Calm AI for Crazy Days: Inside Granola's Design Philosophy, with co-founder Sam Stephenson artwork

Calm AI for Crazy Days: Inside Granola's Design Philosophy, with co-founder Sam Stephenson

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis

April 8, 2026

Sam Stephenson, co-founder of Granola, explains how a deliberately minimalist design philosophy helped turn the AI note-taking app into one of the fastest-growing products in the market.
Speakers: Erik Torenberg, Sam Stephenson
**Erik Torenberg** (0:00)
Hello, and welcome back to The Cognitive Revolution. Today my guest is Sam Stephenson, co-founder and designer at Granola, the breakout AI note-taking app that recently raised $125 million at a $1.5 billion valuation. As a user of the app myself, I've been struck by how streamlined, even minimalist, the Granola product experience is. And considering how easy it is to code up new features these days, I just knew that this had to be a very deliberate design choice on Sam's part. And so I wanted to use this conversation to hear what he's learned about designing AI products for mass market adoption. We begin with Granola's product design philosophy, which Sam playfully calls surprisingly unambitious, at least in terms of the number of jobs that they aim to do for users. Taking inspiration from the kitchen tool company Oxo, which designs products that work for people with disabilities and end up delighting everyone else, Granola aims to provide a calm product experience for people with crazy work days. In practice, as you'll hear, the keys to Sam's success are simple, timeless design disciplines. Spend lots of time with lots of users. Understand their challenges and needs deeply. And do one thing extremely well before adding other features. All very familiar advice to any product leader, but increasingly counter to the trend in the vibe coding era.
As always, we get into a lot of additional detail along the way. Sam says that Granola's rapid growth has been driven overwhelmingly by the single core mechanism of users sharing call notes with teammates and partners. He also highlights a number of popular and surprising use cases, and explains how they're using recipes, such as the Blind Spot Finder that I created when Granola sponsored a number of episodes earlier this year, both for marketing purposes and, more importantly, to inspire users to use the product to its fullest potential. He tells us what partners they're using for transcription, why Granola has no limits or concept of credits, and how they're thinking about managing inference costs as they add new features over time. He explains their decision to make Granola work at the operating system audio level, rather than joining calls as a participant, like most other note-taking apps do, and how this relates to their thoughts on privacy and consent, their decision to store call transcripts but not raw audio, and the idea that we might want to engineer at least some AI systems to forget certain details over time, just as we humans do. He also unpacks how Granola is thinking about their new team collaboration features, the tricky balance between the immense upside of better information sharing across organizations, and the risks of oversharing sensitive information, and also how much we can trust AIs to decide what should be shared with whom. We discuss how Granola's team works today, including why he thinks that Figma remains valuable but should be nervous, and more importantly, how they are using a combination of internal demo days and intensive dogfooding to inform what are ultimately mostly vibes-based decisions about what to launch. Toward the end, we get Sam's greatest hopes and fears for Granola, namely that it will help people live something closer to their best lives, with less screen time and more space for reflection and strategic thinking, and on the other hand, the possibility that a few leading AI hyperscalers could end up dominating the market and capturing most of the value that AI creates. Clearly, there are multiple ways to build a successful AI product in today's world. But for me, as someone who is constantly obsessing over frontier capabilities, this conversation was a very useful way to calibrate myself on how mainstream users understand and relate to AI. And also a great reminder that timeless design discipline continues to work. With that, I hope you enjoy this inside look at the design thinking powering one of the fastest growing AI products in the market today. With Sam Stephenson, Co-Founder of Granola. The Cognitive Revolution is brought to you in part by Google, makers of the Gemini family of models, and much more. Here's a fun fact about me. The first thing I knew I wasn't going to be when I grew up, going all the way back to first grade, was an artist. I could vaguely imagine what I wanted to create, but I couldn't come anywhere close to creating what I'd imagined. And so, I concluded that art wasn't for me. Recently though, I've been using the Gemini image creation model, which you may know as Nano Banana, to create art for every new episode of the show. The workflow is honestly shockingly simple. I started by identifying a source of inspiration. In my case, it's a set of massive frescoes at the Detroit Institute of Arts that depict Henry Ford's iconic assembly lines and evoke the transformative impact, for better and for worse, that the Industrial Revolution had on human workers and society as a whole. I then use a three-part prompt, which consists of a style guide, combining colors, textures, and details I remember from the paintings with my own ideas about cyberpunk futurism, a few notes on the episode title and themes I want to feature, and a few reference photos of the episode guest. Mere seconds later, I'm opening original art. And while it does usually take a few rounds of iteration to land on something that I'm proud of, that process is also pretty easy and quite fun. I just give my favorite generated images and guest photos back to the model with some additional natural language instructions and wait to see what it makes. I never thought I'd be able to create a consistent visual identity for the show. But with Nano Banana, I can have fun creating things that I enjoy, that make my guests look good, that perform well on YouTube, and that pay homage to a uniquely memorable piece about the promise and peril of technological change. All in just a few minutes. It truly is an incredible time to be alive. So try Nano Banana for yourself via Google's AI Studio or the Gemini app. Thank you to Google for supporting the Cognitive Revolution. And now on with the show. Sam Stephenson, co-founder and designer at Granola. Welcome to the Cognitive Revolution.

85 more minutes of transcript below

Feed this to your agent

Try it now — copy, paste, done:

curl -H "x-api-key: pt_demo" \
  https://spoken.md/transcripts/1000651996090

Works with Claude, ChatGPT, Cursor, and any agent that makes HTTP calls.

From $0.10 per transcript. No subscription. Credits never expire.

Using your own key:

curl -H "x-api-key: YOUR_KEY" \
  https://spoken.md/transcripts/1000760334545