, you’ll run multiple agents in parallel, building the frontend, refactoring the database, shipping features, all in the background. On top of that, you’ll have a clean interface to design and interact with AI more creatively. Software creation is moving from execution to orchestration, and soon, it won’t be a specialised skill, it’ll be the baseline.

Extraordinary

19,743 Aufrufe • vor 7 Monaten

Akshay Nathan reveals OpenAI power voice users have six different mics on their desks to talk to Codex all day "I think the one to to call out, like I think the, this is one where like you see early adopters so far ahead of the curve of everyone else." "Like when I walk around the office I see some people with like six different mics on their desk and that's what they use to communicate with, you know, Codex or ChatGPT work all day. But that's clearly not made it out to everyone." "And I think part of that is, you know, the product needs to do a much better job of people discovering that this capability even exists. Part of it is like we need to bring people along on like changing from, you know, typing or tapping to like speaking and like how much more fluid and frictionless that is as an interface."

Akshay Nathan reveals OpenAI power voice users have six different mics on their desks to talk to Codex all day "I think the one to to call out, like I think the, this is one where like you see early adopters so far ahead of the curve of everyone else." "Like when I walk around the office I see some people with like six different mics on their desk and that's what they use to communicate with, you know, Codex or ChatGPT work all day. But that's clearly not made it out to everyone." "And I think part of that is, you know, the product needs to do a much better job of people discovering that this capability even exists. Part of it is like we need to bring people along on like changing from, you know, typing or tapping to like speaking and like how much more fluid and frictionless that is as an interface."

Fireside Alpha

83,293 Aufrufe • vor 20 Tagen

Anthropic's in trouble, again! They spent years building what's now fully open-source. What made Claude feel different from a normal app is that the agent could act inside the interface instead of only talking in a chat box. For instance, Claude Artifacts let an agent render real UI, charts, dashboards, and interactive components that assemble live inside the response. Every major AI product tried to replicate it. But the problem was that unlike reasoning, planning, tool-calling, etc., none of it shipped natively with LangGraph, CrewAI, or Google ADK. So teams started building an owned version that required engineering the entire interface layer from scratch. Most teams, however, just settled for shipping the agent as a backend API in a chat box since rendering the UI is only one piece of it. To actually make it work, the interface layer also needed real-time streaming, state kept in sync between agent and UI, conversations that persist across sessions, and reconnection when a user refreshes mid-run. CopilotKit🪁 is now the only open-source framework that actually lets you build your own full-stack Claude-like apps. It decouples the agent from the interface, talking over AG-UI (an open protocol for agent-to-user communication). Being a standard protocol, the frontend never needs to know whether it is talking to a LangGraph or a CrewAI agent. You can change the backend anytime and the UI will never notice. In practice, CopilotKit's interface layer gives several pre-implemented React building blocks that wire the agent directly into the app, like: - generative UI, so the agent renders real components instead of text - chat windows, sidebars, and popups, or a fully headless setup - shared state, so the agent and app stay in sync - human-in-the-loop approvals, where the agent waits before acting - persistent threads that store the whole session, including the agent-user interactions and generated UI, not just text And because that full history is captured, those interactions can feed a self-learning layer that also improves the agent from real usage over time. The interface layer that Anthropic spent years engineering in-house is now literally available to any developer/team. CopilotKit is open-source with 30k+ GitHub stars, and AG-UI, the protocol underneath, is already supported across every major agent framework: LangGraph, CrewAI, Mastra, Google ADK, and more. CopilotKit GitHub repo → (don't forget to star it ⭐ ) If you want to go deeper, I found a detailed breakdown by Shubham Saboo recently on the three Generative UI patterns, with implementation. Read it below.

Anthropic's in trouble, again! They spent years building what's now fully open-source. What made Claude feel different from a normal app is that the agent could act inside the interface instead of only talking in a chat box. For instance, Claude Artifacts let an agent render real UI, charts, dashboards, and interactive components that assemble live inside the response. Every major AI product tried to replicate it. But the problem was that unlike reasoning, planning, tool-calling, etc., none of it shipped natively with LangGraph, CrewAI, or Google ADK. So teams started building an owned version that required engineering the entire interface layer from scratch. Most teams, however, just settled for shipping the agent as a backend API in a chat box since rendering the UI is only one piece of it. To actually make it work, the interface layer also needed real-time streaming, state kept in sync between agent and UI, conversations that persist across sessions, and reconnection when a user refreshes mid-run. CopilotKit🪁 is now the only open-source framework that actually lets you build your own full-stack Claude-like apps. It decouples the agent from the interface, talking over AG-UI (an open protocol for agent-to-user communication). Being a standard protocol, the frontend never needs to know whether it is talking to a LangGraph or a CrewAI agent. You can change the backend anytime and the UI will never notice. In practice, CopilotKit's interface layer gives several pre-implemented React building blocks that wire the agent directly into the app, like: - generative UI, so the agent renders real components instead of text - chat windows, sidebars, and popups, or a fully headless setup - shared state, so the agent and app stay in sync - human-in-the-loop approvals, where the agent waits before acting - persistent threads that store the whole session, including the agent-user interactions and generated UI, not just text And because that full history is captured, those interactions can feed a self-learning layer that also improves the agent from real usage over time. The interface layer that Anthropic spent years engineering in-house is now literally available to any developer/team. CopilotKit is open-source with 30k+ GitHub stars, and AG-UI, the protocol underneath, is already supported across every major agent framework: LangGraph, CrewAI, Mastra, Google ADK, and more. CopilotKit GitHub repo → (don't forget to star it ⭐ ) If you want to go deeper, I found a detailed breakdown by Shubham Saboo recently on the three Generative UI patterns, with implementation. Read it below.

Avi Chawla

461,550 Aufrufe • vor 4 Monaten

Standard Intelligence's devansh responds to roon's tweet that "text is the universal interface," and explains why their new foundation model is trained on video: "At some point in the arbitrarily long future, if we only use text models, we could force most things to be text. But I think there are just a lot of things that are much more native when done from a computer-use [perspective]." "GUIs are designed for humans to use. We have this massive long tail of things on the internet that are entirely undoable by LLMs." "For example, when I do ML engineering most of my time is spent doing the grunt work of engineering. It's a lot of looking at graphs, analyzing, and comparing loss curves. You can do this in text, but it's a much larger pain than doing it in the native interface." "There's a reason humans don't interact with a computer purely through text, it would kind of suck."

Standard Intelligence's devansh responds to roon's tweet that "text is the universal interface," and explains why their new foundation model is trained on video: "At some point in the arbitrarily long future, if we only use text models, we could force most things to be text. But I think there are just a lot of things that are much more native when done from a computer-use [perspective]." "GUIs are designed for humans to use. We have this massive long tail of things on the internet that are entirely undoable by LLMs." "For example, when I do ML engineering most of my time is spent doing the grunt work of engineering. It's a lot of looking at graphs, analyzing, and comparing loss curves. You can do this in text, but it's a much larger pain than doing it in the native interface." "There's a reason humans don't interact with a computer purely through text, it would kind of suck."

TBPN

64,699 Aufrufe • vor 7 Monaten

.Anish Acharya says the future of AI isn’t one model to rule them all—and explains why platforms that integrate multiple models will benefit the most: "I think we're going to need and rely on all of the models." "It's sort of like if you have a team of people... if you have five people, they could all do a basic set of things pretty capably." "But then they all have their specializations. Maybe one of them is really good at closing a customer who doesn't want to sign the deal, and one of them is really good at culture and getting the best out of the team." "There are some areas in which they are going to build apps, and that will be a threat to app companies. But there are many areas in which app companies are advantaged. Cursor and Krea are great examples of this—products where you benefit from being multi-model." "When you actually use a creative tool, you don't want to just use Nano Banana, you want to have access to OpenAI, Nano Banana, Kling—all of them—Qwen, you name it. So using a single interface to access all the models is powerful." Anish Acharya on BILLIONS with Guillaume Moubeche

.Anish Acharya says the future of AI isn’t one model to rule them all—and explains why platforms that integrate multiple models will benefit the most: "I think we're going to need and rely on all of the models." "It's sort of like if you have a team of people... if you have five people, they could all do a basic set of things pretty capably." "But then they all have their specializations. Maybe one of them is really good at closing a customer who doesn't want to sign the deal, and one of them is really good at culture and getting the best out of the team." "There are some areas in which they are going to build apps, and that will be a threat to app companies. But there are many areas in which app companies are advantaged. Cursor and Krea are great examples of this—products where you benefit from being multi-model." "When you actually use a creative tool, you don't want to just use Nano Banana, you want to have access to OpenAI, Nano Banana, Kling—all of them—Qwen, you name it. So using a single interface to access all the models is powerful." Anish Acharya on BILLIONS with Guillaume Moubeche

a16z

33,300 Aufrufe • vor 7 Monaten

Sam Altman thinks OpenAI should be a platform, not a product company: "What I think most people want is the single interface to their own personal or their company's AGI that can kinda help them with whatever they need, and then the ability with an API to build anything they want on top of it." "That is the platform that we should offer to the world." "I don't think we should go build every product category. I don't think we should go try to compete with all of our customers. I don't think we should try to subsume the entire economy." "I think we should offer this platform and try to have a hundred million new businesses and eight billion people use it in all kinds of new ways." "So one kind of direct interface to the product, one API for people to use however they want. Those eventually come more and more together too, and then it's all about what people do with it, build on top of it." Sam Altman w/ David Senra

Sam Altman thinks OpenAI should be a platform, not a product company: "What I think most people want is the single interface to their own personal or their company's AGI that can kinda help them with whatever they need, and then the ability with an API to build anything they want on top of it." "That is the platform that we should offer to the world." "I don't think we should go build every product category. I don't think we should go try to compete with all of our customers. I don't think we should try to subsume the entire economy." "I think we should offer this platform and try to have a hundred million new businesses and eight billion people use it in all kinds of new ways." "So one kind of direct interface to the product, one API for people to use however they want. Those eventually come more and more together too, and then it's all about what people do with it, build on top of it." Sam Altman w/ David Senra

a16z

61,993 Aufrufe • vor 20 Tagen

AI power users are here and the case for agent-friendly software is materializing. Aaron Levie on agents outnumbering people 1000x: "If you start to imagine that we all have to build software for agents… we spend as much time now thinking about the agent interface to our tool as we do the human interface." "If you have a hundred or a thousand times more agents than people, then your software has to be built for agents… it's going to be through an API or a CLI or MCP." "What if you give a coding agent access to your SaaS tools and a coding agent access to your knowledge work, workflows and context?" "It can actually code its way or use APIs through whatever task it's trying to achieve." "That appears to be like a paradigm that is starting to compound… and I actually think it kind of makes sense as the ultimate manifestation of this stuff." Aaron Levie

AI power users are here and the case for agent-friendly software is materializing. Aaron Levie on agents outnumbering people 1000x: "If you start to imagine that we all have to build software for agents… we spend as much time now thinking about the agent interface to our tool as we do the human interface." "If you have a hundred or a thousand times more agents than people, then your software has to be built for agents… it's going to be through an API or a CLI or MCP." "What if you give a coding agent access to your SaaS tools and a coding agent access to your knowledge work, workflows and context?" "It can actually code its way or use APIs through whatever task it's trying to achieve." "That appears to be like a paradigm that is starting to compound… and I actually think it kind of makes sense as the ultimate manifestation of this stuff." Aaron Levie

a16z

42,152 Aufrufe • vor 1 Monat

Satya Nadella says the next AI interface is not chat. It is the control room for 100 agents working overnight under your delegated authority. "Coding has worked so well that we now have to rebuild the IDE." "Oh my god, I have these 100 agent sessions. The cognitive load it transfers back to me as a human is so excessive that now I need a new UI." "The chat as the only artifact is also impossible. So that's why we need a canvas." Then he gives the enterprise version: "All through the night there was a bunch of stuff that all these autopilots that I have working on my behalf with my delegated authority did." And the operator question becomes: "What did you do? Did I do this work?" The real bottleneck is not whether agents can generate more tasks. It is whether humans get the interface, memory, permissions, and audit trail to safely manage 100 delegated workers.

Satya Nadella says the next AI interface is not chat. It is the control room for 100 agents working overnight under your delegated authority. "Coding has worked so well that we now have to rebuild the IDE." "Oh my god, I have these 100 agent sessions. The cognitive load it transfers back to me as a human is so excessive that now I need a new UI." "The chat as the only artifact is also impossible. So that's why we need a canvas." Then he gives the enterprise version: "All through the night there was a bunch of stuff that all these autopilots that I have working on my behalf with my delegated authority did." And the operator question becomes: "What did you do? Did I do this work?" The real bottleneck is not whether agents can generate more tasks. It is whether humans get the interface, memory, permissions, and audit trail to safely manage 100 delegated workers.

Karl Mehta

22,215 Aufrufe • vor 3 Monaten

I wake up fairly early and I love listening to classical Hindustani ragas to get my day going. I got inspired recently by this website called Dhuni and wanted to get some of my own favorites built into a radio station and build an interesting interface with a man slowly walking through a forest as dawn becomes day becomes evening becomes night and the dawn comes back again. Used Emergent And literally one-shotted this whole thing in less than 10 minutes. I was just 🤯. I have used the product often over the last 6-8 months as an investor but this was genuinely so well done. I tried using the same prompt on at least 3 other platforms and some essentially connected to radio stations that had Hindi music but then randomly inserted English music. Some didn't have an interface as cool, some had output that was barely understandable and needed a lot of APIs to YT. Some asked me to use curl on the terminal to download my favorite tracks as MP3s 😆 This experience just brought back to me how large an opportunity personal apps can be in the future. This exact thing would have cost me $20/mo as saas sub and would be fairly generic. This app now is exactly to my taste. The interface is exactly as I described it, the music is exactly like I want it. Just a delightful personal software I'm now waking up to every day. I am hosting it on Emergent here if you want to check it out:

I wake up fairly early and I love listening to classical Hindustani ragas to get my day going. I got inspired recently by this website called Dhuni and wanted to get some of my own favorites built into a radio station and build an interesting interface with a man slowly walking through a forest as dawn becomes day becomes evening becomes night and the dawn comes back again. Used Emergent And literally one-shotted this whole thing in less than 10 minutes. I was just 🤯. I have used the product often over the last 6-8 months as an investor but this was genuinely so well done. I tried using the same prompt on at least 3 other platforms and some essentially connected to radio stations that had Hindi music but then randomly inserted English music. Some didn't have an interface as cool, some had output that was barely understandable and needed a lot of APIs to YT. Some asked me to use curl on the terminal to download my favorite tracks as MP3s 😆 This experience just brought back to me how large an opportunity personal apps can be in the future. This exact thing would have cost me $20/mo as saas sub and would be fairly generic. This app now is exactly to my taste. The interface is exactly as I described it, the music is exactly like I want it. Just a delightful personal software I'm now waking up to every day. I am hosting it on Emergent here if you want to check it out:

Hemant Mohapatra

19,168 Aufrufe • vor 6 Monaten

I believe that the interfaces of the future will disappear. Instead of buttons and menus, we will interact with objects. The process itself becomes the feedback. Building software is always a complex craft, but spatial computing is a different beast entirely. It demands a fusion of visual art, logic, and spatial UI where every interaction happens in the air around you. With OPERATOR, built for Apple Vision Pro, we explored this by turning music into a sculpture. The music track isn't a timeline anymore; it’s a 3D object you can walk around, touch, and modify from any angle.

I believe that the interfaces of the future will disappear. Instead of buttons and menus, we will interact with objects. The process itself becomes the feedback. Building software is always a complex craft, but spatial computing is a different beast entirely. It demands a fusion of visual art, logic, and spatial UI where every interaction happens in the air around you. With OPERATOR, built for Apple Vision Pro, we explored this by turning music into a sculpture. The music track isn't a timeline anymore; it’s a 3D object you can walk around, touch, and modify from any angle.

maxim zhestkov

102,915 Aufrufe • vor 8 Monaten

MyKeep is officially live 💙 MyKeep is a private and a safe visual space for everything you save - literally everything that usually end up scattered across different apps and folders 🤌 The idea was simple: save everything in one place, organize it smartly (that you don't even have to organize) in your way, and actually find it again when you need it. Today, My Keep is now open as Beta V1 to everyone 💙 It's now available to everyone with an awesome stable version with more and more crazy features, and there is a lot more coming (you would never think of), but it is ready for people to start using and shaping with their feedback. The trailer will show you : What MyKeep is, Why I built it, and the kind of experience I want it to become. Start saving at: 🚀

MyKeep is officially live 💙 MyKeep is a private and a safe visual space for everything you save - literally everything that usually end up scattered across different apps and folders 🤌 The idea was simple: save everything in one place, organize it smartly (that you don't even have to organize) in your way, and actually find it again when you need it. Today, My Keep is now open as Beta V1 to everyone 💙 It's now available to everyone with an awesome stable version with more and more crazy features, and there is a lot more coming (you would never think of), but it is ready for people to start using and shaping with their feedback. The trailer will show you : What MyKeep is, Why I built it, and the kind of experience I want it to become. Start saving at: 🚀

Vinay Juneja

10,978 Aufrufe • vor 2 Monaten

On the left is my original system animation, developed entirely by myself. On the right is ColorOS 17, one of the most highly praised Android interfaces today. I'd like to share some of my design philosophy and hear your thoughts. First, I want every icon to become an active part of the animation. In my design, each icon has a subtle dynamic relationship with the other icons on the home screen. Whenever you swipe back to the home screen, the surrounding icons respond with a gentle pulling and magnetic attraction effect, creating a natural sense of interaction and movement. To avoid visual clutter and unnecessary eye strain, I deliberately slowed down this process and carefully refined the motion curves. My goal is to make this attraction effect subtle enough to feel natural, yet noticeable enough to give the entire interface a sense of connection and life. Everything should feel light, fluid, and organic, while maintaining visual harmony. Second, I've completely rethought the spatial logic of app-opening animations. Traditional Android animations generally rely on proportional scaling, where an app window gradually expands from its icon into a full-screen interface. I decided to explore a different approach: a scroll-like unfolding animation. Instead of simply scaling up, the app window unfolds outward from the center toward both sides, much like a scroll being gently unrolled. I believe this creates a stronger sense of spatial continuity and feels more intuitive and natural than conventional proportional scaling. I've also paid particular attention to the transitions between window expansion, background changes, and icon movement, ensuring that every stage flows smoothly into the next without abrupt shifts in speed or distracting visual jumps. Finally, I've made almost every aspect of this animation fully customizable. This includes the attraction speed of background icons, magnetic pull strength, motion curves, window expansion timing, background blur intensity, progressive blur transitions, and their respective animation curves. Almost every visual parameter you see in the video can be adjusted independently. This gives me the freedom to experiment with countless combinations and continuously refine the balance between fluidity, natural movement, spatial depth, and visual comfort. My philosophy is simple: great system animations should feel alive without becoming chaotic, fluid without losing structure, and sophisticated without trying too hard. This animation is still a work in progress, and I'm constantly refining it. Take a look at the side-by-side comparison. Which animation style do you prefer? What do you think I should improve next? I'd genuinely love to hear your feedback and suggestions. I'll carefully consider them as I continue developing future versions.

On the left is my original system animation, developed entirely by myself. On the right is ColorOS 17, one of the most highly praised Android interfaces today. I'd like to share some of my design philosophy and hear your thoughts. First, I want every icon to become an active part of the animation. In my design, each icon has a subtle dynamic relationship with the other icons on the home screen. Whenever you swipe back to the home screen, the surrounding icons respond with a gentle pulling and magnetic attraction effect, creating a natural sense of interaction and movement. To avoid visual clutter and unnecessary eye strain, I deliberately slowed down this process and carefully refined the motion curves. My goal is to make this attraction effect subtle enough to feel natural, yet noticeable enough to give the entire interface a sense of connection and life. Everything should feel light, fluid, and organic, while maintaining visual harmony. Second, I've completely rethought the spatial logic of app-opening animations. Traditional Android animations generally rely on proportional scaling, where an app window gradually expands from its icon into a full-screen interface. I decided to explore a different approach: a scroll-like unfolding animation. Instead of simply scaling up, the app window unfolds outward from the center toward both sides, much like a scroll being gently unrolled. I believe this creates a stronger sense of spatial continuity and feels more intuitive and natural than conventional proportional scaling. I've also paid particular attention to the transitions between window expansion, background changes, and icon movement, ensuring that every stage flows smoothly into the next without abrupt shifts in speed or distracting visual jumps. Finally, I've made almost every aspect of this animation fully customizable. This includes the attraction speed of background icons, magnetic pull strength, motion curves, window expansion timing, background blur intensity, progressive blur transitions, and their respective animation curves. Almost every visual parameter you see in the video can be adjusted independently. This gives me the freedom to experiment with countless combinations and continuously refine the balance between fluidity, natural movement, spatial depth, and visual comfort. My philosophy is simple: great system animations should feel alive without becoming chaotic, fluid without losing structure, and sophisticated without trying too hard. This animation is still a work in progress, and I'm constantly refining it. Take a look at the side-by-side comparison. Which animation style do you prefer? What do you think I should improve next? I'd genuinely love to hear your feedback and suggestions. I'll carefully consider them as I continue developing future versions.

Ice Universe

45,434 Aufrufe • vor 1 Tag

“what are your dreams for the future?” 🆑: my ambition is to try and have the simplest life, keeping all those passions alive, and this is really where i’m spending my time now. i don't really need anything more because i’m happy the way i am, and my only ambition now is to obviously be a world champion. this is all i’ve ever dreamed about and this is all i’ve ever worked for and what i will continue to do so. but just having a relatively simple life and of course, simple is relative and it's more simpler than what it is now because obviously my life is quite hectic and i travel from everywhere. i go everywhere in the world every week for racing, for different kind of events. but trying to keep a simpler life and at the end of the day, i think what really matters in life is mostly people that you love most and to just keep that in mind, even though life is obviously quite hectic. 🎥: eight sleep

“what are your dreams for the future?” 🆑: my ambition is to try and have the simplest life, keeping all those passions alive, and this is really where i’m spending my time now. i don't really need anything more because i’m happy the way i am, and my only ambition now is to obviously be a world champion. this is all i’ve ever dreamed about and this is all i’ve ever worked for and what i will continue to do so. but just having a relatively simple life and of course, simple is relative and it's more simpler than what it is now because obviously my life is quite hectic and i travel from everywhere. i go everywhere in the world every week for racing, for different kind of events. but trying to keep a simpler life and at the end of the day, i think what really matters in life is mostly people that you love most and to just keep that in mind, even though life is obviously quite hectic. 🎥: eight sleep

clara

15,190 Aufrufe • vor 4 Monaten

I built an entire RAG application without writing any code. This is one of the easiest ways to start building AI applications. I used Langflow. It's open-source. It's a visual interface for building and deploying AI applications. I built a couple of workflows to show you how it works, and I'm impressed! Check the video I recorded. I built two workflows: 1. The first one loads data into a vector store database (Astra DB). 2. The second asks questions from that data using OpenAI's models. Langchain does the heavy lifting behind the scenes, but having a visual interface makes this 10 times easier. Here is Langflow's GitHub repository: In the video, I used their pre-release version. The development experience for building AI applications is improving tremendously! What a time to be a builder!

I built an entire RAG application without writing any code. This is one of the easiest ways to start building AI applications. I used Langflow. It's open-source. It's a visual interface for building and deploying AI applications. I built a couple of workflows to show you how it works, and I'm impressed! Check the video I recorded. I built two workflows: 1. The first one loads data into a vector store database (Astra DB). 2. The second asks questions from that data using OpenAI's models. Langchain does the heavy lifting behind the scenes, but having a visual interface makes this 10 times easier. Here is Langflow's GitHub repository: In the video, I used their pre-release version. The development experience for building AI applications is improving tremendously! What a time to be a builder!

Santiago

263,170 Aufrufe • vor 2 Jahren