The world changed last week—Opus 4.5 is the best coding model Dan has ever used.

It can keep coding and coding autonomously without tripping over itself—and it marks a completely new horizon for the craft of programming. The dream is here: You can write English, and make software.

We had Paul Ford on AI & I to talk about it. Ford is the co-founder of Aboard and also a prolific writer. He authored one of Dan’s favorite pieces of technology writing What Is Code?—so he’s the perfect person to unpack this with him.

We talk about the wonder—and genuine unease—that comes with using tools this powerful. We also get into what people who love technology should care about as the ground under us shifts faster than we can imagine.

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

Head to ai.studio/build to create your first app

Ready to build a site that looks hand-coded—without hiring a developer? Launch your site for free at Framer.com, and use code DAN to get your first month of Pro on the house!

Timestamps:

00:00:00 - Start

00:01:57 - Introduction

00:03:28 - How Claude Opus 4.5 made the future feel abruptly close

00:08:12 - The design principles that make Claude Code a powerful coding tool

00:10:57 - How Ford uses Claude Code to build real software

00:20:12 - Why collapsing job titles and roles can feel overwhelming

00:22:56 - Ford’s take on using LLMs to write

00:24:09 - A metaphor for weathering existential moments of change

00:25:45 - What GLP-1s taught Ford about how people adapt to big shifts

00:49:36 - Why you should care what your LLM was trained on

00:52:15 - Ford prompts Claude Code to forecast the future of the consulting industry

00:59:18 - Recognize when an LLM is reflecting your assumptions back to you

01:12:39 - How large enterprises might adopt AI

Links to resources mentioned in the episode:

• Paul Ford: Paul Ford
• Ford’s company Aboard: https://aboard.com/
• The piece Ford wrote for Bloomberg in 2015: What Is Code?
• Alan Kay’s concept of a personal computer for children: https://en.wikipedia.org/wiki/Dynabook

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.

Originally recorded in July before The Browser Company’s acquisition by software giant Atlassian earlier this year, we’re republishing this episode because its lessons are truly timeless. Today, the team continues to operate independently under Atlassian’s umbrella.

The internet backlash when the company killed Arc in May 2025 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.

In this episode of AI & I, Josh and Hursh spoke for the first time in a full-length podcast about their pivot from Arc to Dia. We talked 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

Timestamps:

00:00:00 - Start

00:00:48 - Introduction

00:02:22 - The story of how Dan might've been the CEO of The Browser Company

00:09:40 - The moment Josh and Hursh knew they had to walk away from Arc

00:16:59 - How to handle the weight of the unknown in a pivot

00:23:24 - The prototype-driven culture that kept The Browser Company alive

00:25:06 - Why having a product loved by millions of users isn't enough

00:32:12 - The architectural decisions underlying how Dia was built

00:46:04 - How Dia almost shipped without its best feature

00:50:45 - The best ways people are using Dia in the wild

01:07:27 - How Josh and Hursh think about competing with incumbents

01:17:13 - How romanticism informs the product decisions behind Dia

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/

Note: This episode is a rerun from our archives.

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

Head to ai.studio/build to create your first app.

Pitch is the AI presentation platform that helps professionals collaborate on, create, and deliver winning slide decks — all while staying on brand: https://pitch.com/use-cases/ai-presentation-maker/?utm_medium=paid-influencer&utm_campaign=every

Timestamps:

Episode start: 00:00:00

Introduction: 00:01:16

Why Kieran believes agents are turning a corner: 00:03:18

Why Claude Code stands out from other agents: 00:06:36

What makes agentic coding different from using tools like Cursor: 00:11:58

The Cora team’s workflow to turn tasks into momentum: 00:15:20

How to build a prompt that turns ideas into plans: 00:23:07

The new mental models for this age of software engineering: 00:34:00

Why traditional tests and evals still matter: 00:39:13

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

Henrik Werdelin wants to launch a million businesses that each make $1M—and he’s doing it with AI.

After helping launch Barkbox and Ro Health through his incubator Prehype, Henrik is distilling everything he knows into Audos, a platform that helps you use AI agents to turn your idea into a profitable, lasting company.

We had him on AI & I to talk about “portfolio entrepreneurship”—a new breed of entrepreneurship shepherded in by AI, where founders build families of products around the same customer, instead of one moonshot idea. It’s a philosophy we hold close to our hearts 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 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

Head to ai.studio/build to create your first app.

Ready to build a site that looks hand-coded—without hiring a developer? Launch your site for free at https://www.framer.com/*, and use code DAN to get your first month of Pro on the house!*

Pitch is the AI presentation platform that helps professionals collaborate on, create, and deliver winning slide decks — all while staying on brand: https://pitch.com/use-cases/ai-presentation-maker/?utm_medium=paid-influencer&utm_campaign=every !

Timestamps:

00:01:33 - Introduction

00:02:50 - Dan and Henrik on the new breed of entrepreneurship that AI makes possible

00:11:08 - Why Henrik believes the future belongs to a million $1M companies

00:16:14 - How to build “relationship capital” with your customers

00:21:35 - Why “customer-founder fit” shapes lasting companies

00:23:01 - Everything Henrik learned about himself from a decade of building companies

00:31:44 - How Henrik finds focus and meaning in the daily chaos

00:34:17 - How Henrik is parenting two kids in the age of AI

00:50:33 - The way AI can fix what social media broke

00:56:59 - What happens when AI agents become part of how we tell stories

Links to resources mentioned in the episode:

• Henrik Werdelin: Henrik Werdelin
• Try Audos: Audos
• Henrik’s new book: Me, My Customer, and AI

37signals makes tens of millions in profit every year but Jason Fried isn’t all that interested in running a business.

Instead, he cares most about making great products—like Basecamp, HEY, and Ruby on Rails—products that are centered around a single, coherent idea. These products are complete wholes, where each piece matters—like a Frank Lloyd Wright house or a vintage car.

But how do you create products like that?

In this conversation, we talk to Jason about what two decades of building 37signals has been like—and how to build products that have soul.

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

Listen to Working Smarter wherever you get your podcasts, or visit workingsmarter.ai

Timestamps:

00:00:00 - Start

00:00:32 - Introduction

00:02:06 - What architecture, watches, and cars teach us about software

00:10:54 - How Jason thinks AI plays into product-building

00:20:58 - How developers at 37signals use AI

00:25:47 - Jason’s biggest realization after 26 years of running 37signals

00:29:58 - Where Jason thinks luck shaped his career

00:32:41 - What Jason would do if he were graduated into the AI boom

00:37:22 - Dan asks for advice on running a non-traditional company like Every

00:46:39 - Why staying true to yourself is the only way to build something lasting

00:49:38 - Wholeness as the north star for building products—and companies

Links to resources mentioned in the episode:

• Jason Fried: Jason Fried (@jasonfried), Jason Fried
• More about 37Signals: 37signals
• The book about architecture by Christopher Alexander: The Timeless Way of Building

This episode contains sponsored content in partnership with Salesforce.

At Dreamforce 2025, Every CEO Dan Shipper sat down with Silvio Savarese, chief AI scientist at Salesforce, to discuss how one of the world’s largest software companies is shaping the future of AI for the enterprise.

Together, Dan and Savarese explore how his team at Salesforce develops AI solutions that now power more than 13,000 businesses—including OpenAI, Dell, and FedEx—helping them become truly Agentic Enterprises that operate with greater scale, speed, and precision. Examples include a large language model built for Salesforce developers years before ChatGPT’s release, and Agentforce, the company’s agentic layer that enables a hybrid future of work where humans and AI agents collaborate to achieve more than either could alone.

They also discuss how Agentforce gives enterprises a deeply unified AI platform that connects their data with agent functionality—making it both powerful and practical. The conversation touches on how Salesforce builds trust with enterprise customers amid the jagged frontier of AI by ensuring consistency in results, while continuing to push the boundaries of what agents can do autonomously. Savarese shares how enterprise-grade simulation environments help them strike that balance, and reflects on how AI agents will ultimately transform how businesses and individuals alike get things done.

@Salesforce #SalesforcePartner #DF25

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:

00:00 – Start

01:16 – Inside Salesforce’s early AI innovations

02:50 – How Agentforce works and what it can do

07:03 – The real challenges of deploying AI at scale

08:57 – Why Salesforce builds simulation environments for AI

12:35 – The future of agents and enterprise AI

At Every, the team credits Claude Code with transforming the way they work.

They now ship to codebases they barely know, each new feature makes the next easier to build, and even non-technical teammates confidently use the terminal.

To explore how this happened, AI & I host Dan Shipper invited Claude Code’s creators—Cat Wu (@_catwu) and Boris Cherny (@bcherny) from Anthropic AI—to discuss what they’ve learned from building one of the most beloved AI engineering tools in the world.

This episode is a must-watch for anyone—technical or not—who wants to understand how to use Claude Code like the people who built 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 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/subscribeFollow him on X: https://twitter.com/danshipper

Build your first AI-powered app at ai.studio/build.

Timestamps:

00:00:00 - Start

00:01:26 - Introduction

00:02:25 - Claude Code’s origin story

00:07:03 - How Anthropic dogfoods Claude Code

00:14:06 - Boris and Cat’s favorite slash commands

00:15:49 - How Boris uses Claude Code to plan feature development

00:21:53 - Everything Anthropic has learned about using sub-agents well

00:26:16 - Use Claude Code to turn past code into leverage

00:33:14 - The product decisions for building an agent that’s simple and powerful

00:36:38 - Making Claude Code accessible to the non-technical user

00:45:12 - The next form factor for coding with AI

Links to resources mentioned in the episode:

• Cat Wu: cat (@_catwu)
• Boris Cherny: Boris Cherny (@bcherny)
• Claude Code: https://www.claude.com/product/claude-code

Good writing has always been downstream of good thinking. The average language model can help you write faster—but can it help you think better?

Danny Aziz wrestled with this question while building the new version of Spiral, an AI writing partner informed by our editorial taste at Every that launched yesterday.

The result is a product—and a philosophy—built by the ultimate craftsman who believes you can lean into AI without blunting your edge with slop. We had Danny on AI & I to talk about using AI without losing your craft. We get into the hidden alpha in AI tools that slow you down, how to code with AI without losing your craft, and everything Danny learned about cajoling AI to write well.

You can try Spiral here: https://writewithspiral.com/

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

Ready to build a site that looks hand-coded—without hiring a developer? Launch your site for free at Framer.com, and use code DAN to get your first month of Pro on the house.

Timestamps:

00:00:00 – Start

00:01:00 – Introduction

00:05:26 – How Danny used Spiral to prepare for this podcast

00:08:29 – Why slowing down makes AI writing better

00:13:42 – The agents working under the hood for Spiral

00:14:46 – How Spiral helps you explore the canvas of possibilities

00:24:41 – Why Danny pivoted away from the old version of Spiral

00:31:51 – How to use AI without losing your craft

00:34:55 – Danny’s workflow for building Spiral as a solo engineer

00:40:39 – Code with AI while staying in control

00:45:26 – What Danny learned about getting AI to write well

00:47:52 – How Danny used DSPy to give AI taste

00:56:16 – Dan v. AI Dan: Can the machine match the man?

Links to resources mentioned in the episode:

• Danny Aziz: Danny Aziz (@DannyAziz97) / X
• Give Spiral a go: Spiral
• The article Every published about DSPy: I’ve Stopped Writing Prompts—DSPy Does It Better

This episode is a little different from our usual fare: It’s a conversation with our head of AI training Alex Duffy about Good Start Labs, a company he incubated inside Every. Today, Good Start Labs is spinning out of Every as a separate company with $3.6 million in funding from General Catalyst, Inovia, Every, and a group of angel investors from top-tier AI labs like DeepMind. We get into how Alex learned some of his biggest lessons about the real world from games, starting with RuneScape, which taught him how markets work and how not to get scammed. He explains why the static benchmarks we use to evaluate LLMs today are breaking down, and how games like Diplomacy offer a richer, more dynamic way to test and train large language models. Finally, Alex shares where he sees the most promise in AI—software, life sciences, and education—and why he believes games can make the models we use smarter, while helping people understand and use AI more effectively.

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

00:00:00 - Start

00:01:48 - Introduction

00:04:14 - Why evals and benchmarks are broken

00:07:13 - The sneakiest LLMs in the market

00:13:00 - A competition that turns prompting into a sport

00:15:49 - Building a business around using games to make AI better

00:22:39 - Can language models learn how to be funny

00:25:31 - Why games are a great way to evaluate and train new models

00:26:58 - What child psychology tells us about games and AI

00:30:10 - Using games to unlock continual learning in AI

00:36:42 - Why Alex cares deeply about games

00:44:37 - Where Alex sees the most promise in AI

00:50:54 - Rethinking how young people start their careers in the age of AI

Links to resources mentioned in the episode:

• Alex Duffy: alex duffy (@alxai_)
• Good Start Labs: https://goodstartlabs.com/, good start (@goodstartlabs)
• The book Alex is reading about the importance of games: Playing with Reality: How Games Shape Our World
• The book Dan recommends by the psychoanalyst D.W. Winnicott: Playing and Reality

Aaron Levie is AI-pilled, but he’s one of the few CEOs who sees a future where AI agents work for us, instead of replacing us—helping us to do more than we could before.

Aaron’s been the CEO of Box for 20 years–long enough to see a few tech revolutions up close—and taking the company AI-first gave him a glimpse of what the next one means for us. We get into why jobs aren’t going away, the new shape of work, and what it takes to build an AI-first company from the inside.

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

Meet NotebookLM, the AI research tool and thinking partner that can analyze your sources, turn complexity into clarity and transform your content: https://notebooklm.google.com/

Timestamps:

00:00:00 - Start

00:01:30 – Introduction

00:02:36 – Why AI won’t take your job

00:06:42 – Jevons Paradox and the future of work

00:10:40 – How Aaron’s experience with the cloud era shapes his view of AI

00:19:44 – Why every knowledge worker is becoming a manager of AI agents

00:25:21 – What Aaron’s learned from bringing AI into every corner of Box

00:33:57 – What’s overhyped in AI today

00:43:31 – How Aaron balances everyday execution with innovation

Links to resources mentioned in the episode:

• Aaron Levie: Aaron Levie (@levie)
• Box: https://www.box.com/
• Dan’s essay on the shift toward the allocation economy: "The Knowledge Economy Is Over. Welcome to the Allocation Economy"
• Dwarkesh’s podcast with Richard Sutton: https://www.dwarkesh.com/p/richard-sutton

If your MCP server has dozens of tools, it’s probably built wrong.You need tools that are specific and clear for each use case—but you also can’t have too many. This creates an almost impossible tradeoff that most companies don’t know how to solve.

That’s why we interviewed Alex Rattray, the founder and CEO of Stainless. Stainless builds APIs, SDKs, and MCP servers for companies like OpenAI and Anthropic. Alex has spent years mastering how to make software talk to software, and he came on the show to share what he knows. We get into MCP and the future of the AI-native internet.

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

Ready to build a site that looks hand-coded—without hiring a developer? Launch your site for free at Framer.com, and use code DAN to get your first month of Pro on the house.

Timestamps:

00:00:00 - Start

00:01:14 - Introduction

00:02:54 - Why Alex likes running barefoot

00:05:09 - APIs and MCP, the connectors of the new internet

00:10:53 - Why MCP servers are hard to get right

00:20:07 - Design principles for reliable MCP servers

00:23:50 - Scaling MCP servers for large APIs

00:25:14 - Using MCP for business ops at Stainless

00:28:12 - Building a company brain with Claude Code

00:33:59 - Where MCP goes from here

00:41:10 - Alex’s take on the security model for MCP

Links to resources mentioned in the episode:

- Alex Rattray: Alex Rattray (@RattrayAlex), Alex Rattray

- Stainless: https://www.stainless.com/