正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Ok I'm convinced, Generative UI is the future I built this today using Vercel's AI SDK & PostHog, it allows you to talk with your analytics data All you do is describe in natural language what you'd like to see and then talk with the results

Rhys

58,889 subscribers

233,794 次观看 • 2 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

11 条评论

Rhys 的头像

Rhys2 年前

Since it's a chat, all you need to do to make an edit is ask for it - here's me asking to modify a chart without having to specify the time range again or what other properties to add, it just understands from the history

Rhys 的头像

Rhys2 年前

Imagine the power this unlocks - You could create custom client dashboards to give this ability to your users It also lets everyone on your team take a deeper role into analytics, they don't have to understand SQL they just have to ask a question

Rhys 的头像

Rhys2 年前

If there's interest I can put this on a website for people to use with their own PostHog data For now though, it's open source and super easy to run locally - the repo is available at

Rhys 的头像

Rhys2 年前

This is also the first Generative UI project that I've seen which uses real data which is an accomplishment I'm really proud of For the Vercel stock price one, it was a super helpful learning resource but it was ChatGPT making up values - this one really works

Rhys 的头像

Rhys2 年前

Here's the source code if you want to play around with it yourself!

Tanmay 的头像

Tanmay2 年前

@vercel Isnt this just props filling pre built ui?

Rhys 的头像

Rhys2 年前

@vercel In this case it’s conversion your natural language into SQL (HogQL for PostHog) queries, running them, and then determining how to render the results Along with that it’s loading all the data from the results into your conversation so you can talk about it

Philipp Tsipman 的头像

Philipp Tsipman2 年前

@vercel This is awesome! Thank you for open-sourcing it! 🙏 And... just submitted the first issue. :)

Rhys 的头像

Rhys2 年前

@vercel 🫡 thanks for opening up an issue, put out a commit that I think will fix it

Spencer 的头像

Spencer2 年前

@vercel How is this generative UI? It looks like generative charts, which I think would be a killer app. Add a csv or data set and ask it in natural language to create a beautiful chart that represents the data.

Rhys 的头像

Rhys2 年前

@vercel I was mainly just going off of for the wording I think it’s v0 of Generative UI where it starts out with us passing premade components combined with chat and eventually turns into dynamic

相关视频

Is your job actually safe from AI? I’ve been thinking about this a lot. To get some real answers, I'm using Frank AI Researcher to let you talk to an AI agent yourself. It takes 5 minutes. You tell the agent what you do every day and what tech you use. Then, it gives you a "future-proof score" to show how much of your work can be automated right now. I really want to see what you guys find out. Link to talk to the agent:👇

Is your job actually safe from AI? I’ve been thinking about this a lot. To get some real answers, I'm using Frank AI Researcher to let you talk to an AI agent yourself. It takes 5 minutes. You tell the agent what you do every day and what tech you use. Then, it gives you a "future-proof score" to show how much of your work can be automated right now. I really want to see what you guys find out. Link to talk to the agent:👇

AI Panda

70,835 次观看 • 5 个月前

Try this out, it’s really cool! You can sketch a mockup, talk about what it should look like, and in seconds the UI is built. Powered by Groq Inc. Then you can iterate with voice to make improvements. (App is open source, btw 🔥)

Try this out, it’s really cool! You can sketch a mockup, talk about what it should look like, and in seconds the UI is built. Powered by Groq Inc. Then you can iterate with voice to make improvements. (App is open source, btw 🔥)

Ben Klieger

142,674 次观看 • 1 年前

Jensen Huang built the world's most valuable chip company and is telling the next generation of programmers prompt engineering is the future: "Why program in Python? So weird." "The first time I talk to the computer, I'm just speaking in plain English." "English, by the way, human, it's the best programming language of the future." "How do you make a computer do what you want it to do? How do you fine tune the instructions with that computer? That's called prompt engineering. There's an artistry to that." PS. If you found value in this post make sure to like and repost this tweet + follow Uncover AI to stay updated with the latest AI news. See you in the next one:

Jensen Huang built the world's most valuable chip company and is telling the next generation of programmers prompt engineering is the future: "Why program in Python? So weird." "The first time I talk to the computer, I'm just speaking in plain English." "English, by the way, human, it's the best programming language of the future." "How do you make a computer do what you want it to do? How do you fine tune the instructions with that computer? That's called prompt engineering. There's an artistry to that." PS. If you found value in this post make sure to like and repost this tweet + follow Uncover AI to stay updated with the latest AI news. See you in the next one:

Uncover AI

36,137 次观看 • 4 个月前

This is the future of UI. I built an AI chat that changes its own visual shape and form as you talk. The AI invents the perfect user interface to fulfill your needs and guide you to the desired result. Try for free.

This is the future of UI. I built an AI chat that changes its own visual shape and form as you talk. The AI invents the perfect user interface to fulfill your needs and guide you to the desired result. Try for free.

Florian S

158,072 次观看 • 1 年前

Jensen Huang says, In the future, we will be able to talk to a protein We'll ask it: "what are you? are you soluble? how do you react to heat or chemicals?" This is how AI can talk to an image today, and how we've moved from only processing data to actually understanding it

Jensen Huang says, In the future, we will be able to talk to a protein We'll ask it: "what are you? are you soluble? how do you react to heat or chemicals?" This is how AI can talk to an image today, and how we've moved from only processing data to actually understanding it

Haider.

149,843 次观看 • 10 个月前

"Mom was like, 'Jay, he's in the room with some chicken heads.' Jay pulled up. He kicked my girls out. He had the talk with me like, 'This what you want to do? You want to be in the projects with these girls? I'm rich. I'm trying to give you the opportunity to change your life, to change life in this apartment. I want to bring you with me, but if this is what you want to do, cool. I'll leave you here to do it.' I didn't see Jay for probably like a year or two." - MemphisBleek

"Mom was like, 'Jay, he's in the room with some chicken heads.' Jay pulled up. He kicked my girls out. He had the talk with me like, 'This what you want to do? You want to be in the projects with these girls? I'm rich. I'm trying to give you the opportunity to change your life, to change life in this apartment. I want to bring you with me, but if this is what you want to do, cool. I'll leave you here to do it.' I didn't see Jay for probably like a year or two." - MemphisBleek

Club Shay Shay

591,510 次观看 • 1 年前

The top 10 most significant events in AI this week: 1. AI changed Photoshop forever. Adobe released 'Generative Fill,' allowing you to guide with Photoshop using AI and natural language.

The top 10 most significant events in AI this week: 1. AI changed Photoshop forever. Adobe released 'Generative Fill,' allowing you to guide with Photoshop using AI and natural language.

Rowan Cheung

1,190,982 次观看 • 3 年前

Replit Head of AI Michele Catasta says soon we'll see people using far fewer apps because they'll have replaced them with agents: "The reason is, we built UIs, computers in this way in the last decade because the only way we had to interact with them was through the keyboard and mouse, which are error-prone." "But the way you work is, you talk to your colleagues. You discuss, decide what to do. You express in natural language your intent, and then you either delegate or get the job done yourself." "But, guess what? Agents do exactly that. The more autonomous we make them, the more capable we make them, the more they're going to be able to complete tasks end-to-end."

Replit Head of AI Michele Catasta says soon we'll see people using far fewer apps because they'll have replaced them with agents: "The reason is, we built UIs, computers in this way in the last decade because the only way we had to interact with them was through the keyboard and mouse, which are error-prone." "But the way you work is, you talk to your colleagues. You discuss, decide what to do. You express in natural language your intent, and then you either delegate or get the job done yourself." "But, guess what? Agents do exactly that. The more autonomous we make them, the more capable we make them, the more they're going to be able to complete tasks end-to-end."

TBPN

19,472 次观看 • 2 个月前

PostHog Changelog, S1E1: Warm Green Space Goo - Experiments: You can now measure declines in metrics, like account deactivations, during experiments. Why? Because sometimes "up and to the right" isn't the correct goal. - Max AI: Max can now generate surveys in seconds using natural language. Just go to the Surveys product and start telling Max what your dream survey looks like. - Max AI: You can now add existing insights, dashboards, events, and actions as context to your conversations with Max. Try using this to summarize the trends on a dashboard, or analyze how a key metric is trending over time.

PostHog Changelog, S1E1: Warm Green Space Goo - Experiments: You can now measure declines in metrics, like account deactivations, during experiments. Why? Because sometimes "up and to the right" isn't the correct goal. - Max AI: Max can now generate surveys in seconds using natural language. Just go to the Surveys product and start telling Max what your dream survey looks like. - Max AI: You can now add existing insights, dashboards, events, and actions as context to your conversations with Max. Try using this to summarize the trends on a dashboard, or analyze how a key metric is trending over time.

PostHog

17,131 次观看 • 11 个月前

Today we're launching Amplitude MCP MCP was made for data analytics. Ask a vague question and have an AI model iteratively query Amplitude to find you insights. Amplitude MCP exposes all of Amplitude's functionality so an agent can interact with it directly. It allows you to use Amplitude without having to know anything about Amplitude's user interface or your data taxonomy. It uses the intelligence of off the shelf AI agents, including Claude, Gemini, and Cursor, to query Amplitude data you already have to find answers. It leverages all of your existing Amplitude data and how it's used to navigate through large complex behavioral datasets. You can have conversations about your product data directly inside any AI model with MCP. It can create Amplitude dashboards and notebooks with what it finds and even make recommendations. This is the best MCP use case I've ever seen. Watching an AI agent think, reason, query Amplitude, and then repeat that process iteratively is magical. See it in action:

Today we're launching Amplitude MCP MCP was made for data analytics. Ask a vague question and have an AI model iteratively query Amplitude to find you insights. Amplitude MCP exposes all of Amplitude's functionality so an agent can interact with it directly. It allows you to use Amplitude without having to know anything about Amplitude's user interface or your data taxonomy. It uses the intelligence of off the shelf AI agents, including Claude, Gemini, and Cursor, to query Amplitude data you already have to find answers. It leverages all of your existing Amplitude data and how it's used to navigate through large complex behavioral datasets. You can have conversations about your product data directly inside any AI model with MCP. It can create Amplitude dashboards and notebooks with what it finds and even make recommendations. This is the best MCP use case I've ever seen. Watching an AI agent think, reason, query Amplitude, and then repeat that process iteratively is magical. See it in action:

Spenser Skates

32,420 次观看 • 11 个月前

There's a silence surrounding me I can't seem to think straight I'll sit in the corner and no one can bother me I think I should speak now (Why won't you talk to me?) I can't seem to speak now (You never talk to me) My words won't come out right (What are you thinking?) I feel like I'm drowning (What are you feeling?) I'm feeling weak now (Why won't you talk to me?) But I can't show my weakness (You never talk to me) I sometimes wonder (What are you thinking?) Where do we go from here (What are you feeling?) It doesn't have to be like this All we need to do is make sure we keep talking (Why won't you talk to me?) I feel like I'm drowning (You never talk to me) You know I can't breathe now (What are you thinking?) We're going nowhere (What are you feeling?) We're going nowhere (Why won't you talk to me?) (You never talk to me) (What are you thinking?) (Where do we go from here?) It doesn't have to be like this All we need to do is make sure we keep talking #PinkFloyd

There's a silence surrounding me I can't seem to think straight I'll sit in the corner and no one can bother me I think I should speak now (Why won't you talk to me?) I can't seem to speak now (You never talk to me) My words won't come out right (What are you thinking?) I feel like I'm drowning (What are you feeling?) I'm feeling weak now (Why won't you talk to me?) But I can't show my weakness (You never talk to me) I sometimes wonder (What are you thinking?) Where do we go from here (What are you feeling?) It doesn't have to be like this All we need to do is make sure we keep talking (Why won't you talk to me?) I feel like I'm drowning (You never talk to me) You know I can't breathe now (What are you thinking?) We're going nowhere (What are you feeling?) We're going nowhere (Why won't you talk to me?) (You never talk to me) (What are you thinking?) (Where do we go from here?) It doesn't have to be like this All we need to do is make sure we keep talking #PinkFloyd

Pink Floyd 💎

27,894 次观看 • 2 年前

LinkedIn just started hiding AI-written posts. And their system catches them 94 percent of the time. But the answer is NOT to stop using AI. They announced this in May. If your post sounds like everyone else's, it doesn't get deleted. It just stops spreading. Your followers see it. Nobody new ever does. They're even flagging the way AI writes. Sentences like "it's not this, it's that"? Flagged. But most people missed one line in that announcement: using AI to HELP you write is totally fine. You just have to make it sound like you. Here are 2 things you can do: One, give your AI your own stuff. Upload your old posts, your client results, your stories, your data, your transcripts. Now instead of pulling generic advice off the internet, it's writing from YOUR experience. In your voice. Two, write about what people care about RIGHT NOW. I check AnswerThePublic to see the exact questions my audience is typing in this week then I write about those. The more you sound like yourself and talk about real problems people face, the more people will want to hear what you have to say.

LinkedIn just started hiding AI-written posts. And their system catches them 94 percent of the time. But the answer is NOT to stop using AI. They announced this in May. If your post sounds like everyone else's, it doesn't get deleted. It just stops spreading. Your followers see it. Nobody new ever does. They're even flagging the way AI writes. Sentences like "it's not this, it's that"? Flagged. But most people missed one line in that announcement: using AI to HELP you write is totally fine. You just have to make it sound like you. Here are 2 things you can do: One, give your AI your own stuff. Upload your old posts, your client results, your stories, your data, your transcripts. Now instead of pulling generic advice off the internet, it's writing from YOUR experience. In your voice. Two, write about what people care about RIGHT NOW. I check AnswerThePublic to see the exact questions my audience is typing in this week then I write about those. The more you sound like yourself and talk about real problems people face, the more people will want to hear what you have to say.

Neil Patel

12,378 次观看 • 1 个月前

Today i'm Open Sourcing "Rilable" The iOS app that builds Web apps and iOS Apps. I built it with Fable 5 in 10 prompts. (~ $210 in tokens on API pricing) All apps are built with Claude Models, and every app spins up a sandbox (Exactly like Lovable) using Daytona. Database is Convex. The app allows you to build apps that have AI features for this it uses Vercel AI gateway, and iOS apps are using Chorus.com iOS skill (All links below)

Today i'm Open Sourcing "Rilable" The iOS app that builds Web apps and iOS Apps. I built it with Fable 5 in 10 prompts. (~ $210 in tokens on API pricing) All apps are built with Claude Models, and every app spins up a sandbox (Exactly like Lovable) using Daytona. Database is Convex. The app allows you to build apps that have AI features for this it uses Vercel AI gateway, and iOS apps are using Chorus.com iOS skill (All links below)

Riley Brown

72,248 次观看 • 3 个月前

I'm excited to share my talk on building Agentic RAG systems at last week's event with Arize AI and Google! 🥳 My talk covered: 1. The differences between Vanilla RAG and Agentic RAG 2. The agent ecosystem and how you can build agents today 3. How Weaviate AI Database is building agents with Generative Feedback Loops (GFLs) This snippet presents the multi-agent paradigm for Agentic RAG. I hope you find this talk interesting and would love to know what you think! The slide deck and full video links are below.

I'm excited to share my talk on building Agentic RAG systems at last week's event with Arize AI and Google! 🥳 My talk covered: 1. The differences between Vanilla RAG and Agentic RAG 2. The agent ecosystem and how you can build agents today 3. How Weaviate AI Database is building agents with Generative Feedback Loops (GFLs) This snippet presents the multi-agent paradigm for Agentic RAG. I hope you find this talk interesting and would love to know what you think! The slide deck and full video links are below.

Erika Shorten

61,515 次观看 • 1 年前

You can legit build your own OpenClaw🦞 from scratch in about 20 minutes with the GitHub Copilot SDK. And when you build it, you can make it do anything. Here's how to build a personal AI assistant, and how I'm using one today.

You can legit build your own OpenClaw🦞 from scratch in about 20 minutes with the GitHub Copilot SDK. And when you build it, you can make it do anything. Here's how to build a personal AI assistant, and how I'm using one today.

Burke Holland

26,933 次观看 • 6 个月前

A retrospective on INFOWARS & what it’s like to host a show here with Tim Tompkins! This is the house the PEOPLE built. Let’s talk about it and do even more!

A retrospective on INFOWARS & what it’s like to host a show here with Tim Tompkins! This is the house the PEOPLE built. Let’s talk about it and do even more!

Rex

16,769 次观看 • 4 个月前

Tubbo: "I really want you guys to talk about AI more actively." Listen to the guy. Talk about (generative) AI and its consequences. Spread information in online spaces, but also talk to your IRLs if you can.

Tubbo: "I really want you guys to talk about AI more actively." Listen to the guy. Talk about (generative) AI and its consequences. Spread information in online spaces, but also talk to your IRLs if you can.

Tubbo Daily

34,517 次观看 • 11 个月前

Introducing RAGs, a Streamlit app that allows you to create and customize your own RAG agent and then use it over your own data, all with natural language 🔥 Directly inspired by OpenAI GPTs, you can converse with an agent to help you do search/retrieval over any data you specify. The app contains three main pages: 🏠 Home Page : Have a “builder agent” build your RAG agent through natural language (you specify the data). ⚙️ RAG Config: Look at configured parameters 🤖 Use your RAG agent! Check out details below 👇 Blog: Repo:

Introducing RAGs, a Streamlit app that allows you to create and customize your own RAG agent and then use it over your own data, all with natural language 🔥 Directly inspired by OpenAI GPTs, you can converse with an agent to help you do search/retrieval over any data you specify. The app contains three main pages: 🏠 Home Page : Have a “builder agent” build your RAG agent through natural language (you specify the data). ⚙️ RAG Config: Look at configured parameters 🤖 Use your RAG agent! Check out details below 👇 Blog: Repo:

LlamaIndex 🦙

475,732 次观看 • 2 年前

Naval on how to get a job in 2025: Learn how to use AI Naval on E215: "The fastest way to help somebody get a job right now: the best thing you can do is say, 'Hey, go download the AI tools and just start talking to them. Just start using them in any way.'" "And then you can walk into any employer in almost any field and say, 'Hey, I understand AI.' And they'll hire you on the spot." "AI is a productivity tool. It increases the productivity of a worker. It allows them to do more creative work and less repetitive work. As such, it makes them more valuable." "Yes, there is some retraining involved, but not a lot. These are natural language computers. You can talk to them in plain English, and they talk back to you in plain English." "I think we will see job creation by AI that will be as fast or faster than job destruction." "You saw this even with the internet. Like, YouTube came along. Look at all these YouTube streamers and influencers. That didn't used to be a job." "Go brush up on your AI. Learn a little bit. Watch a few videos. Use the AI." "Tinker with it and then go reapply for that job that rejected you, and watch how they pull you in."

Naval on how to get a job in 2025: Learn how to use AI Naval on E215: "The fastest way to help somebody get a job right now: the best thing you can do is say, 'Hey, go download the AI tools and just start talking to them. Just start using them in any way.'" "And then you can walk into any employer in almost any field and say, 'Hey, I understand AI.' And they'll hire you on the spot." "AI is a productivity tool. It increases the productivity of a worker. It allows them to do more creative work and less repetitive work. As such, it makes them more valuable." "Yes, there is some retraining involved, but not a lot. These are natural language computers. You can talk to them in plain English, and they talk back to you in plain English." "I think we will see job creation by AI that will be as fast or faster than job destruction." "You saw this even with the internet. Like, YouTube came along. Look at all these YouTube streamers and influencers. That didn't used to be a job." "Go brush up on your AI. Learn a little bit. Watch a few videos. Use the AI." "Tinker with it and then go reapply for that job that rejected you, and watch how they pull you in."

The All-In Podcast

164,054 次观看 • 1 年前