The Every Podcast

We had ⁠Dean Leitersdorf⁠ on the pod and he did something no guest had ever done.

Mid-sentence, he transformed from a startup founder in a black t-shirt to a wizard with light shooting from his hands. Then, he was in a white-walled game universe, and when he picked up the tissue box on his table, it morphed into a gun which he could shoot by moving his arm.

He did it with one of his products, ⁠Mirage⁠: It takes any live video feed (like Dean on the pod) and instantly renders each frame into a new style of your choosing—40 milliseconds from input to output.

Dean is the co-founder and CEO of the creators of ⁠Decart⁠ which makes Mirage. They recently raised $100 million at a $3.1 billion valuation to build a new era of real-time generative AI experiences like this.

Realtime generative video models are going to change video games forever, and Dean is on the forefront: imagine creating endless variations on existing titles, like GTA-V with a frigid winter filter, or taking a bare-bones vibe-coded prototype and using Mirage to texture it. 

But games are just the beginning, Dean sees Mirage as opening the door to a new medium, a new experience created by AI. 

In this episode, we take a look at how Mirage works under the hood, and what the Decart team learned about the future of software while wrestling with its toughest research problems. We also debate AGI—how close it really is, what counts as progress, and what kind of society it might create. This episode is a must watch for anyone interested in the future of gaming, creativity, or if you just want your mind blown by what’s already possible. 

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: 

• Introduction: 00:00:47
• A demo of Mirage, the first real-time video-to-video model in the world: 00:02:38
• How Mirage can take your vibe-coded game to the next level: 00:06:22
• The new architecture of modern software: 00:08:45
• How Mirage works so blazingly fast: 00:16:34
• Inside Decart’s invention of a new “live stream diffusion” model: 00:20:33
• Solving the error accumulation problem for real-time video: 00:21:17
• How Dean thinks about inventing a new creative medium: 00:29:55
• Dean’s take on the post-AGI world: 00:39:43
• Why AI brings back the age of the generalist: 00:51:15

Links to resources mentioned in the episode:

• Dean Leitersdorf: @DLeitersdorf
• Decart: ⁠https://about.decart.ai/⁠ 
• Try Mirage and Delulu: ⁠https://mirage.decart.ai/⁠, ⁠https://play.google.com/store/apps/details?id=ai.decart.delulu⁠, ⁠https://apps.apple.com/il/app/delulu-by-decart/id6749955738⁠  
• More about Yan LeCun’s error accumulation problem: ⁠https://x.com/ylecun/status/1640123182983045120⁠ 

AGI is coming. Reid Hoffman just wrote the book on how to prepare.

According to Reid, every major tech breakthrough (the written word, the printing press, the telephone) triggered mass fear. But, contrary to our worries, new technology tends to enhance human agency—even more so, if you know how to use it well.

Reid is the cofounder of LinkedIn, Inflection AI, and Manas AI; a partner at venture capital firm Greylock Partners; an early backer and board member of OpenAI; and an award-winning podcaster

We spent an hour talking about how to develop a compass for navigating AGI. Here are a few takeaways:
Our sense of human agency is not just about external control but an internal stance—how we approach uncertainty & new tech is crucial
In new technology waves, NO blueprint or plan will have the right answers. Instead, adapting to new technology requires broad access, an experimental mindset, and flexibility
In an AGI world most jobs will transform, not disappear—and how you can prepare with hands-on trial and error
How certain social norms and ethics should change as AGI changes the landscape—like individual access to personal data
Why now may be finally be the era where quantified self tools become valuable
…and more, including everything in his new book Superagency, out this week.

It was a pleasure to have him on the show for a second time. This is a must-watch for anyone who wants to help build a more human future with 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 here: https://every.ck.page/ultimate-guide-.... 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:   / danshipper

Sponsor:
Attio is the AI-native CRM built for the next era of companies. With Attio, setup takes minutes. Connect your email and calendar, and it instantly builds a CRM that mirrors your business. Go to https://www.⁠⁠⁠⁠attio.com/every to get 15% off on your first year.

Timestamps:
00:00:00 — Episode Start
00:01:29 — Introduction
00:02:50 — Patterns in how we've historically adopted technology
00:07:02 — Why humans have typically been fearful of new technologies
00:13:25 — How Reid developed his own sense of agency
00:20:08 — The way Reid thinks about making investment decisions
00:22:00 — Attio: Go to⁠⁠⁠⁠ https://attio.com/every⁠⁠⁠⁠⁠ and get 15% off your first year on your AI-powered CRM.
00:29:40 — AI as a "techno-humanist" compass
00:35:30 — How to prepare yourself for the way AI will change knowledge work
00:41:39 — Why equitable access to AI is important
00:45:15 — Reid's take on why private commons will be beneficial for society
00:47:23 — How AI is making Silicon Valley's conception of the "quantified self" a reality
00:52:14 — The shift from symbolic to sub-symbolic AI mirrors how we understand intelligence
01:03:29 — Reid's new book, Superagency

Links to resources mentioned in the episode:
Reid Hoffman: @reidhoffman Superagency, Reid’s newest book: https://www.superagency.ai/

**Automate 80% of your repetitive writing, thinking, and creative tasks**
**Try Spiral made by Dan Shipper & Every: https://spiral.computer?utm_source=youtube**

Claire Vo built ChatPRD—an on-demand chief product officer powered by AI. It’s now used by over 10,000 product managers and is pulling in six figures in revenue. 

The best part?

Claire has a demanding day job as the CPO at LaunchDarkly. So she built all of ChatPRD herself—over the weekend—with AI.

I sat down with Claire to talk about how ChatPRD works, how she built it as a side hustle using AI, and all of the ways she’s using AI tools to accelerate her work and life. 

We get into:

- How she used AI to build ChatPRD over Thanksgiving break
- The part of product management that Claire thinks AI will disrupt
- Why the PMs of tomorrow will be “proto-managers” who create prototypes rather than just specs
- How junior PMs can use AI to upskill faster
- The ways in which ChatPRD is baked into her own workflow
- How building ChatPRD is making Claire a better PM
- How Claire uses AI as a tech-forward parent

This is a must-watch for anyone interested in turning their side hustle into a thriving business or who works in product.

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

Thanks to Google and LTX Studio for sponsoring this episode!

The Gemini 2.5 family of models is now generally available. 2.5 Pro, the most advanced model, is great for reasoning over complex tasks; next up, 2.5 Flash finds the sweet spot between performance and price; and finally, 2.5 Flash Lite is ideal for low-latency, high-volume tasks. Start building in Google AI Studio at ⁠https://ai.dev/⁠

LTX Studio is helping storytellers go from concept to delivery in one seamless platform. Whether you're storyboarding your next film, prototyping ad concepts, or creating pixel-ready assets, LTX Studio allows you to fully realize your imaginations. Check them out here: ⁠https://tinyurl.com/2d5nx3ut⁠

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

Links to resources mentioned in the episode:
- Claire Vo: https://x.com/clairevo; @chiefproductofficer
- ChatPRD: https://www.chatprd.ai/; https://x.com/chatprd; https://www.linkedin.com/company/chatprd/; https://www.youtube.com/@ChatPRD    
- Some of the AI tools that Claire used to build ChatPRD: http://Clerk.dev; https://tiptap.dev/ 
- Greeking Out, the Greek mythology podcast that Claire’s son enjoys: https://www.nationalgeographic.com/podcasts/greeking-out

Read Dan Shipper's essay on the allocation economy: https://every.to/chain-of-thought/the-knowledge-economy-is-over-welcome-to-the-allocation-economy

Guillermo Rauch is one of the most prolific coders of this generation. 

But he doesn’t think of himself as a coder anymore. 

Coding, he says, is a specific skill that AI is becoming great at. Instead, he thinks the future of coding is more holistic, full-stack engineers who can ideate, design, and execute all together. 

Guillermo is the founder and CEO of Vercel, the creator of NextJS, and SocketIO. We spent an hour talking about the future of software development in an AI world—and the meta-skills that are essential for the coders of today to master—in order to use tomorrow’s tools to their fullest extent.

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

Sponsors:

LTX Studio is helping storytellers go from concept to delivery in one seamless platform. Whether you're storyboarding your next film, prototyping ad concepts, or creating pixel-ready assets, LTX Studio allows you to fully realize your imaginations. Check them out here: https://tinyurl.com/2d5nx3ut

Attio is the AI-native CRM built for the next era of companies. With Attio, setup takes minutes. Connect your email and calendar, and it instantly builds a CRM that mirrors your business. Go to https://www.⁠⁠⁠⁠attio.com/every to get 15% off on your first year.

Want even more?
Read Dan Shipper's essay on developing taste with AI: https://every.to/chain-of-thought/what-i-do-when-i-can-t-sleep

Try Cora to manage your email with AI: https://cora.computer
Try Spiral to repurpose content with AI: https://spiral.computer
Try Sparkle to organize your files with AI: https://makeitsparkle.co

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
00:00:00 - Episode start
00:01:33 - Introduction
00:03:18 - How to spot trends early
00:07:34 - Why you should be your own customer
00:14:55 - How to create an ecosystem of talent and ambition
00:17:29 - Why Guillermo doesn't identify as a coder
00:20:50 - AI is gearing us toward an allocation economy
00:28:34 - How Vercel's copilot compares with other coding agents
00:40:35 - Guillermo's advice on having better taste
00:42:46 - The future of AI agents is specialized
00:47:50 - How AI startups can compete with big tech

Links to resources mentioned in the episode:
Guillermo Rauch: @rauchg
Vercel: https://vercel.com/ 
Last week’s episode with Nabeel Hyatt: https://every.to/podcast/the-venture-capitalist-who-only-makes-two-bets-a-year
Dan’s essay about the allocation economy: https://every.to/chain-of-thought/the-knowledge-economy-is-over-welcome-to-the-allocation-economy

Dwarkesh Patel is on a quest to know everything. 

He’s using LLMs to enhance how he reads, learns, thinks, and conducts interviews. 

Dwarkesh is a podcaster who’s interviewed a wide range of people, like Mark Zuckerberg, Tony Blair, and Marc Andreesen. Before conducting each of these interviews, Dwarkesh learns as much as he can about his guest and their area of expertise—AI hardware, tense geopolitical crises, and the genetics of human origins, to name a few. 

The most important tool in his learning arsenal? AI—specifically Claude, Claude Projects, and a few custom tools he’s built to accelerate his workflow.

He does this by researching extensively, and as his knowledge grows, each piece of new information builds upon the last, making it easier and easier to grasp meaningful insights. 

In this interview, I turn the tables on him to understand how the prolific podcaster uses AI to become a smarter version of himself. We get into:

How he uses LLMs to remember everything
His podcast prep workflow with Claude to understand complex topics
Why it’s important to be an early adopter of technology
His taste in books and how he uses LLMs to learn from them
How he thinks about building a worldview 
His quick takes on the AI’s existential questions—AGI and P(doom)

We also use Claude live on the show to help Dwarkesh research for an upcoming podcast recording.

This is a must-watch for curious people who want to use AI to become smarter.

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

Sponsor: 
Gemini: Experience high quality AI video generation with Google's most capable video model: Veo 3. Try it in the Gemini app at gemini.google with a Google AI Pro plan or get the highest access with the Ultra plan.

Want even more?
Sign up for Every to unlock our ultimate guide to prompting ChatGPT here: https://every.ck.page/ultimate-guide-.... 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:   / danshipper   

Timestamps:
00:00:00 - Teaser
00:01:44 - Introduction 
00:05:37 - How Dwarkesh uses LLMs to remember everything 
00:11:50 - Dwarkesh's taste in books and how he uses AI to learn from them 
00:17:58 - Why it's important to be an early adopter of technology 
00:20:44 - How Dwarkesh uses Claude to understand complex concepts
00:26:36 - Dwarkesh on how you can compound your intelligence 
00:28:21 - Why Dwarkesh is on a quest to know everything 
00:39:19 - Dan and Dwarkesh prep for an upcoming interview 
01:04:14 - How Dwarkesh uses AI for post-production of his podcast 
01:08:51 - Rapid fire on AI's biggest questions—AGI and P(doom)

Links to resources mentioned in the episode:
Dwarkesh Patel:   / dwarkesh_sp  
Dwarkesh’s podcast and newsletter: https://www.dwarkeshpatel.com/; https://substack.com/@dwarkesh 
Dwarkesh’s interview with researcher Andy Matuschak on spaced repetition: https://www.dwarkeshpatel.com/p/andy-... 
The book about technology and society that both Dan and Dwarkesh are reading: Medieval Technology and Social Change
Dan’s interview with Reid Hoffman: https://every.to/chain-of-thought/rei... 
The book by Will Durant that inspires Dwarkesh: Fallen Leaves https://www.amazon.com/Fallen-Leaves-... 
One of the most interesting books Dwarkesh has read: The Great Divide https://www.amazon.com/Great-Divide-N...
Upcoming guests on Dwarkesh’s podcast: David Reich  https://reich.hms.harvard.edu/ and Daniel Yergin https://www.danielyergin.com/

The smallest technical decisions become humanity's biggest pivots:

The same-origin policy—a well-intentioned browser security rule from the 1990s—accidentally created Facebook, Google, and every data monopoly since. It locks your data in silos—and you stayed where your stuff already is. This dynamic created aggregators.

Alex Komoroske—who led Chrome's web platform team at Google and ran corporate strategy at Stripe—saw this pattern play out firsthand. And he's obsessed with the tiny decisions that will shape AI's next 30 years:

Whether AI keeps memory centrally or user-controlled?

Is AI free/ad-supported or user-paid?

Should AI be engagement-maximizing or intention-aligned?

How should we handle prompt injection in MCP and agentic systems?

Should AI be built with AOL-style aggregation or web-style openness?

This is a much-watch if you care about the future of AI and humanity.

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 

Sponsors: 
Google Gemini: Experience high quality AI video generation with Google's most capable video model: Veo 3. Try it in the Gemini app at gemini.google with a Google AI Pro plan or get the highest access with the Ultra plan.

Attio: Go to⁠⁠⁠⁠ https://attio.com/every⁠⁠⁠⁠⁠ and get 15% off your first year on your AI-powered CRM.

Timestamps:

1. Introduction: 00:01:45
2. Why chatbots are a feature not a paradigm: 00:04:25
3. Toward AI that’s aligned with our intentions: 00:06:50
4. The four pillars of “intentional technology”: 00:11:54
5. The type of structures in which intentional technology can thrive: 00:14:16
6. Why ChatGPT is the AOL of the AI era: 00:18:26
7. Why AI needs to break out of the silos of the early internet: 00:25:55
8. Alex’s personal journey into systems-thinking: 00:41:53
9. How LLMs can encode what we know but can’t explain: 00:48:15
10. Can LLMs solve the coordination problem inside organizations: 00:54:35
11. The under-discussed risk of prompt injection: 01:01:39

Links to resources mentioned in the episode:

• Alex Komoroske: @komorama
• Common Tools: https://common.tools/ 
• The public Google document with Alex’s raw ideas and thoughts: Bits and Bobs
• A couple of Alex’s favorite books: Why Information Grows by Cesar Hidalgo and The Origin of Wealth by Eric Beinhocker

If you had millions of people using a product you spent years building, would you kill it?

That’s exactly what The Browser Company did with Arc.

The internet backlash was intense, but cofounders Josh Miller and Hursh Agrawal saw that AI was about to make the web something you talk to, not just click into. The best home for that assistant was the thing that's already between you and the internet—the browser. And they realized they couldn’t just duct-tape it on to Arc.

One year of heads-down work later, the team launched Dia in beta, and people are raving about it. Dia is a sleek, fast, browser with AI at its core—it gets better with every tab you open, becoming more and more helpful with time. 

And even though it’s still early, Josh and Hursh’s big pivot looks like one for the ages.

This week on AI & I, Josh and Hursh joined me for their first full-length podcast about their pivot from Arc to Dia. We talk through their decision-making process, the very public backlash the company faced, and the grit it took to stay the course. 

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 

Sponsor:
Attio: Go to⁠⁠⁠⁠ https://attio.com/every⁠⁠⁠⁠⁠ and get 15% off your first year on your AI-powered CRM.

Timestamps:

1. Introduction: 00:01:13
2. The story of how Dan might’ve been the CEO of The Browser Company: 00:02:47
3. The moment Josh and Hursh knew they had to walk away from Arc: 00:09:42
4. How to handle the weight of the unknown in a pivot: 00:17:08
5. The prototype-driven culture that kept The Browser Company alive: 00:23:31
6. Why having a product loved by millions of users isn’t enough :00:25:42
7. The architectural decisions underlying how Dia was built: 00:33:29
8. How Dia almost shipped without its best feature: 00:47:12
9. The best ways people are using Dia in the wild: 00:51:18
10. How Josh and Hursh think about competing with incumbents: 01:07:55
11. How romanticism informs the product decisions behind Dia: 01:17:04

Links to resources mentioned in the episode:

• Hursh Agrawal: @hursh
• Josh Miller: @joshm
• More about Dia: https://www.diabrowser.com/ 
• Writer and investor M.G. Siegler’s essay about the AI browser wars: https://spyglass.org/ai-browser-wars/ 

You don’t need to handle your inbox anymore. It’s Cora’s job now. 

Cora is the AI chief of staff we built for your email at Every. It’s been in private beta for the last 6 months and currently manages email for 2,500 beta users—and today we’re making it available for anyone to use. Start your free 7-day trial by going to: https://cora.computer/

Cora is the $150K executive assistant that costs $15/month. Or $20/month if you want an Every subscription, too. This is what that actually means:

• Cora understands what’s important to you, screens your inbox, and only lets the most relevant emails through. 
• The rest of your emails are summarized in a beautifully designed brief that’s sent to you twice a day.
• If it has enough context, Cora drafts replies for you in your voice.
• You can talk to Cora like you would your chief of staff—you can give it special instructions on how you want certain emails handled, ask it to summarize things, and even give you an opinion on complex decisions.

In this episode of AI & I, I sat down with the team behind Cora—⁠Brandon Gell⁠, head of the product studio; ⁠Kieran Klaassen⁠, Cora’s general manager; and ⁠Nityesh Agarwal⁠, engineer at Cora—for a closer look at how it all came together. We talk about:

• The story of the first time Brandon, Kieran, and I used Cora, while sipping wine at the Every retreat in Nice. 
• The evolution of Cora’s categorization system, from a 4-hour vibe-coded prototype to a multi-faceted product with thousands of happy users.
• The features on Cora’s roadmap we’re most excited about: a unified brief across different email accounts, an iOS app, and an even more powerful assistant.

This is a must-watch if you’re curious about what it feels like to give Cora your inbox, and take back your life. Go to https://cora.computer/ to start your 7-day free trial now.

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.

Sponsor: Experience high quality AI video generation with Google's most capable video model: Veo 3. Try it in the Gemini app at gemini.google with a Google AI Pro plan or get the highest access with the Ultra plan.

To hear more from Dan Shipper:

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

Timestamps:

1. Introduction: 00:01:40
2. Three ways Cora transforms your inbox (and your day): 00:04:21
3. A live walkthrough of Cora’s features: 00:05:09
4. The inside story of the first time Kieran, Brandon, and Dan used Cora: 00:12:13
5. Train Cora like you would a trusted chief of staff: 00:16:30
6. The AI tools that blew our minds while building Cora: 00:27:25
7. How we build workflows that compound with AI at Every: 00:30:34
8. The dream features that we’d like to put on Cora’s roadmap: 00:42:36

Links to resources mentioned in the episode:

• Try Cora now with a 7-day free trial: cora.computer 
• The episode about how Kieran and Nityesh use Claude Code to build Cora: ⁠"How Two Engineers Ship Like a Team of 15 With AI Agents"⁠ 

Joe Hudson is a coach who works with the executives building AGI at OpenAI. 

From inside OpenAI, he witnesses the full spectrum of human emotion that comes with bringing something new into the world—the exhilaration, the terror, the weight of it all. He feels these emotions, too: He believes AI will eventually replace what he does as a coach.

But instead of fixating on that fear, Hudson is asking a deeper question: Who is he becoming in the meantime? He believes that moments like this—when we can feel the ground quiver—can be powerful catalysts for transformation, but only if we’re willing to face the uncertainty they bring.

In this episode of AI & I, Dan Shipper sits down with Hudson to talk about how he’s answering that question. They get into what happens when the thing you’ve built your life around might disappear, how to find who you are beneath your professional identity, and why Hudson believes intention is the key to growing with 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 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

Sponsors: 

Google Gemin: Experience high quality AI video generation with Google's most capable video model: Veo 3. Try it in the Gemini app at ⁠gemini.google⁠ with a Google AI Pro plan or get the highest access with the Ultra plan.

Attio: Go to⁠⁠⁠⁠ ⁠https://attio.com/every⁠⁠⁠⁠⁠⁠ and get 15% off your first year on your AI-powered CRM.

Timestamps:

1. Introduction: 00:01:49
2. What it feels like inside the room where AGI is being built: 00:03:14
3. The most important question to ask yourself as AGI approaches: 00:08:15
4. The importance of sitting with uncertainty: 00:17:49
5. How Joe is preparing his daughters for a post-AGI world: 21:11:04
6. How we think, feel, and react; the three layers of human awareness: 27:25:01
7. Staying grounded while coaching the people shaping our future: 35:34:04
8. Why Joe doesn’t take things personally—even when the stakes are high: 42:44:03

Links to resources mentioned in the episode:

• Joe Hudson: @FU_joehudson; 
• Learn more about the coaching and workshops that Joe runs: Art of Accomplishment

If you’re using AI to just write code, you’re missing out.

Two engineers at Every shipped six features, five bug fixes, and three infrastructure updates in one week—and they did it by designing workflows with AI agents, where each task makes the next one easier, faster, and more reliable.

In this episode of AI & I, Dan Shipper interviewed the pair—Kieran Klaassen, general manager of Cora, our inbox management tool, and Cora engineer Nityesh Agarwal—about how they’re compounding their engineering with AI. They walk Dan through their workflow in Anthropic’s agentic coding tool, Claude Code, and the mental models they’ve developed for making AI agents truly useful. Kieran, our resident AI-agent aficionado, also ranked all the AI coding assistants he’s used.

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   

Sponsors:
Microsoft Teams
Want seamless collaboration without the cost? Microsoft Teams offers a robust free plan for individuals that delivers unlimited chat, 60-minute video meetings, and file sharing—all within one intuitive workspace that keeps your projects moving forward. Head to ⁠https://aka.ms/every⁠ to use Teams for free, and experience effortless collaboration, today.

Attio: Go to⁠⁠⁠⁠ https://www.⁠⁠⁠⁠attio.com/every⁠⁠⁠⁠⁠ and get 15% off your first year on your AI-powered CRM.

Timestamps:

1. Introduction: 00:01:16
2. Why Kieran believes agents are turning a corner: 00:03:18
3. Why Claude Code stands out from other agents: 00:06:36
4. What makes agentic coding different from using tools like Cursor: 00:11:58
5. The Cora team’s workflow to turn tasks into momentum: 00:15:20
6. How to build a prompt that turns ideas into plans: 00:23:07
7. The new mental models for this age of software engineering: 00:34:00
8. Why traditional tests and evals still matter: 00:39:13
9. Kieran ranks all the AI coding agents he’s used: 00:42:00

Links to resources mentioned in the episode:

• Try Cora, our AI email assistant: https://cora.computer/  
• Kieran Klaassen: @kieranklaassen
• Nityesh Agarwal: @nityeshaga
• The book that helps Nityesh form mental models to work with AI agents: High Output Management
• A guide to Anthropic’s prompt improver: https://www.anthropic.com/news/prompt-improver