Ivan Zhao

Things Ivan Says on Podcasts

not now, my bread's in the oven

Where to Find Them

Ivan Zhao writes Reboot . They have also been a guest on No Priors , Grit , Possible , Decoder with Nilay Patel , AI & I and Lenny's Podcast: Product | Career | Growth . They also write for CONSUME ME and a lexicon of verbs on Substack.

Recently: “Notion’s Founder on the One Thing Your AI Is Missing” on AI & I (November 2026); “How Notion rebuilt for the age of AI” on Possible (March 2026); “Notion's CEO wants you to demand better from your tools” on Decoder with Nilay Patel (August 2025); “How Notion Reimagined Productivity Tools | Ivan Zhao” on Grit (August 2025); “Notion’s lost years, its near collapse during Covid, staying small to move fast, the joy and suffering of building horizontal, more | Ivan Zhao (CEO and co-founder)” on Lenny's Podcast: Product | Career | Growth (March 2025); “RAG is the key for smarter productivity tools with Notion CEO Ivan Zhao” on No Priors (February 2024).

What They Said

“Should people have the power, if they want to, to modify the tools they use? To me it's hell yes. But a lot of things you use every day, a chair, a car, a door, you just want someone to figure out the best form factor and do a good job. Just because you can doesn't mean you should. You might not want to vibe code a bridge or a building.” — Ivan Zhao, AI & I

Dan asked how the original no-code vision changes now that anyone can vibe code. Ivan splits software into what people should be able to modify, what is better crafted by someone else, and enterprise software people shouldn't build themselves.

AI & I · 2026-11-18 Permalink → Listen →
AI & I Around 08:26 into the episode
Ivan Zhao

…In some sense, the original vision of the 60s, 70s, hippie generation computing came to life, and that's actually why Notion was started. Notion was about how do we bring this computing power to as many people as possible without forcing them to learn how to code. And so I'm a big fan of this.

Dan Shipper

…that as the way that you make software, and the way that Notion is built is the way that you could make software or code without having to code pre-LLMs. So now that we're in that era, how does that change how you think what should be built or how to make that vision come alive in this new way?

Ivan Zhao

I think we should separate this into multiple axes. One axis is: should people have the power if they want to to modify the tools they use? To me, it's hell yes, definitely. That's the free, there's a basic sense of freedom with the medium you use every day. Vibe coding, AI coding agent, give people that power better than any other medium. So I'm fully supportive. Then there is what about the thing that you use every day that you don't have a strong opinion about, you just want someone taking care of you. A lot of problems we face every day, a chair, for example, a car, a door, you might not be an expert of those tools. You just want someone to figure out what's the best form factor of a chair and door is and just do a good job, right? You might not want to wipe coding a bridge or a building. So that part, I don't think just because you can doesn't mean you should. So certain category of software I will actually put under this bucket. So for example, calendar app. Actually today we launched the second version of the calendar app on mobile. It's completely built from scratch. Thing Your. Native. And in my consideration…

Dan Shipper

And how do you think about what you make and where it fits in on that axis?

Ivan Zhao

Where who?

Dan Shipper

Notion.

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“One assumption we hold true inside the company is that for the next billion knowledge workers coming online, the vast majority will be agents. So our customer is no longer only humans, but a lot more agents. Second, we also believe that human camaraderie and human collaboration matters. We don't want to live in a world where you chat with your little chat box and it becomes the TikTok, Instagram effect.” — Ivan Zhao, AI & I

An audience member asked why people would keep using Notion if their agents can just use the apps for them. Ivan says Notion treats agents as customers too, while still building a shared canvas where humans and agents work together.

AI & I · 2026-11-18 Permalink → Listen →
AI & I Around 32:21 into the episode
Natalia Quintero

I'm on you.

Dan Shipper

…curious because from a media agency standpoint, we're also thinking about this from websites and media. But from your perspective as a developer, how are you approaching that? Like, how do we continue to engage the consumer and keep them wanting to use Notion instead of just having their agents?

Ivan Zhao

Yeah. It's a really good question. It's not as black and white as that. One assumption we hold true inside a company is we assume for the next billion knowledge workers coming online, vast majority will be agents. So our customer is no longer just only humans, but a lot more agents. And those are the key agents, the cloud, the chat GPTs of the world. That's one. Second, we also believe that human camaraderie and human collaboration matters. We don't want to live in a world that you chat with your little chat box and become like TikTok, Instagram, effect. Whether that's good or bad, business will put it aside. We don't want to live in that world. So the thing we care about is that the sheer canvas, the team of humans, work with the team of agents, the Kanban boards of the world. And for that, that's closer to where the context is, or closer to Notion is. So for us, it's not black and white. Yes, a lot more agents coming online, but there's also a part that you want to preserve, which is closer to headless product, no UI at all.

Dan Shipper

Awesome. That's all the time we have, folks. Ivan Zhao you so much. It was a pleasure.

Ivan Zhao

Thing Your.

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“Claude Code became really popular and everybody talked into their own little black box to build things, using GitHub as a way to merge them. Then you realize, we don't understand what each other are doing. It's better to have a team-based thing. So instead of each human talking to their own coding agent, we set up a Notion Kanban board. It's almost going back to Kanban and Jira, but it turns out to be a pretty good visual metaphor to orchestrate a bunch of agents' work.” — Ivan Zhao, AI & I

Dan asked whether Ivan had found anything that keeps people locked in to understanding how their agents work. Ivan describes his team's fix: coordinating coding agents through a shared Kanban board instead of private one-to-one sessions.

AI & I · 2026-11-18 Permalink → Listen →
AI & I Around 23:26 into the episode
Ivan Zhao

…Math, create better shorthand to understand the world around us. Agent can do a lot for us, but you cannot have understanding. It's difficult, right? I think more software AI toolmakers should think about how do you help people to gain the understanding of what those systems are doing for us.

Dan Shipper

Have you found anything that works for you to make sure that you're locked into understanding how it works?

Ivan Zhao

I can share some tips our teams are using. It's also almost ironic, right? So like think about the way of a coding agent. Clockhold become really popular. Everybody talked into their own little black box to build things. And using GitHub as a way to merge things, then you realize, holy shit, we don't understand what each other are doing. It's better to have a team-based coding thing. Now, instead of human talking to their own coding agent, we set up Notion Kanban board. It's almost going back to the thing that Kanban, Jira, everybody, hey, but turns out it's actually a pretty good visual metaphor to orchestrate a bunch of agents work, right? That's what I mean, a concrete example of visualization. You visualize the thing to the best of your ability, and you hope you can absorb it.

Dan Shipper

So we have time for a few questions. So if you have a question, raise your hand and right in the back over there. Hey, thank you. I wanted to talk about and ask a question about structure versus unstructured. Because the tradition that you're talking about, I think of it as being about comparing or…

Ivan Zhao

Sorry.

Dan Shipper

I'm not going to answer it. I just think it's a great question.

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“The deeper level is: does the human have the understanding? Do you understand what's going on? If a team of humans builds a medium-plus-size code base, after a week you sort of don't understand what's going on. I don't think we should surrender our understanding. Definitely not without putting up a fight. If anything, we should try to figure out how to create better abstractions, better tools and better visualization to understand things.” — Ivan Zhao, AI & I

Dan raised the 'one more prompt' pull of late-night vibe coding and the idea of having the AI quiz you before it builds. Ivan says the real issue is whether people still understand the systems their agents build.

AI & I · 2026-11-18 Permalink → Listen →
AI & I Around 22:30 into the episode
Ivan Zhao

…after 10 minutes, you got grossed out. I got grossed out. It feels like that a little bit. So it feels like, yes, there's a tremendous amount of productivity gained from agents, from AI, but what other second-order effects can we at least think about a little bit while we're building more to it?

Dan Shipper

…know that we made this thing that makes it really easy to build stuff, and that's awesome. And we know that when it's 11 at night, you can probably just use it to rip tokens that mean nothing and you're just sucked into your phone. How do you think about how to deal with those second-order effects?

Ivan Zhao

Depends on whatever you're building a chat product, maybe just bake this into your system. I think that's too superficial level. The deeper level is like, does the human have the understanding? Like, do you understand what's going on? Like, if you usually build a system or if a team of human medium plus size code base, after a week, you sort of don't understand what's going on. I don't think we should surrender our understanding. Definitely not without putting up a fight. If anything, we should try to figure out how to create better abstractions, better tools, and better visualization to understand things. That's entirely the purpose of science. Math, create better shorthand to understand the world around us. Agent can do a lot for us, but you cannot have understanding. It's difficult, right? I think more software AI toolmakers should think about how do you help people to gain the understanding of what those systems are doing for us.

Dan Shipper

Have you found anything that works for you to make sure that you're locked into understanding how it works?

Ivan Zhao

I can share some tips our teams are using. It's also almost ironic, right? So like think about the way of a coding agent. Clockhold become really popular. Everybody talked into their own little black box to build things. And using GitHub as a way to merge things, then you realize, holy shit, we…

Dan Shipper

So we have time for a few questions. So if you have a question, raise your hand and right in the back over there. Hey, thank you. I wanted to talk about and ask a question about structure versus unstructured. Because the tradition that you're talking about, I think of it as being about comparing or…

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“There's a difference between Lego pieces and clay. Clay is a mud. It's very hard for a kid or even an adult to build a tall tower out of clay. Things just fall apart. Lego has inherent structure and gives you that structured power. I think vibe coding or a coding agent gives you the clay, the fine-grained JavaScript. But oftentimes the maker doesn't have the opinion or expertise to structure a tall tower out of it. I think the industry is converging on what the Legos of vibe coding are, where the permissions, syncing and collaboration are taken care of for you.” — Ivan Zhao, AI & I

An audience member asked how Notion thinks about moving from structured building blocks to the unstructured, token-level world of AI. Ivan answers with the Lego-versus-clay analogy and says the middle ground is what Notion is building toward.

AI & I · 2026-11-18 Permalink → Listen →
AI & I Around 25:19 into the episode
Ivan Zhao

Sorry.

Dan Shipper

I'm not going to answer it. I just think it's a great question.

Ivan Zhao

I think it's a great question, too. So, Notion logo is a cube, right? It's a toy. Kids can build up a cube. Actually, Lego is an even better example. There's a difference between Lego pieces versus a clay. Clay is kind of like a mud. It's very hard for a kid or even an adult to build up tall clay. Things just fall apart. Lego, easier to pick up their hand, has inherent structure. It's not as unstructured, it's not as fine-grained as a clay, but give you that structured power. Have some opinion injected. I think vibe coding or coding agent is more give you the clay, give you the JavaScript, give you the fine-grain thing. But oftentimes, the maker doesn't have the opinion or expertise to structure a tall tower out of it. I think there is a sweet spot. I think the industry is merging towards what are the Legos of Vibe coding. So the fundamental permissions, syncing, collaboration are taken care of for you. Yes, you can still express your business logic and intent, but the pieces are there. In fact, that's what we're doing.

Dan Shipper

And what does that mean? Like, what would be an example of a vibe coding building block that it's not necessarily clay, but it's maybe more manipulable than a Lego brick because you have an agent to help you do it?

Ivan Zhao

Well, the basic is you get an agent to help you set up your Notion, or the more powerful version of it is, we actually released this, I think it's become public now. Notion pattern libraries open up to all the agents and can read from Notion databases, guarded against by the Notion system…

Dan Shipper

And the pattern library is like it's an open source library, so an agent can implement it in your own apps.

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“What's really important is the data. How do you hold your data? How do you hold your context, your semantics, what's important to you and your business? To us, that's a lot more durable than the procedural logic and the UI. So we see our job more and more as being the keeper of your data, to open it up to different agents in the world, in the fancy term, context, and allow different agents to work with this context and provide a guardrail, allow a team of humans to collaborate on this context.” — Ivan Zhao, AI & I

Dan Shipper asked how Notion's team deals with models changing so fast that product work can be obsolete in months. Ivan says agents can write the workflow code and the UI, so the durable part of software is the data and context underneath.

AI & I · 2026-11-18 Permalink → Listen →
AI & I Around 11:15 into the episode
Ivan Zhao

…you want to feel that way. It's almost like experience, right? Yes, you can cook yourself, but oftentimes, you like to go to a restaurant as well. We like to think about many of our products are feels like going to a good restaurant, cost-effective restaurant, but give you a good experience.

Dan Shipper

…to make something like think about how does this button feel and think about all the little details, knowing that maybe the thing that you're making probably might not be relevant in three months or six months. Do you think about that? Do your teams think about that? And how do you deal with it?

Ivan Zhao

I think the value of what AI agent really fundamentally changed is if you think about the value of software, for the past 15 years, it's usually a team of people or a company defines one of the best ways to follow this workflow and create a UI and the buttons to do those workflows. And AI agent opened up both of them. The AI agent can write a procedural code to do any kind of workflow you want. You can Vibecode the UI, whatever you want them to do. So, in some sense, we are not married to that. Notion actually started design allow you to create your own UI even before AI. But what's really important is the data. How do you hold your data? How do you hold your context? Your semantics? What's important to you, to your business? To us, that's a lot more durable than the procedural logic and then the UI. So, we see our job more and more to be the keeper of your data, to open up to different agents in the world, in the fancy term called context, and allow different agents to work with this context and provide a guardrail, allow a team of humans to collaborate on this context. To me, that's more durable, and that's outside model. You define that for your business.

Dan Shipper

How are you playing with these tools yourself? We were talking a little bit about Vibecoding. Do you have your hands in them? And what are you doing? What are you building?

Ivan Zhao

Making games.

Dan Shipper

What kind of games?

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.

Collections They Appear In