The Every Podcast

Building an email client used to take many years and millions of dollars.

But Every’s Kieran Klaassen built Cora—a totally new way to manage your inbox with AI—in just 3 months. He even shipped the original MVP of the product in a single day—something that just wasn’t possible before the current state of generative AI. 

Now, there are almost 10,000 people on the waitlist for Cora, and we’re onboarding new users every single day. 

Every’s head of Studio Brandon Gell and I worked closely with Kieran as he built Cora, and to kick off my podcast, AI and I, in 2025, I invited both of them on the show to talk about it. We go behind the scenes, getting into how Kieran built the product with Cursor, o1, and o1 Pro, what we’re learning as we onboard new users every day, and the future of Cora and of Every as a multi-modal media company.

This is a must watch for anyone curious about our approach to building with AI at Every.

If you found this episode interesting, please like, subscribe, comment, and share! 

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

Subscribe to Every: https://every.to/subscribe 

Follow him on X: https://twitter.com/danshipper 

Links to resources mentioned in the episode:

Sign up for the Cora waitlist: https://cora.computer/ 

Learn more about Cora: Introducing Cora: Manage Your Inbox With AI

Kieran Klaassen: @kieranklaassen

Brandon Gell: @bran_don_gell

AI is going to change science forever.

Small scale studies will give way to large scale open data gathering efforts. We’ll shift from seeking broad general theories to making contextual predictions in individual cases. The traditional research paper will change fundamentally.

That’s why I had Alice Albrecht on the show. Few people straddle the worlds of science and AI like she does: She holds a Ph.D. in cognitive neuroscience from Yale and is a machine learning researcher with almost a decade of experience. In 2021, she founded re:collect, an app that aimed to augment human intelligence with AI. It was acqui-hired by news curation app SmartNews in September of this year, and she is now the senior director of AI product. 

We discuss the contours of this new paradigm of science: the growing importance of data in scientific discovery, how AI makes N-of-1 studies imperative—when they’re normally seen as unscientific, the case for big tech to open-source their data for research, and the power of unbundling data from interpretations, in both science and media. Here is a link to the episode transcript. 

In January of this year, we published Alice’s thesis about how augmenting human intelligence with AI is more effective than attempting to achieve super intelligence through standalone AI systems, and in a happy coincidence, she’s our last podcast guest of 2024. Thank you for listening, and we’ll see you in the new year.

In the meantime, this is a must-watch for anyone interested in how AI is changing the future of scientific research.

If you found this episode interesting, please like, subscribe, comment, and share! 

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

Subscribe to Every: https://every.to/subscribe 

Follow him on X: https://twitter.com/danshipper 

Links to resources mentioned in the episode:

Alice Albrecht: @AliceAlbrecht

The company that recently acquired Alice’s startup: SmartNews

The piece Alice wrote for Every about how AI can augment human intelligence: The Case for Cyborgs 

Every’s product incubations that we discuss in the context of how AI is changing media: Extendable Articles, TLDR 

Chris Pedregal knows how to build AI products that people love. 

Chris is the cofounder and CEO of Granola, an AI-powered notepad for meetings. We use it for many of our meetings at Every—the app listens in on the conversation, transcribes it in the background, and when the meeting ends, creates automated notes and a shareable transcript for anyone who missed it. If you take notes during the meeting, Granola polishes them to be more organized and complete. 

Granola is one of my favorite consumer AI products because it’s equal parts delightful and useful. It’s not a bland chat interface. It’s not an over-the-top demo that you wouldn’t use more than once. Granola is a product with “soul,” imbued with the team’s vision for how AI can work alongside you to turn discursive conversations into clear insights. And I’m not the only one who thinks so—since Granola’s launch in May 2024, its user base has grown by 5x, with around 5,000 weekly active users, and half the people who try the app still use it 10 weeks later for an average of six meetings a week. The company also recently raised a $20 million Series A.

Granola has the marks of being built by a thoughtful, intentional team, which is why I was excited to have Chris on the show. We spent an hour talking about Chris’s product development philosophy, the role of intuition in making products with “soul” and how he balances this with user feedback, how you can become a better product thinker, and the kinds of consumer AI startups Chris thinks will succeed. Here is a link to the episode transcript. 

This is a must-watch for anyone interested in building valuable, sticky AI products that users will love.

If you found this episode interesting, please like, subscribe, comment, and share! 

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

Subscribe to Every: https://every.to/subscribe 

Follow him on X: https://twitter.com/danshipper 

Links to resources mentioned in the episode:

Chris Pedregal: @cjpedregal

Granola: http://Granola.ai, @meetgranola 

The piece Chris wrote for Every about building useful AI products: https://every.to/thesis/how-to-build-a-truly-useful-ai-product  

Here’s the most compelling benchmark of AI progress: A task that took 60 minutes a year ago now takes 60 seconds.

In January 2024, researcher Geoffrey Litt and I spent an hour coaxing ChatGPT to build a simple app on this podcast. Nearly 12 months later, Steve Krouse and I built the same app with one prompt in less than minute.

Steve is the cofounder and CEO of Val Town, a cloud-based platform for developers to write, share, and deploy code directly in the browser. In this episode, we used Townie, an AI assistant integrated into Val Town, to build an app that would keep track of time on the podcast, take notes, and generate more questions for the guest. 

Townie had generated the app even before Steve could finish describing it on the show, a mark of how much AI has evolved over the last year. As the founder of a growing startup, Steve tells me his contrarian take on why he isn’t focused on the needs of the non-technical AI programmer, betting instead on being the platform sophisticated developers turn to for backend infrastructure. He also tells me how he started programming and how it continues to shape his vision for Val Town. Here is a link to the episode transcript. (Disclosure: I’m a small investor in Val Town.)

This is a must-watch for founders building AI-powered developer tools, and anyone interested in the future of programming.

If you found this episode interesting, please like, subscribe, comment, and share! 

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

Subscribe to Every: https://every.to/subscribe 

Follow him on X: https://twitter.com/danshipper 

Links to resources mentioned in the episode:

Steve Krouse: https://stevekrouse.com/, @stevekrouse 

Val Town: https://www.val.town/ 

Townie, the AI assistant integrated into Val Town: https://www.val.town/townie/signup?next=%2Ftownie 

Pieces on Val Town’s blog about how the team built Townie: How we built Townie—an app that generates fullstack apps, Building a code-writing robot and keeping it happy  

The book by Seymour Papert about how programming changes the way you think: Mindstorms: Children, Computers, and Powerful Ideas

Over the last few months at Every, we’ve launched two new AI products with tens of thousands of users, and we’ll release a third one before the end of the year. The weird thing is: We’re a media company with less than 10 full-time employees, and we’re mostly bootstrapped.

That’s not how things are supposed to work in startups.

When we were first starting Every Studio six months ago, we were told a million reasons why it wouldn’t work: divided focus, not enough money, and the biggest one—it would be too hard to find talented people to run the products we build.

Yesterday, we proved out one of the biggest risks to this strategy: We launched a brand-new version of our AI product Spiral with Danny Aziz as its general manager. 

Danny left a $200,000-a-year salary to come chase his dreams with us. So we decided to take this moment to pull back the curtain and ask, Why? Why did he join us? And why is the model we’ve built working so far? What have we learned about what happens when you mix media, software, and AI in a single organization?

That’s why I invited Danny and Brandon Gell, Every’s head of Studio, on the show. We get into the details of Every’s business model, how new technology and the right people can make the flywheel turn, the power of learning by doing and building from real needs, and where each of us sees ourselves one year from now. Here is a link to the episode transcript.

This is a must-watch for anyone who wants to build a business on their own terms, and have a lot of fun while doing it. 

If you found this episode interesting, please like, subscribe, comment, and share! 

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

Subscribe to Every: https://every.to/subscribe 

Follow him on X: https://twitter.com/danshipper 

Links to resources mentioned in the episode:

Danny Aziz: @DannyAziz97

Brandon Gell: @bran_don_gell

Try Spiral here: https://spiral.computer/  

More about Every’s product incubation arm: https://every.to/p/introducing-every-studio 

Everyone told Vicente Silveira that his startup—a GPT wrapper—would fail. Instead, one year later, it’s thriving—with about 500,000 registered users, nearly 3,000 paying subscribers, and over 2 million conversations in the GPT store. 

Vicente is the cofounder and CEO of AI PDF, a tool to help you summarize, chat with, and organize your PDF files. When OpenAI allowed users to upload documents to ChatGPT, the consensus was that his startup, and all the other GPT wrappers out there, were toast. Even when some of his competitors closed up shop, Vicente believed they could still create value for users as a specialized tool. The AI PDF team kept building. 

Today, AI PDF is one of the most popular AI-powered PDF readers in the world—and they did it with a five-person team and a friends-and-family funding round.

I sat down with Vicente to understand, in granular detail, the success of AI PDF.

Vicente explains how staying small and specialized is a key strategic advantage for his business. We get into why lean startups are better positioned than companies like OpenAI and Anthropic to create cutting-edge solutions for users, the role early adopters of technology play in shaping the market for new products, Vicente’s candid take on raising capital as a growing startup, and his thoughts on the emerging role of AI managers who will be responsible for overseeing AI agents. We demo an agent integrated into AI PDF, prompting it to analyze a bunch of recent articles from my column Chain of Thought and write a bulleted list of the core thesis statements—and even pit AI PDF against Perplexity live on the show. 

This is a must-watch for small teams building profitable companies at the bleeding edge of AI. 

If you found this episode interesting, please like, subscribe, comment, and share! 

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

Subscribe to Every: https://every.to/subscribe 

Follow him on X: https://twitter.com/danshipper 

Links to resources mentioned in the episode:

Vicente Silveira: @vicentes

AI PDF: https://myaidrive.com/  

Dan’s piece on the allocation economy: https://every.to/chain-of-thought/the-knowledge-economy-is-over-welcome-to-the-allocation-economy    

Prompt engineering isn’t just about telling AI to solve your problems—it’s about knowing which ones to solve. 

Yet there’s a mismatch between the people who can identify the right problems—experts with deep domain knowledge—and the technical infrastructure required for developing and refining prompts. Jared Zoneraich, the cofounder and CEO of prompt engineering platform PromptLayer, is bridging the gap with a platform on which non-technical experts can manage, deploy, and evaluate prompts quickly.

The role of human prompt engineers, however, has been the topic of controversy, with some arguing that AI can optimize prompts better than us, while others suggest that more capable LLMs eliminate the need for meticulously crafted prompts altogether. I spent an hour talking to Jared about why he believes prompt engineering isn’t becoming obsolete. He also tells me everything he’s learned about writing a good prompt and what the future of AI tools looks like. Here is a link to the episode transcript.

This is a must-watch for prompt engineers, people interested in building with AI systems, or anyone who wants to generate predictably good responses from LLMs.

If you found this episode interesting, please like, subscribe, comment, and share! 

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

Subscribe to Every: https://every.to/subscribe 

Follow him on X: https://twitter.com/danshipper 

Links to resources mentioned in the episode:

Jared Zoneraich: @imjaredz

PromptLayer: @promptlayer, https://www.promptlayer.com/

A couple of Steven Wolfram’s articles on ChatGPT: What Is ChatGPT Doing … and Why Does It Work?, ChatGPT Gets Its “Wolfram Superpowers”!   

Notion cofounder Simon Last told me everything he’s learned from integrating an AI application into a platform that has over 100 million users.

Simon likes to keep a low profile, even though he’s the driving force behind Notion AI, one of the most widely scaled AI applications in the world.

In this episode, we get into how AI changes the way he builds software since the days he cofounded Notion with Ivan Zhao in 2013. He talks about the challenges that arise because AI doesn’t follow the deterministic rules of traditional software, and how he designs evals to build AI systems that are reliable at scale. Simon tells me about the AI tools he uses to code and how he would think about rebuilding Notion from scratch with them. He also shares his thoughts on how the growing capabilities of AI are redefining human roles, and argues that we have the responsibility to shape technology to align with our collective vision of the future. 

This is a must-watch for anyone interested in building reliable AI products at scale.

If you found this episode interesting, please like, subscribe, comment, and share! 

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

Subscribe to Every: https://every.to/subscribe 

Follow him on X: https://twitter.com/danshipper 

Links to resources mentioned in the episode:

Simon Last: @simonlast

Notion AI: https://www.notion.so/product/ai 

The AI code editor Simon uses: Cursor

OpenAI’s definition of AGI that Simon ascribes to: https://openai.com/charter/ 

Union Square Ventures is building an AI operating system to support their investment team. 

But it’s not what you think: It’s a constellation of AI tools that captures and synthesizes the firm's collective wisdom. It’s evolving every day, and Matt Cynamon is the mad scientist in charge

Matt calls himself a “regular” at USV. In practice that means he’s responsible for running experiments with AI for the firm. As an inherently curious person with the professional obligation to tinker, he’s built a suite of tools for the firm, including: 

• The Librarian, a chatbot trained on around 15,000 articles from USV’s blog
• Portfolio Tracker, a GPT that analyzes the investments made by the firm
• Meeting Notes, a tool that makes it possible for team members to interact with meetings  

I sat down with Matt to talk about how AI is enabling him to bring his ideas to life as a generalist, get demos of the tools listed above, and exchange notes on all the other projects he has in the works at USV. We edit actionable insights extracted by an AI from meetings at USV and prepare them to be posted on the firm’s X handle live on the show. We even try out an art project at USV’s office called The Dream Machine, which generates art from conversations. Here’s a link to the episode transcript.   

This is a must-watch for anyone interested in riding the AI wave by learning how to ship useful products quickly.

If you found this episode interesting, please like, subscribe, comment, and share! 

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

Subscribe to Every: https://every.to/subscribe 

Follow him on X: https://twitter.com/danshipper 

TIMESTAMPS:

1. Introduction: 00:00:52
2. How Matt became in charge of everything AI at USV: 00:01:56
3. How AI empowers generalists to be creators: 00:06:22
4. The Librarian, a chatbot trained on everything USV has published: 00:10:41
5. Portfolio Tracker, an AI tool to track USV’s investments: 00:21:09
6. The AI projects that Matt has in the pipeline at USV: 00:27:21
7. Meeting Notes, USV’s AI note-taking tool: 00:34:33
8. Prompting AI to generate a post for USV’s X handle: 00:44:57 
9. Why it’s important to diversify ownership over data: 01:00:20
10. The Dream Machine, AI that generates images from conversations: 01:03:20

Links to resources mentioned in the episode:

Matt Cynamon: @mattcynamon

Union Square Ventures: @usv, https://www.usv.com/ 

More about the AI tools at USV: https://www.usv.com/people/the-librarian/, https://www.usv.com/writing/2024/02/ai-aesthetics/ 

The X post generated live on the show: https://x.com/usv/status/1847354782941663523  

Yohei Nakajima⁠ leads a double life. 

By day, he’s a general partner of a small venture firm, ⁠Untapped Capital⁠. 

By night, he’s one of the most prolific internet tinkerers in AI. (He also sometimes works on ⁠automating his job as a venture capitalist.)

He’s the creator of BabyAGI (@babyAGI_), the first open-source autonomous agent that went viral in March 2023. Yohei has since released seven iterations of BabyAGI, a coding agent called Ditto, a framework for building autonomous agents, and, most recently, BabyAGI 2o, a self-building autonomous agent.

I sat down with Yohei to talk about:

• What feeds Yohei’s drive to create new tools
• The evolution of BabyAGI into a more powerful version of itself 
• What Yohei learned about himself by tinkering on the internet
• Yohei’s personal philosophy about how the tools we build our extensions of ourselves
• Why founders in AI should think about their products from a modular lens, by addressing immediate problems while enabling growth in the future
• Yohei’s insight into a future where models will train themselves as you use them

We experiment with Ditto live on the show, using the tool to build a game of Snake and a handy scheduling app. Yohei also screenshares a demo of BabyAGI 2o in action.

If you found this episode interesting, please like, subscribe, comment, and share! 

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT here: ⁠https://every.ck.page/ultimate-guide-to-prompting-chatgpt⁠. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

• Subscribe to Every: ⁠https://every.to/subscribe⁠ 
• Follow him on X: ⁠https://twitter.com/danshipper⁠ 

Timestamps:

1. Introduction: 00:00:59
2. BabyAGI and its evolution into a more powerful tool: 00:02:26
3. How better models are changing the way Yohei builds: 00:05:00
4. Using code building agent Ditto to build a game of Snake: 00:08:10
5. The ins and outs of how Ditto works: 00:13:24
6. How Yohei gets a lot done in little time: 00:19:21
7. Yohei’s personal philosophy around building AI tools: 00:21:50
8. How Yohei experiments with AI as a tech-forward parent: 00:33:13
9.  Demo of Yohei’s latest release, BabyAGI 2o: 00:39:29
10.  Yohei’s insights on the future of AI tooling: 00:51:24

Links to resources mentioned in the episode: 

• Yohei Nakajima: @yoheinakajima, ⁠http://yohei.me⁠ 
• Untapped Capital: @UntappedVC, ⁠https://www.untapped.vc/⁠ 
• My first interview with Yohei, around the time he released BabyAGI: ⁠https://every.to/chain-of-thought/this-vc-is-slowly-automating-their-job⁠ 
• The other AI tools Yohei has created: ⁠Ditto⁠, BabyAGI 2, BabyAGI 2o
• The tweet thread about AI bots being let loose on a Discord server: https://x.com/AISafetyMemes/status/1847312782049333701