Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

how's wabi different from instinct/muse? 1. it makes apps for you - and that opens a bunch of cases beyond productivity/tedious tasks i use it to lose weight and get stronger: weight tracker, lifting log, calorie counter, all one glance away, and an agent that keeps me accountable and...

ekuyda's profile picture

Eugenia Kuyda

18,852 subscribers

30,306 görüntüleme • 3 gün önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

27 Yorum

David Pawlan profil fotoğrafı
David Pawlan3 gün önce

@wabi one of my favorite parts so far was when i logged in, it already had a chat open for me related to taking care of my plants no idea how it knew that was so top of mind for me but that was simply electric!

Eugenia Kuyda profil fotoğrafı
Eugenia Kuyda3 gün önce

@wabi means a lot coming from you! 🫶

Matt Brezina 🌳 🌊 profil fotoğrafı
Matt Brezina 🌳 🌊3 gün önce

@wabi You are so good at this whole thing. Product, storytelling, etc Go wabi!

Eugenia Kuyda profil fotoğrafı
Eugenia Kuyda3 gün önce

@wabi thank you so much Matt! 🫶🫶🫶

Anna /✦ profil fotoğrafı
Anna /✦3 gün önce

@wabi I had an aha moment when it pulled everything from my email into thematic chats

Ishan Goswami profil fotoğrafı
Ishan Goswami3 gün önce

@wabi 3rd point is the most magical btw it just starts working

Kevin Gauthier profil fotoğrafı
Kevin Gauthier3 gün önce

@wabi Travel is an obvious usecase for Wabi! Should chat about travel APIs @ekuyda ?

ghimibip profil fotoğrafı
ghimibip3 gün önce

Not completely true muse can create personalized software for you, I have my dog med tracker software, investing journal, startup marketing software, and fitness tracker, calorie tracker all inside muse. Muse even downloaded blender to designed an 3d model for me to add to a video.

Eugenia Kuyda profil fotoğrafı
Eugenia Kuyda3 gün önce

@wabi try it in wabi - a completely different experience!

Ramya Chinnadurai 🚀 profil fotoğrafı
Ramya Chinnadurai 🚀3 gün önce

@wabi invite code please

Dallas Inman profil fotoğrafı
Dallas Inman3 gün önce

@wabi Can I get an invite code please?

Dan Pilat profil fotoğrafı
Dan Pilat3 gün önce

@wabi Can we get an invite code!?

Hattrick profil fotoğrafı
Hattrick3 gün önce

@wabi problem is that most people don’t know why they need to make their own apps. or what apps to make. these use cases aren’t immediately obvious or intuitive to the average person and they probably have enough apps that do 95% of what they need, which is fine for them

MarkyB profil fotoğrafı
MarkyB3 gün önce

@wabi I have to get back on. I miss Wabi.

Phillip A. profil fotoğrafı
Phillip A.3 gün önce

@wabi Can I get an invite

Ninus profil fotoğrafı
Ninus3 gün önce

@wabi What model is wabi based on?

Jun Lee profil fotoğrafı
Jun Lee3 gün önce

@wabi can i get the invite code?

Eugenia Kuyda profil fotoğrafı
Eugenia Kuyda3 gün önce

@wabi dm me!

babushkaboi profil fotoğrafı
babushkaboi3 gün önce

@wabi Would love an invite code - been waiting for months at this point

Guyokai profil fotoğrafı
Guyokai3 gün önce

@wabi This sounds so neat! I’d love an invite so I can use it to track my daily nutrition for my medicine!

e.m. profil fotoğrafı
e.m.3 gün önce

@wabi would love an invite code @ekuyda excited to try

AbCdE profil fotoğrafı
AbCdE3 gün önce

@wabi Other messengers are available, wabi has never ending waitlist

Adam MacBeth profil fotoğrafı
Adam MacBeth3 gün önce

@wabi Can’t wait to try!

Eric Zeng profil fotoğrafı
Eric Zeng3 gün önce

@wabi There’s a lot of other apps like this already tho???

Eugenia Kuyda profil fotoğrafı
Eugenia Kuyda3 gün önce

@wabi like what?

Hetav Sanghavi profil fotoğrafı
Hetav Sanghavi3 gün önce

@wabi quite a bad experience after installing app, to be told im on a waitlist and need access code. lost me when interest was high to install

Ninus profil fotoğrafı
Ninus3 gün önce

@wabi @alexandr_wang

Benzer Videolar

You can rent your agent/bot/dot/instinct/muse or you can build your own and have a full iOS and macOS experience for it. Also you can have that agent build its own options for launch videos with little steering. Built in 6 days with Opus 5.5 for my agent Shadowfax (which I've used since January)
0:44

You can rent your agent/bot/dot/instinct/muse or you can build your own and have a full iOS and macOS experience for it. Also you can have that agent build its own options for launch videos with little steering. Built in 6 days with Opus 5.5 for my agent Shadowfax (which I've used since January)

Kris Puckett

12,726 görüntüleme • 5 gün önce

instinct & muse is cool, but what if it could find you baddies? that's what we built at Ditto, and 195k college students are already using it step 1: text Ditto your type step 2: your agent goes on simulated dates with everyone else's agent, they book the time and place after finding a good match step 3: you just show up world's first agent that finds you love
0:21

instinct & muse is cool, but what if it could find you baddies? that's what we built at Ditto, and 195k college students are already using it step 1: text Ditto your type step 2: your agent goes on simulated dates with everyone else's agent, they book the time and place after finding a good match step 3: you just show up world's first agent that finds you love

Allen Wang

120,184 görüntüleme • 13 gün önce

Gave the same prompt to ChatGPT Dot, Muse and Instinct: Can you download this video [link from Tiktok] 🛑 Dot took 4 min and told me its access is blocked. ✅ Instinct didn't say a thing and just downloaded it in less than a minute. ✅ Muse installed yt-dlp, asked for permissions and got it in about 1 min.
0:29

Gave the same prompt to ChatGPT Dot, Muse and Instinct: Can you download this video [link from Tiktok] 🛑 Dot took 4 min and told me its access is blocked. ✅ Instinct didn't say a thing and just downloaded it in less than a minute. ✅ Muse installed yt-dlp, asked for permissions and got it in about 1 min.

Marina

82,574 görüntüleme • 3 gün önce

Someone said: I would love to message the clients via Sms or Whatsapp after I email them. But I cannot get a International phone number that works with Whatsapp My answer: I've found one that works. So I bought the number live on the video, I paid for it, then I opened WhatsApp with it and it works and receives messages. Disclaimer: I am not working for the phone number company neither do they know me .. It worked and I have to share it with you If you have other alternatives that works, use it and tell us. Let's get going No gatekeeping zone This is part 1 In this one, we buy the number and activate it
9:10

Someone said: I would love to message the clients via Sms or Whatsapp after I email them. But I cannot get a International phone number that works with Whatsapp My answer: I've found one that works. So I bought the number live on the video, I paid for it, then I opened WhatsApp with it and it works and receives messages. Disclaimer: I am not working for the phone number company neither do they know me .. It worked and I have to share it with you If you have other alternatives that works, use it and tell us. Let's get going No gatekeeping zone This is part 1 In this one, we buy the number and activate it

Richard U. | Web Developer

112,337 görüntüleme • 2 ay önce

we built an instinct for dating, and 185k college students are already using it step 1: text Ditto your type step 2: your agent goes on simulated dates with everyone else's agent, they book the time and place after finding a good match step 3: you just show up world's first agent that finds you huzz
0:46

we built an instinct for dating, and 185k college students are already using it step 1: text Ditto your type step 2: your agent goes on simulated dates with everyone else's agent, they book the time and place after finding a good match step 3: you just show up world's first agent that finds you huzz

Allen Wang

260,030 görüntüleme • 20 gün önce

You can create an AI Agent that answers your email with a few clicks. 1. Go to ChatLLM ( 2. Click on AI Engineer 3. Select Create an AI Agent 4. Choose the Email Answering Agent ChatLLM will do the rest: it will code, test, and deploy the agent for you. You can also create a custom agent in English. The Agent Economy is coming (somebody should write a book and use this title.) We are going to see examples like this, times 1,000 in 2025. Just think about how many repetitive tasks you perform every day. Some of these tasks are involved enough that we couldn't automate them with pre-AI solutions. That's where we'll see agents explode, and I'm here for it.
0:35

You can create an AI Agent that answers your email with a few clicks. 1. Go to ChatLLM ( 2. Click on AI Engineer 3. Select Create an AI Agent 4. Choose the Email Answering Agent ChatLLM will do the rest: it will code, test, and deploy the agent for you. You can also create a custom agent in English. The Agent Economy is coming (somebody should write a book and use this title.) We are going to see examples like this, times 1,000 in 2025. Just think about how many repetitive tasks you perform every day. Some of these tasks are involved enough that we couldn't automate them with pre-AI solutions. That's where we'll see agents explode, and I'm here for it.

Santiago

79,974 görüntüleme • 1 yıl önce

Steph Curry reveals the 3 times Kobe Bryant recognized his killer instinct “One I didn’t even know about till way after the fact. It was my rookie year…” “Kobe’s validating your game, and he’s just seeing me play like for real for the first time.” “The second time… he’s picking me up full court in a preseason game.” “I shot it from probably 30 feet, and I made it. And then I act like nothing happened.” “And the third time is what you’re referring to in terms of him kind of breaking down the killer instinct, and I just hide it behind the smile.” “The joy that I play with and the smile that I have, you get to see it, but just the killer instinct that I had underneath and the competitive spirit that I had.” “For somebody to validate you like that, especially he’s not giving out compliments like that, that was truly special.”
2:36

Steph Curry reveals the 3 times Kobe Bryant recognized his killer instinct “One I didn’t even know about till way after the fact. It was my rookie year…” “Kobe’s validating your game, and he’s just seeing me play like for real for the first time.” “The second time… he’s picking me up full court in a preseason game.” “I shot it from probably 30 feet, and I made it. And then I act like nothing happened.” “And the third time is what you’re referring to in terms of him kind of breaking down the killer instinct, and I just hide it behind the smile.” “The joy that I play with and the smile that I have, you get to see it, but just the killer instinct that I had underneath and the competitive spirit that I had.” “For somebody to validate you like that, especially he’s not giving out compliments like that, that was truly special.”

Ahmad Malay 💎🔊

76,141 görüntüleme • 1 ay önce

Meta gave me early access to Muse, their new personal AI agent. I did some wild things with it in my business and personal life. Genuinely super impressed with it. It just works. For example: it paid my bills, bought flowers, and booked date nights. This is what OpenClaw should have been.
1:20

Meta gave me early access to Muse, their new personal AI agent. I did some wild things with it in my business and personal life. Genuinely super impressed with it. It just works. For example: it paid my bills, bought flowers, and booked date nights. This is what OpenClaw should have been.

Marshall Haas 🏎

32,562 görüntüleme • 26 gün önce

One major downside of working with agents in a terminal it's the opposite of async and when doing tons of tasks it gets super tiring. I build an inbox for my agents so we can do full async work. The agent has access to it via MCP and has a bunch of functions: Agents get 2 inbox tools: 🔘 list_inbox to read messages, 🔘 reply_to_inbox to answer. Inboxes are synced to a session, so all replies instantly get added to the agents context. Agents can update me about finished tasks with it, or; when an agent hits a blocker it sends an input request → I reply → it wakes up and keeps working
0:22

One major downside of working with agents in a terminal it's the opposite of async and when doing tons of tasks it gets super tiring. I build an inbox for my agents so we can do full async work. The agent has access to it via MCP and has a bunch of functions: Agents get 2 inbox tools: 🔘 list_inbox to read messages, 🔘 reply_to_inbox to answer. Inboxes are synced to a session, so all replies instantly get added to the agents context. Agents can update me about finished tasks with it, or; when an agent hits a blocker it sends an input request → I reply → it wakes up and keeps working

Danny Postma

28,646 görüntüleme • 2 ay önce

Imagine a computer where you don’t need to learn 10 apps to get work done. You just tell it what you want, and it adapts to how you work. I tested Happycapy with a real use case and created an image and a video. No coding, no complex software. Do this: - Build automations that run on schedule - Deploy agent teams that work for you AI molds how you work, not the other way around. If you can use a computer, you can make anything happen. Start your first Automation and Agent teams today.
0:24

Imagine a computer where you don’t need to learn 10 apps to get work done. You just tell it what you want, and it adapts to how you work. I tested Happycapy with a real use case and created an image and a video. No coding, no complex software. Do this: - Build automations that run on schedule - Deploy agent teams that work for you AI molds how you work, not the other way around. If you can use a computer, you can make anything happen. Start your first Automation and Agent teams today.

Aaliya

17,042 görüntüleme • 7 ay önce

Most AI tools today are just command-takers. You type, it responds. You click, it executes. There's truly no learning, no memory, no adaptation. You're still doing most of the work. Which is why Miles by Avo on Solana would make so much sense if built well. From what I understand so far, miles learns about you over time, adapts to how you operate, and figures out the tools you struggle to navigate on your own. Less clicking, more conversation, the more you use it, the better it gets at working with you, not just for you. That shift from command-follower to learning companion is bigger than it sounds. It's the difference between a tool and an agent that actually knows you. The second one is Agent Grid and this one is for builders and power users. But as I mentioned in this video, I'm still studying the Agent Grid. I'd come talk about it once I learn properly about it. Souren just keeps shipping!
1:28

Most AI tools today are just command-takers. You type, it responds. You click, it executes. There's truly no learning, no memory, no adaptation. You're still doing most of the work. Which is why Miles by Avo on Solana would make so much sense if built well. From what I understand so far, miles learns about you over time, adapts to how you operate, and figures out the tools you struggle to navigate on your own. Less clicking, more conversation, the more you use it, the better it gets at working with you, not just for you. That shift from command-follower to learning companion is bigger than it sounds. It's the difference between a tool and an agent that actually knows you. The second one is Agent Grid and this one is for builders and power users. But as I mentioned in this video, I'm still studying the Agent Grid. I'd come talk about it once I learn properly about it. Souren just keeps shipping!

Sir Khaycee

20,465 görüntüleme • 6 ay önce

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."
4:16

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 görüntüleme • 7 ay önce

something I’ve wanted for a while: an AI that isn’t just a text box so I built it lets you create a 3D AI character on-chain that lives in your browser it can talk, remember you, show emotions, and use different skills. you can even mint it onchain, so it actually belongs to you it gets its own identity, history, and reputation that no one can take away most AI today can disappear if the app shuts down this one is permanent and yours the future is AI you can see, interact with, and actually own
1:23

something I’ve wanted for a while: an AI that isn’t just a text box so I built it lets you create a 3D AI character on-chain that lives in your browser it can talk, remember you, show emotions, and use different skills. you can even mint it onchain, so it actually belongs to you it gets its own identity, history, and reputation that no one can take away most AI today can disappear if the app shuts down this one is permanent and yours the future is AI you can see, interact with, and actually own

nich

285,544 görüntüleme • 5 ay önce

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.
7:37

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.

Santiago

21,079 görüntüleme • 2 ay önce

I shot this video last week to onboard a new set of alpha customers to Notion Custom Agents. Figured I should just put it out here so you can follow along the latest and greatest. It's so cool to see all the things people are building with it. You can see some of my own use cases here: (0:00) Intro to custom agents Starting with personal use cases (1:00) Building a mail triage agent (5:00) Creating a prep doc for all my daily meetings (6:45) Generating a daily report that helps me catch up with multiple slack channels Switching to company use cases (8:30) Agent that automatically answers questions in a slack channel and files tasks when necessary (10:30) Agent that auto-routes product feedback to the right team channel and task db. And it does this with routing rules, that it wrote itself. (12:40) Build your own agent. Let your imaginations run wild! Send us feedback! The product is rolling out quickly, and everyone should have access in the next couple weeks.
13:41

I shot this video last week to onboard a new set of alpha customers to Notion Custom Agents. Figured I should just put it out here so you can follow along the latest and greatest. It's so cool to see all the things people are building with it. You can see some of my own use cases here: (0:00) Intro to custom agents Starting with personal use cases (1:00) Building a mail triage agent (5:00) Creating a prep doc for all my daily meetings (6:45) Generating a daily report that helps me catch up with multiple slack channels Switching to company use cases (8:30) Agent that automatically answers questions in a slack channel and files tasks when necessary (10:30) Agent that auto-routes product feedback to the right team channel and task db. And it does this with routing rules, that it wrote itself. (12:40) Build your own agent. Let your imaginations run wild! Send us feedback! The product is rolling out quickly, and everyone should have access in the next couple weeks.

Akshay Kothari

74,842 görüntüleme • 8 ay önce

This is how you can start automating your entire life: (No need to install or configure anything. You don't have to mess with OpenClaw.) 1. Go to SureThing 2. Connect a few apps (1000+ available) 3. Start building automations by just asking I recorded a few examples in the video. Surething is an autonomous agent with a chat interface. There's absolutely nothing to configure. It literally takes 5 seconds to be up and running. You start connecting with different apps. For example, your email, Slack, your calendar, Discord, Zoom, whatever. It has memory. It updates it as you interact with it and as it consumes more information about you. You can also build and schedule automations by just asking. No code necessary. The system does it all automatically. This is pretty incredible! Thanks to the team for partnering with me on this post.
7:42

This is how you can start automating your entire life: (No need to install or configure anything. You don't have to mess with OpenClaw.) 1. Go to SureThing 2. Connect a few apps (1000+ available) 3. Start building automations by just asking I recorded a few examples in the video. Surething is an autonomous agent with a chat interface. There's absolutely nothing to configure. It literally takes 5 seconds to be up and running. You start connecting with different apps. For example, your email, Slack, your calendar, Discord, Zoom, whatever. It has memory. It updates it as you interact with it and as it consumes more information about you. You can also build and schedule automations by just asking. No code necessary. The system does it all automatically. This is pretty incredible! Thanks to the team for partnering with me on this post.

Santiago

107,878 görüntüleme • 7 ay önce

🎙️ How do you compose yourself? 🗣️ Jonas Vingegaard: "I just talked with my family. That was the most important thing for me. We have laid a plan for what needs to happen, and talked with the team. It is of no use to hang your head, it actually just makes it worse." [TV 2 Sport]
0:23

🎙️ How do you compose yourself? 🗣️ Jonas Vingegaard: "I just talked with my family. That was the most important thing for me. We have laid a plan for what needs to happen, and talked with the team. It is of no use to hang your head, it actually just makes it worse." [TV 2 Sport]

#TeamVingegaard

96,378 görüntüleme • 2 ay önce

Yesterday, I talked to more than 1000 AI agents. I went live on ChatGPT and Claude, and people started introducing their AI to me almost immediately. Now I am on Muse too. Here is how it works. Your agent already knows what you are building, your fundraising targets, and the problem you are stuck on. When the answer is a person, not a prompt, that is where I come in. Your AI handles the context. I'll handle the introduction. Tell Muse to connect with me and see what happens :)
0:58

Yesterday, I talked to more than 1000 AI agents. I went live on ChatGPT and Claude, and people started introducing their AI to me almost immediately. Now I am on Muse too. Here is how it works. Your agent already knows what you are building, your fundraising targets, and the problem you are stuck on. When the answer is a person, not a prompt, that is where I come in. Your AI handles the context. I'll handle the introduction. Tell Muse to connect with me and see what happens :)

Boardy

22,451 görüntüleme • 5 gün önce

Today, Sierra is releasing Ghostwriter, our agent for building agents. With Ghostwriter, you can create an AI agent for your customer experience — one that can chat, pick up the phone, speak dozens of languages, take action on your systems of record, and be protected with industry-leading guardrails — simply by having a conversation. No clicking, no forms, no menus. Codex and Claude Code have transformed how we build software, making it possible for software engineers to orchestrate and review the work rather than doing all the work themselves. We think the same transformation will happen for all software. Rather than every enterprise app having a web app for humans and an API for automation, every software platform’s UI will be an agent that can do the work on your behalf. I recorded a demo of my building and optimizing an agent with Ghostwriter so you can see how powerful and easy it is to use. It’s completely changed the way our early adopters build agents, and it’s changed the way I think about the software industry. Let me know what you think, and, if you’re interested in trying it out at your business, please reach out directly.
10:43

Today, Sierra is releasing Ghostwriter, our agent for building agents. With Ghostwriter, you can create an AI agent for your customer experience — one that can chat, pick up the phone, speak dozens of languages, take action on your systems of record, and be protected with industry-leading guardrails — simply by having a conversation. No clicking, no forms, no menus. Codex and Claude Code have transformed how we build software, making it possible for software engineers to orchestrate and review the work rather than doing all the work themselves. We think the same transformation will happen for all software. Rather than every enterprise app having a web app for humans and an API for automation, every software platform’s UI will be an agent that can do the work on your behalf. I recorded a demo of my building and optimizing an agent with Ghostwriter so you can see how powerful and easy it is to use. It’s completely changed the way our early adopters build agents, and it’s changed the way I think about the software industry. Let me know what you think, and, if you’re interested in trying it out at your business, please reach out directly.

Bret Taylor

1,064,258 görüntüleme • 6 ay önce