
Summary
Written by a model from the transcript; not yet reviewed.
In this episode of The Every Podcast, Dan Shipper sits down with Notion founder and CEO Ivan Zhao to discuss how the rise of AI agents and vibe coding has fundamentally reshaped the company's product vision. Reflecting on Notion's origins in the 1960s and 70s computing ideal of software as a universal medium, Zhao explains why raw coding agents resemble raw clay rather than structured building blocks. The discussion explores the tension between rapid software generation and maintaining human understanding, team collaboration, and durable context layers. Zhao also shares how he builds historical text-based games to test emerging models and details Notion's ongoing evolution into a context and knowledge system for modern teams.
Throughout the conversation, the guest and host examine the second-order effects of continuous AI interaction and why structured tools like Kanban boards remain essential for orchestrating multi-agent work. Rather than fighting the shift toward AI-native tools, Notion positions itself as the durable keeper of business data and semantic context. Listeners gain a rare look into the strategic mindset of a major software CEO navigating the transition from static applications to agentic workflows.
- Focus on owning the data layer and semantic context of your business, because procedural logic and user interfaces change much faster than core knowledge. 13:02
- Recognize that while vibe coding gives people raw creation power like clay, teams still need structured components and guardrails to build scalable solutions. 26:53
- Combat the isolated black-box nature of individual AI coding by using visual collaboration frameworks like Kanban boards to keep teams aligned. 25:10
Chapters
- 0:20Podcast Intro and Host Overview
Dan and Natalia introduce the episode and explain the focus on Notion’s founder Ivan Zhao.
- 0:53AI’s Impact on No-Code Platforms
Discussion of how AI changes the need for block-based interfaces and the shift toward AI coding agents.
- 8:20Building AI-Integrated Products and Teams
Ivan shares strategies for integrating AI agents into teams while maintaining clarity and collaboration.
- 11:40Future Roadmap and Business Context Layer
Ivan outlines Notion’s plans to provide a context layer for businesses and the vision for AI transformation.
- 21:13Second-Order Effects of AI and User Experience
Ivan reflects on the societal and personal impacts of AI, emphasizing the need for understanding and thoughtful design.
- 25:51Audience Q&A: Structure vs. Tokens
Listeners ask about moving from structured blocks to token-based AI, and Ivan explains the sweet spot.
- 33:33Closing Remarks and Thank You
Hosts wrap up the episode, thanking Ivan and summarizing key takeaways.
Highlights
- 4:36
Software as a Universal Mediuminsight
The guest explains that Notion's founding was inspired by 1960s and 70s computing ideals where interactive software was meant to be read and written by everyone.
- 8:23
Three Categories of Softwarestrategy
The guest breaks down software into three axes: tools people want to modify themselves, well-crafted consumer apps where users want a finished solution, and secure enterprise infrastructure.
- 12:51
Data Durability Over UI Logicinsight
The guest argues that user interfaces and procedural code are fleeting in the age of AI agents, making business data and context the truly durable assets.
- 13:42
Building Historical Text Gamesstory
The guest shares how he uses various language models and development tools to build open-narrative historical games featuring interactive figures from specific eras like Vienna in 1900.
- 17:17
The 13-Year Evolution of Notionstory
The guest reflects on Notion's 13-year journey, describing the first five years as wandering in the dark before finding product-market fit during COVID and locking themselves in a hotel room in late 2022 to build early AI features.
- 25:10
Visualizing Multi-Agent Workflowsstrategy
The guest explains how his teams counter the isolation of vibe coding by using visual Kanban boards to orchestrate and understand work done by multiple agents.
- 26:56
Lego Bricks Versus Raw Clayinsight
Comparing vibe coding to raw clay rather than structured Lego bricks, the guest highlights the need for opinionated tools and pattern libraries that give builders proper structural support.
Quotes
“Notion was about how do we bring this computing power to as many people as possible without forcing them to learn how to code.”
Unnamed speaker · 0:10 “I think there's some kind of soul overlap between Notion and Every, and I think that comes from who Ivan is as a person.”
Dan Shipper · 1:26 “The AI agent can write a procedural code, do any kind of workflow you want. You can vibe code a UI, whatever you want them to do, right?”
Unnamed speaker · 12:34 “We have the Lego pieces, many of them, we don't offer them with a box today. So our goal for the next quarter, less than two, hopefully, is that solution for a 50 people company, having all the context and knowledge, know how together, out of the box, onboard through agent.”
Unnamed speaker · 30:29
Sponsored segments
- Lovable 6:49–7:45
About this episode
Lovable is the fastest way to turn ideas into software people love: https://lovable.dev/grow?utm_source=every&utm_medium=podcast&utm_campaign=2026-11-flagship-sponsorship&utm_content=primary Now that AI enables anyone to build their own software, should you build everything yourself? At Thesis, Notion cofounder and CEO Ivan Zhao joins Every’s Dan Shipper to discuss which tools should and should not be vibe coded—and why you should understand how your systems work, even as agents do the building. Subscribe to Every (free for 14 days): https://every.to/youtube-every-offer?utm_source=youtube&utm_campaign=thesis2027&utm_content=thesistalktoolsforthought Links to resources mentioned in the episode: Ivan Zhao: https://x.com/ivanhzhao Ivan’s post on his 13th year at Notion, “The Next Era of Notion”: https://www.notion.com/blog/the-next-era-of-notion Notion Calendar: https://www.notion.com/product/calendar The IBM System/360, the room-sized computer Ivan references: https://www.ibm.com/history/system-360 Claude Code: https://claude.com/product/claude-code Claude: https://claude.ai ChatGPT: https://chatgpt.com Andrew Ambrosino, who leads the Codex app at OpenAI: https://ambrosino.io Timestamps: 0:00 Introduction 1:18 Why vibe coding revives the 1960s vision of software 4:40 When people should build their own tools—and when they shouldn't 7:47 Why data and context outlast UI and procedural logic 9:46 The history game Ivan is vibe coding with his wife 12:23 Bringing a 13-year-old company from pre-AI to post-AI 16:00 The TikTokification of AI and its second-order effects 19:46 Don't surrender your understanding to agents 22:01 Why builders need Lego-like blocks to vibe code 28:04 Why the next billion knowledge workers will be agents
Transcript
5,539 words · 6 speakers
Speaker names marked are inferred from speaking time and the show’s known hosts — they are not voice-verified.
Topics
- Notion
- AI
- Vibe coding
- Every
- Lego
- ChatGPT
- Claude
- Calendar app
- GPT-4
- OpenAI
Page updated · transcript and summary are machine-generated