AI & I

Dan Shipper

Learn how the smartest people in the world are using AI to think, create, and relate. Each week I interview founders, filmmakers, writers, investors, and others about how they use AI tools like ChatGPT, Claude, and Midjourney in their work and in their lives. We screen-share through their historical chats and then experiment with AI live on the show. Join us to discover how AI is changing how we think about our world—and ourselves.

For more essays, interviews, and experiments at the forefront of AI: https://every.to/chain-of-thought?sort=newest.

Subscribe Listen in podnod RSS feed Show website

20 episodes
Updated Wednesday

Episodes20

Newest first

Wednesday · 53 min
Best of the Pod: Wired's Kevin Kelly on Why AI Is a 50-year Overnight Success
Kevin Kelly has spent over 30 years experiencing the edge of new technology: from the earliest days of the internet to the first years of Burning Man. But he’s always treated the frontier as a place to visit, not somewhere to live. It’s partially how he’s been able to stay grounded through tech’s various hype cycles. As founding executive editor of Wired and author of The Inevitable, Kelly spends as much time analyzing the latest in AI as he does reading about significant moments in history. It’s a discipline he traces back to his work with the Long Now Foundation, which he cofounded to encourage long-term thinking, reaching from the last 10,000 years to the next. On this week’s AI & I, Dan Shipper revisits his conversation with Kelly. They get into why historians can be the best futurists, and how our bid to understand what intelligence is has parallels with early scientists' attempts to figure out electricity. Kelly also describes the joy he found in creating an AI-generated saga featuring Leonardo Da Vinci, Christopher Columbus, and Martin Luther—one that will only ever be read and enjoyed by him. If you found this episode interesting, please like, subscribe, comment, and share! To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Timestamps for YouTube: 0:00 Start 0:50 Introduction 1:10 Why Dan and Kelly love Annie Dillard 12:52 How to predict the future like Kelly 16:10 What the history of electricity can teach us about AI 20:13 How Kelly thinks about the nature of intelligence 25:44 Kelly's advice on discovering your competitive advantage 29:33 How Kelly assembled a bench of star writers for Wired 34:43 How Kelly used ChatGPT to co-create a book 39:12 Using AI as a mirror for your mind 43:43 What Kelly learned from betting on VR in the 1980s Links to resources mentioned in the episode: Kevin Kelly on X: https://twitter.com/kevin2kelly The Inevitable by Kevin Kelly: https://www.amazon.com/Inevitable-Understanding-Technological-Forces-Future/dp/0525428089 Pilgrim at Tinker Creek by Annie Dillard: https://www.amazon.com/Pilgrim-Tinker-Harper-Perennial-Classics/dp/0061233323 1,000 True Fans by Kevin Kelly: https://www.amazon.com/1000-True-Fans-Kellys-Simple-ebook/dp/B01N9P9O4G Full episode transcript: https://every.to/podcast/transcript-be243312-ea22-4193-8c56-b9cd45a79a87
July 22 · 46 min
How Every's Team Used AI to Ship Its Biggest Launch Ever
Yash Poojary, a growth engineer at Every, dropped an idea for a campaign in Slack at 7 p.m. Instead of building it himself, Every’s head of growth Austin Tedesco took a screenshot of the Slack thread, dropped it into Codex, typed "Can you do this?", and went to the gym. By the time he got back, Codex had built four audience segments, drafted emails for each one, and pulled a social image that had worked before. It took Austin 10 minutes to make some tweaks and schedule the whole thing to send the next morning. Within a few hours, it generated more than $25,000 in revenue. That story came out of the launch week for All Access, Every’s new $625-a-year membership built around the Builder Pack. It includes $7,000 in credits and free usage from ten of the AI products Every uses every day, including Claude Max, Codex, Cursor Pro+, PostHog, Notion, Framer, Render, and Flora. On this episode of AI & I, four of Every's own builders—COO Brandon Gell, head of marketing Douglas Brundage, as well as Yash and Austin—sit down to show how they use AI, breaking down their personal stacks and giving insight into their own strategies and mindset for building. If you found this episode interesting, please like, subscribe, comment, and share! To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Timestamps for YouTube: 0:00 Intro 0:35 All Access Explained 3:01 Yash's Tech Stack and How He's Automating Testing Pipelines 8:02 The Idea to Execution Loop 10:25 How an Agent Turned an Idea into $25K 17:50 The AI Sandwich Workflow 22:03 Making AI Tools Accessible to Solo Builders 28:50 Douglas on Brand and Design 34:51 Tips on What to Build First 43:46 What's Next for All Access Links to resources mentioned in the episode: Brandon Gell on X: https://x.com/bran_don_gell Yash Poojary on X: https://x.com/poojary_yash Austin Tedesco on X: https://x.com/tedescau?lang=en Douglas Brundage on X: https://x.com/DABrundage Introducing Every All Access: https://every.to/on-every/introducing-every-all-access Get the Builder Pack: every.to/builder-pack Go to https://attio.com/every and get 15% off your first year.
July 15 · 59 min
The Founder of a $1.5B AI Company on What Comes After the First Wave of AI Apps
“Running a startup is a knife fight whether things are going well or not,” says Chris Pedregal, cofounder and CEO of Granola. Granola recently raised a $125 million series C round at a $1.5 billion valuation on the strength of its AI meeting notetaker. That valuation hasn’t made Pedregal complacent. Granola built its name as the first to make good AI meeting notes, but Notion, OpenAI, and Zoom have all since released their own versions. Pedregal isn’t rattled—he never thought meeting notes were the real prize. The bigger fight, he says, is over “what interface we use for work, and what work looks like in an AI-native world.” That’s why Granola is betting on owning the entire meeting workflow: preparing people for a call, helping them act on it afterward, and making that context available to whatever agent—Claude, Codex, or anything else—people bring to the table. Over the next few months, the company plans to push hard on its API and MCP to make that possible. Dan Shipper talked with Pedregal for AI & I about why Granola pre-generates millions of meeting briefs, most of which go unopened, what “bring your own agent” software could look like, and why Pedregal still thinks “easy come, easy go” about Granola’s own success. If you found this episode interesting, please like, subscribe, comment, and share. More from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Timestamps: 00:00:59 Introduction 00:01:57 Why starting a company feels like a knife fight 00:04:33 Granola's counterintuitive view on competition 00:10:44 Dan's "pirate and architect" framework for structuring early-stage product teams 00:13:09 How Granola's "shaping" and "validation" phases work for building new features 00:18:17 Why Dan lives almost entirely inside Codex 00:24:40 The case for "Codex-native apps" 00:35:37 Granola's "handrail" philosophy 00:38:12 Why Granola is betting on owning meeting-adjacent context instead of competing as a general agent 00:44:19 What a transcript alone can never capture Episode resources: Chris Pedregal on X: https://twitter.com/cjpedregal Granola on X: https://twitter.com/meetgranola Granola: https://granola.ai Granola hits $1.5B valuation (TechCrunch): https://techcrunch.com/2026/03/25/granola-raises-125m-hits-1-5b-valuation-as-it-expands-from-meeting-notetaker-to-enterprise-ai-app/ Go to https://attio.com/every and get 15% off your first year.
July 8 · 53 min
How a Writer Uses AI Without Losing His Voice
Craig Mod used to pay Campaign Monitor roughly $7,000 a year to send his newsletters. After rebuilding the tool himself with AI, his bill is closer to $150. It’s the kind of thing that convinces him we’re about to enter a “golden age of tool building”—one where anyone can build tools specifically suited to their needs, instead of settling for software from incumbents that are slow to innovate. Mod is the writer and photographer behind the newsletters Roden and Ridgeline and books like Things Become Other Things and Kissa by Kissa—as well as a lifelong technologist. He’s rebuilt the tax software Quicken, created a private alternative for Twitter for his members which he calls The Good Place, and used AI to build an archive for his pop-up newsletters. But while Mod is an advocate of using AI to build, he draws the line at using it to write. Mod talks to Dan Shipper about using AI as a research assistant, why he keeps a tech-free zone in the mornings for deep thinking, and why he’s resisting the pull of the “mainlining” AI era. If you found this episode interesting, please like, subscribe, comment, and share! To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Timestamps: 0:00 Introduction 3:51 Rebuilding Quicken and Campaign Monitor with AI 6:24 Building The Good Place, a private Twitter alternative for Craig’s members 10:39 Why we’re entering a “golden age of tool building” 12:17 Why AI could help writers build audiences 17:35 Using AI to build a newsletter archive and a searchable board-meeting Q&A library 27:58 Creating a technology-free buffer to protect deep thinking 30:31 Why Craig is resisting the temptation to “mainline” AI for ten hours a day 39:44 Why anthropomorphizing AI is “psychotic,” and why Apple got Siri right 47:42 Being adopted, and making peace with humanity’s fragile place in an AI future Go to https://attio.com/every and get 15% off your first year. Links to resources mentioned in the episode: Craig Mod’s website: https://craigmod.com Roden (Craig’s monthly newsletter): https://craigmod.com/roden/
July 1 · 41 min
The AI Workflows Behind Every's Consulting Team
Natalia Quintero joined Every as head of consulting with a mandate to bring AI into the workflows of executives at hedge funds, private equity firms, and tech companies. She is also a recent Codex convert—someone who spent months resisting the tool before Dan Shipper’s daily pestering finally got her to try it. Natalia encountered Codex as a non-technical builder who had learned to navigate file systems and folder structures in Claude Code through sheer effort. She’s now used Codex to do everything from automate her CRM setup to build a portal to manage her father’s medical care. Dan talked with Natalia for AI & I about what it looks like to go from non-technical to building software with Codex, why Every still uses software-as-a-service products from Attio and Asana instead of vibe coding their own tools, and where she thinks AI agents like Every’s internal Claudie employee require human managers. If you found this episode interesting, please like, subscribe, comment, and share! To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Timestamps: 00:01:05 Introduction 00:02:35 How Natalia manages Claudie, the consulting team's AI project manager 00:04:55 Why the consulting team still pays for SaaS products 00:11:47 Codex as a game changer 00:14:55 Building personalized learning guides and illustrated explainers with AI 00:21:40 Inside Natalia's AI-powered email triage system 00:26:44 The shift from knowledge work as sculpting to knowledge work as gardening 00:28:57 Using Codex to one-shot a custom CRM 00:33:16 Using Codex to build an app that coordinates her father's medical care Links to resources mentioned in the episode: Natalia Quintero on X: https://x.com/NataliaZarina Asana (project management): https://asana.com Every Consulting: https://every.to/consulting Go to attio.com/every and get 15% off your first year.
June 24 · 43 min
Building a School Where AI Models Learn About Humanity
If scaling laws hold—and Surge AI CEO Edwin Chen believes they do—we’re hurtling toward a future where there’s nothing humans can do that AI can’t do better. When OpenAI’s models disproved an open conjecture posed by mathematician Paul Erdős using novel algebraic geometry techniques, Fields medalist Timothy Gowers felt the shift acutely. He initially thought the model had proved an upper bound, and braced himself: that would mean it was “all over for mathematicians very soon.” When he realized it had only found a counterexample, he was relieved—it bought him another year or two before the thing he’s devoted his life to becomes something AI does better. As founder and CEO of the company behind the data environments and evals the major model companies use to train their models, Chen has a unique perspective on how quickly AI models are absorbing tasks we used to think of as uniquely human. Dan Shipper talked with Chen for AI & I about what the act of creating or building means when AI can do it better—and whether an answer to that question already exists within science fiction. If you found this episode interesting, please like, subscribe, comment, and share! Join the membership for Where You Live at ⁠https://www.joinbilt.com/dan To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Timestamps: 00:00:54 Introduction 00:01:49 Surge as a "school for AGI" 00:04:46 What AI's capacity for novel mathematics says about human achievement 00:07:29 Motivation in an era when AI can do everything 00:14:34 The trap of optimizing AI models for engagement 00:29:34 Training using datasets versus training using environments 00:35:09 The value of personal data 00:39:40 Why models are bad at writing 00:42:00 Chen's AGI timeline Links to resources mentioned in the episode: Edwin Chen on X: https://x.com/echen Surge: https://surgehq.ai Riemann-bench (research-level math benchmark): https://surgehq.ai/leaderboards/riemann-bench Hemingway-bench (creative writing benchmark): https://surgehq.ai/leaderboards/hemingway-bench Talkie-1930 (language model trained on pre-1930 text): https://huggingface.co/talkie-lm/talkie-1930-13b-it Ted Chiang, “What’s Expected of Us”: https://www.nature.com/articles/436150a Every is the most AI-native startup on the internet. Through ideas, software and education, subscribers get the tools to work at the frontier of AI. Start your free trial today: https://every.to/subscribe?utm_source=youtube Follow Every: https://x.com/every Follow Dan Shipper: https://x.com/danshipper
June 17 · 28 min
GitHub’s COO Explains Why AI Hasn’t Replaced Developers
Last year, there were 1 billion commits on GitHub. This year, Kyle Daigle expects that number to exceed 14 billion, a two-component explosion caused by more humans—and their agents—issuing pull requests. In March alone, 17 million pull requests on GitHub were created by agents. Daigle is the COO of GitHub and Microsoft’s chief marketing officer for developer products. He’s been at GitHub for 13 years, and is paying close attention to how AI is expanding the platform’s user base. Along with agents, legal, sales, and marketing professionals are building apps with the GitHub Copilot app. The line between developer and non-developer is disappearing. On this episode of AI & I, guest host Mike Taylor sat down with Daigle at Microsoft Build to discuss how GitHub is building infrastructure for an agent-native world: agentic code review, model routers that automatically select the right model for the task, and a philosophy that the most durable advantage in this market is developer choice. If you found this episode interesting, please like, subscribe, comment, and share! Want even more? To hear more from Mike Taylor: Subscribe to Every: https://every.to/subscribe Follow him on X: https://x.com/hammer_mt Timestamps for YouTube: 00:00:52: Introduction 00:03:27: The agentic PR flood 00:04:33: GitHub's approach to helping open-source maintainers manage the surge 00:06:15: What 14 billion commits means for code quality 00:08:03: Moving from per-seat licensing to usage-based pricing 00:09:45: Kyle's dual role as GitHub COO and Microsoft's chief marketing officer for developers 00:13:03: Developer choice as competitive moat 00:14:57: How to balance dogfooding your own tools with staying honest about the competition 00:19:45: Hill climbing, frontier tuning, and solving the model-routing problem 00:24:45: Kyle's agentic communication hack Links to resources mentioned in the episode: Kyle Daigle on X: https://x.com/kdaigle Mike Taylor on Every: https://every.to/@mike_2114 Mike’s piece on building an AI version of Kyle Daigle: https://every.to/also-true-for-humans/i-interviewed-an-ai-version-of-github-s-coo-then-spoke-to-the-real-one GitHub Copilot: https://github.com/features/copilot
June 10 · 52 min
How Anthropic Uses Claude Fable 5 With Mike Krieger
Mike Krieger built one of the most consequential consumer apps of the last two decades as the cofounder of Instagram. He is now at the frontier of AI-native product development as head of Anthropic Labs, the team responsible for figuring out what the most capable AI models can do in the hands of real builders. When Krieger first got access to Fable 5 months before its public release, it was exciting and disorienting. “I feel like a total newbie again,” he remembers telling his team. The way he’d been thinking about productivity, strategy, and time management was out of date. The model had outpaced his workflows. Dan Shipper talked with Krieger for AI & I about what it looks like to build with a model as capable as Fable 5, including the new rhythms, challenges, and possibilities it reveals. If you found this episode interesting, please like, subscribe, comment, and share! To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Get started with Braintrust at https://www.braintrust.dev/ Timestamps: 0:03 Introduction 1:48 How Fable completely reshaped Mike's workflow 4:48 When to use Sonnet versus Fable 10:06 What the media tracker Mike built over a weekend reveals about agent-native architecture 15:00 The cost to build has collapsed 19:03 Is software engineering over? 21:48 How Anthropic's engineering teams work today 38:39 The mechanics of verification 44:39 What people should use the model to build 47:24 Dynamic workflows Links to resources mentioned in the episode: Mike Krieger on X: https://x.com/mikeyk Anthropic Labs: https://www.anthropic.com Claude Code: https://claude.ai/code Every: https://every.to
June 3 · 33 min
The SaaS Apocalypse Is a Goldmine With Figma’s Matt Colyer
The "SaaSpocalypse"—the panic that AI will make software-as-a-service obsolete—hasn't rattled Figma’s Matt Colyer. As the company’s director of product management for developers, he's been building his own agents for two years and is buying more software services than ever. In addition to making the case that AI is a “goldmine” for SaaS companies, Colyer talked with Dan Shipper for AI & I about why great design requires a diamond-shaped process: First you diverge, generating as many ideas as possible, then you converge around the best ones. Chat is linear, which makes it good for iterating on one design but bad at generating lots of options. Figma's new on-canvas agent is a first attempt at fixing that. They also get into why AI design tools need to break free of the text box, how Figma's MCP server is closing the loop between code and design, and why "review" has become the biggest bottleneck in AI-assisted product work. If you found this episode interesting, please like, subscribe, comment, and share! To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Timestamps: 1:03 - Introduction 2:15 - Why the SaaSpocalypse narrative has it backwards 5:27 - Matt’s email agent origin story 13:21 - Divergent vs. convergent design thinking 17:39 - Figma’s MCP server 19:45 - Why design agents need personalization 22:09 - Every problem is a context problem 25:12 - Apple and Google as the reigning kings of context 28:18 - Why review is the new bottleneck Links to resources mentioned in the episode: Matt Colyer on X: https://x.com/mcolyer Figma: https://figma.com Figma MCP server: https://www.figma.com/blog/introducing-figma-mcp-server/
May 27 · 41 min
We Automated Everything With AI and Tripled Our Headcount
Dan Shipper runs one of the most AI-native companies today. Every has agents embedded in nearly every workflow—“if you swing a stick in our Slack, you're as likely to hit a human as an agent,” he says. And yet the company has grown from four people to 30 since GPT-3 came out, and is still hiring. Why does Dan believe there's more human work to do than ever? In a format flip for AI & I, Every's COO Brandon Gell turns the tables and interviews Dan about his latest essay, “After Automation”—an 8,000-word argument for why rising automation doesn't eliminate demand for human work, it increases it. The thesis: AI makes yesterday's expert competence cheap and widely available, which floods every field with output that's close but not quite right—and that creates more demand for the humans who can take it the rest of the way. Dan talked with Brandon about the paradox at the heart of agent-native work: The more AI can do, the more humans are needed to direct it, refine its output, and decide what matters next. If you found this episode interesting, please like, subscribe, comment, and share! 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: “After Automation” by Dan Shipper: https://every.to/chain-of-thought/after-automation Brandon Gell on Every: https://every.to/@brandon_5263 Join the membership for where you live at ⁠joinbilt.com/dan⁠ Timestamps: 00:00:51 Introduction 00:05:51 The AI paradox: more automation, more human work 00:10:00 How AI makes yesterday's expert competence cheap 00:18:00 AI can act autonomously but it does not have agency 00:20:39 Why Dan is all in on AGI 00:21:57 AI layoffs are a lie 00:25:42 Ride the models and you'll be fine 00:35:30 How to use AI as a long-form features editor
May 20 · 51 min
Inside Stainless: The Developer Tools Startup Anthropic Just Bought for $300 Million
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. [Disclosure: Dan is a small investor in Stainless.] If you found this episode interesting, please like, subscribe, comment, and share. To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Get started with Braintrust at https://www.braintrust.dev/ Timestamps: 00:01:15 - Introduction 00:05:09 - APIs and MCP, the connectors of the new internet 00:11:00 - Why MCP exists 00:17:15 - Why MCP servers are hard to get right 00:20:24 - Design principles for reliable MCP servers 00:25:06 - Using MCP for business ops at Stainless 00:40:57 - Alex's take on the security model for MCP 00:44:42 - How one-off AI actions become permanent production software Links to resources mentioned in the episode: Alex Rattray: Alex Rattray (@RattrayAlex), Alex Rattray Stainless: https://www.stainless.com/Inside Stainless: The Developer Tools Startup Anthropic Just Bought for $300 Million
May 13 · 1 hr 10 min
Claude Code Can Be Your Second Brain
From time to time, we will republish episodes that you might have missed. This episode originally aired in September 2025. Noah Brier uses Claude Code as his second brain—it’s the coolest notetaking setup we’ve ever seen. He has Claude running on a server in his basement hooked up to a VPN. It stores, reads, and writes to thousands of notes in his Obsidian vault. He does it all from his phone. We had him on the show to tell us exactly how he’s pulling this off. Dan and Noah get into: The nuts and bolts of the Claude Code-Obsidian setup: Noah set up Claude Code on top of his Obsidian root directory, and he walked me through how he uses it to prep for an upcoming speech—creating a project folder, pulling in relevant research from his notes, saving transcripts from chats with other LLMs, and generating daily progress updates. The “thinking partner” that lives inside Noah’s second brain: Noah points out that in the hype around AI’s ability to write, the fact that it can read is overlooked. That’s why he has an agent inside Claude Code with strict guardrails to stay in “thinking mode.” It logs his questions, tracks insights, and catches him up on research if he returns to a project after a few days away. How Noah does deep work on his phone: Noah rigged a home server in his basement, put his Obsidian vault in it—and then runs Claude Code on top. Noah says that being able to think, write, research, and ship code from his phone has fundamentally changed the way he works. This episode is a must-watch for anyone curious about who wants to learn how to use Claude Code to build a true second brain. If you found this episode interesting, please like, subscribe, comment, and share! Timestamps: 00:00:52 - Introduction 00:02:10 - How you can do deep work on your phone 00:05:30 - Why Noah thinks Grok has the best voice AI 00:11:11 - The nuts and bolts of Noah's Claude Code-Obsidian setup 00:26:05 - Using an agent in Claude Code as a "thinking partner" 00:30:23 - Noah's Thomas' English Muffin theory of AI 00:39:47 - The white space still left to explore in AI 00:48:44 - How Noah is preparing his kids for AI 01:00:06 - How he brought his Claude Code setup to mobile Links to resources mentioned in the episode: Noah Brier: ⁠https://www.noahbrier.com/⁠, ⁠Noah Brier (@heyitsnoah) / X⁠ Alephic, his AI strategy consultancy: ⁠alephic.com⁠ The conference he leads about marketing and AI: ⁠http://BRXND.AI⁠ A newsletter he writes about AI: ⁠newsletter.brxnd.ai⁠ The declassified relic from World War II they talk about: ⁠https://www.alephic.com/sabotage The apps Noah used to set up Claude Code on his phone: ⁠Termius⁠, ⁠Tailscale⁠
May 8 · 43 min
The Secrets of Claude's Platform From the Team Who Built It
In the future, you’ll be able to accomplish a goal by just giving Claude an outcome and a budget. That’s the direction Anthropic is building in with its new Managed Agents features, announced at this week’s Code with Claude developer event. The basic idea: Claude, wrapped in a computer in the cloud, that you can spin up, scale, and manage as needed. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7. On this week’s AI & I from @every, I talk with Angela Jiang (@angjiang), head of product for the Claude platform, and Katelyn Lesse (@katelyn_lesse), head of engineering for the Claude platform, about what Anthropic is building and what it takes to make agents reliable in production. If you found this episode interesting, please like, subscribe, comment, and share! To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Timestamps: 00:01:48 - How the Claude platform evolved from API to agents 00:04:09 - The primitives that make up Claude Managed Agents 00:10:37 - Why the harness and the model are becoming a single unit 00:18:49 - The infrastructure wall that kills most agent projects in production 00:24:49 - Why team agents need a different shape than individual productivity tools 00:26:36 - How Anthropic's legal team uses an agent to review marketing copy 00:34:24 - Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms 00:35:50 - How to measure agent success with outcome and budget as the end state 00:39:11 - What the platform looks like a year from now, when Claude writes its own harness
May 6 · 58 min
Why We Switched From Claude Code to Codex
In January, Dan Shipper wrote that whoever wins vibe coding wins how you work on your computer—and OpenAI had some serious catching up to do. Three months and the release of GPT-5.5 later, Codex has more than caught up. Austin Tedesco, Every's head of growth, now spends about 80 percent of his working time inside the Codex desktop app, doing everything from drafting go-to-market plans from a stack of meeting transcripts to rebuilding the company's KPI dashboard. On this episode of AI & I, Dan sat down with Austin to discuss why the agent management interface—a desktop app built on top of a coding agent—is becoming the new operating system for knowledge work, and why Codex has become his daily driver. If you found this episode interesting, please like, subscribe, comment, and share! To hear more from Dan Shipper: Subscribe to Every: every.to/subscribe Follow him on X: twitter.com/danshipper Join the membership for Where You Live at joinbilt.com/dan Timestamps for YouTube: 00:00:00 Introduction 00:00:57 How Codex went from a tool for senior engineers to a daily driver for knowledge work 00:02:42 How Claude Code proved that a great coding agent works for any knowledge work 00:07:24 Austin's switch to Codex 00:13:48 How Austin set up Codex with folders, keys, and reviewer agents 00:18:24 Using Codex to brainstorm automations across Gmail, Slack, and Notion 00:22:42 How Austin manages the human review step when Codex is drafting communications 00:28:54 Using Codex to build specialized agents inspired by product executive Claire Vo 00:31:09 Synthesizing meeting transcripts and Slack threads into a go-to-market plan 00:40:15 Building a live KPI tracker in Notion that agents can read 00:44:54 Using Codex for recruiting Links to resources mentioned in the episode: Austin on X: @tedescau Dan's January essay on OpenAI's catch-up problem: every.to/chain-of-thought/openai-has-some-catching-up-to-do Every's vibe check on GPT-5.5: every.to/vibe-check/gpt-5-5
April 29 · 53 min
How Stripe Is Building for an Agent-native World
Emily Glassberg Sands leads data and AI at Stripe, which processes roughly 2% of global GDP, giving her a bird’s-eye view into how AI is upending the internet economy. Dan Shipper talked with Glassberg Sands for Every's AI & I about what the data on Stripe's network actually shows: AI companies are scaling three times faster than the top SaaS cohort of 2018, fraud has moved from the checkout to the full funnel, and agents have started buying things, although mostly low-stakes commodities like Halloween costumes. The conversation covers the new fraud types unique to AI companies, the AI-on-AI arms race between bad actors and fraud detectors, where AI revenue growth is actually coming from, and how Stripe is rebuilding the payments infrastructure for a world where the buyer is an agent. If you found this episode interesting, please like, subscribe, comment, and share! To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Head to http://granola.ai/every and get 3 months free with the code EVERY Timestamps 00:00:45 Introduction 00:01:27 New rules for an agent-driven economy 00:03:57 Compute theft is the new payment fraud 00:10:00 How Stripe expanded fraud detection from checkout to the full customer lifecycle 00:19:48 Why AI companies are scaling way faster than top SaaS companies 00:23:27 Outcome-based billing is replacing seat-based pricing 00:29:57 Where AI spending is coming from 00:36:45 How the developer experience changes when agents are the builders 00:41:00 The agentic commerce spectrum, from assisted buying to autonomous purchasing 00:51:06 Meet Link, a consumer wallet for delegated agent purchases Links to resources mentioned in the episode: Emily Glassberg Sands on X: https://x.com/emilygsands Stripe: https://stripe.com Stripe Radar: https://stripe.com/radar Stripe Link: https://link.com Lovable: https://lovable.dev
April 22 · 28 min
The AI Sandwich: Where Humans Excel in an AI World
Most frameworks for working with AI agents assume humans should stay in the loop at every phase. That’s the wrong approach, says Cora general manager Kieran Klaassen. Kieran is the creator of Every's AI-native engineering methodology, compound engineering. His four-step framework—plan, work, review, compound—rebuilds how engineers work with agents. The insight, worked out with collaborator Trevin Chow, is about when to be in the loop and when to step away and let the model handle it. "LLMs are very good at just following steps, doing deep work, working for hours—days even now," Kieran says. "That thing is kind of solved." Kieran and Trevin describe an AI workflow as a sandwich. Agents are the workhorse filling, and humans are the bread, responsible for framing the problem at the start and reviewing the outputs at the end. Every CEO Dan Shipper talked with Kieran for AI & I about why setting the frame of a problem is still hard for agents, why simulated personas won't replace human judgment, Dan's bar for AGI—an agent worth running 24/7 with no off switch—and what Kieran's background as a classical composer taught him about performance, polish, and finding the parts of work that bring you joy. If you found this episode interesting, please like, subscribe, comment, and share! Head to http://granola.ai/every and get 3 months free with the code EVERY To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Discover more resources in the episode Compound engineering plugin: https://github.com/EveryInc/compound-engineering-plugin Compound engineering guide: https://every.to/source-code/compound-engineering-the-definitive-guide Compound engineering camp: https://every.to/source-code/compound-engineering-camp-every-step-from-scratch Timestamps: 00:00:00 – Introduction and the AI sandwich metaphor 00:02:33 – What compound engineering is and how it’s evolved 00:04:27 – The "work" phase of agentic coding is essentially solved 00:06:27 – Why humans belong at the beginning and the end of an AI workflow 00:11:06 – Dan's argument for why agents can't change frames—and how this will keep us employed 00:16:51 – Full automation is a moving target 00:23:21 – Musical composition as a model for human-AI collaboration 00:26:39 – Find your place in an AI-accelerated world by leaning into what brings you joy
April 15 · 53 min
The AI Model Built for What LLMs Can't Do
Most AI companies are racing to build bigger LLMs. Eve Bodnia thinks that's the wrong approach. Eve is the founder and CEO of Logical Intelligence, which is developing an alternative to the transformer-based models dominating the industry. Her argument: LLMs’ architecture makes them fundamentally unsuited for some mission-critical tasks. A system that generates output one token at a time, with no ability to inspect its own reasoning mid-process or guarantee its results, shouldn't be trusted to design chips, analyze financial data, or even fly a plane. Her alternative is the energy-based model (EBM), a form of AI rooted in the physics principle of energy minimization, not language prediction. Rather than guessing the next probable word, an EBM maps every possible outcome across a mathematical landscape, where likely states settle into valleys and improbable ones sit on peaks. Dan Shipper talked with Bodnia for AI & I about why she believes LLM progress is plateauing, what it means for AI to actually understand data rather than just pattern-match across it, and how her team is building toward formally verified code generated in plain English—no C++ required. If you found this episode interesting, please like, subscribe, comment, and share! Head to http://granola.ai/every and get 3 months free with the code EVERY To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Timestamps: 00:00:51 - Introduction 00:02:09 - Why correctness and verifiability matter in AI 00:09:33 - What an energy-based model is 00:14:21 - How EBMs construct energy landscapes to understand data 00:19:00 - Why modeling intelligence through language alone is a flawed approach 00:26:54 - What it means for a model to "understand" data 00:37:21 - How EBMs solve the vibe coding problem and enable formally verified code 00:43:21 - Why LLM progress is plateauing 00:49:54 - Mission-critical industries haven't adopted LLMs, and how EBMs could fill that gap
April 8 · 49 min
We Gave Every Employee an AI Agent. Here's What Happened.
While walking to the office, our COO Brandon Gell had his AI agent call him and go over his emails in his inbox one by one. When he arrived, he opened Gmail and confirmed she'd done everything he'd asked. "My jaw is on the floor," he messaged me. That was the moment Every got serious about setting up each employee with their own agent. Today, it's a reality—and it has completely changed how we work. Dan Shipper talked to Every COO Brandon Gell and head of platform Willie Williams for Every's AI & I about what happens when everyone at a company gets their own AI sidekick. If you found this episode interesting, please like, subscribe, comment, and share! To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Visit https://scl.ai/dialect to learn more about Dialect, a new system from Scale AI. Timestamps: 00:00 Introduction 00:02:21 How Brandon built Zosia, an AI agent to run his household 00:07:09 Brandon's aha moment re: using agents for work 00:09:39 What happened when everyone on the team got their own agent 00:12:42 How agents take on their owners' personalities, and why that matters inside an org 00:23:51 Why it's important for agents to do work in public 00:30:51 What we're still figuring out when it comes to agent behavior, including memory gaps, group chat etiquette, and the "ant death spiral" problem 00:40:45 How we built Plus One, our hosted OpenClaw product 00:47:27 The cultural shift required to make agents work at scale
April 1 · 52 min
If SaaS Is Dead, Linear Didn't Get the Memo
Founded in 2019, Linear is the rare company started pre-ChatGPT to have successfully reinvented itself as an agent-native business. On this episode of AI & I, Dan Shipper sat down with Karri Saarinen, cofounder and CEO of the product management tool, to discuss building a platform where humans and agents develop software together—and why the "SaaSpocalypse" isn’t coming for all SaaS companies. If you found this episode interesting, please like, subscribe, comment, and share! To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Visit https://scl.ai/dialect to learn more about Dialect, a new system from Scale AI. Timestamps: 0:00 Introduction 2:00 Why Linear waited to ship AI features instead of rushing to chatbots 5:06 Linear's agent platform and becoming the system that guides AI agents 7:42 Why "SaaS is dead" is a simplistic narrative 12:18 How Linear adopted AI coding tools 17:45 AI's impact on product building workflows—speed versus thoughtfulness 22:18 The value of conceptual work and thinking before shipping 29:30 How AI is reshaping Linear's product strategy 37:18 Demo: Linear's agent skills, shared context, and code review workflow 47:48 The future of product development and the enduring role of human judgment
March 25 · 48 min
How to Build an Agent-native Product | Mike Krieger
Mike Krieger built one of the most consequential consumer apps of the last two decades as cofounder of Instagram. He is now at the frontier of determining what makes a breakout AI-native product as co-lead of Anthropic Labs. Dan Shipper talked with Krieger for Every’s AI & I about how his experience creating Instagram shapes how he thinks about building with AI, including what can be sped up and what remains stubbornly time-intensive. If you found this episode interesting, please like, subscribe, comment, and share! To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Download Grammarly for FREE at grammarly.com Timestamps Introduction: 00:01:39 What's gotten easier—and what hasn't—about building products in the age of AI: 00:02:33 Why vibe coding creates "indoor trees": 00:05:00 How rewrites have become a normal part of the development process: 00:09:00 What "agent native" product design means: 00:11:39 How Mike's labs team is structured and the cofounder model: 00:24:27 The best signal for a product bet is someone with "break through walls" conviction: 00:29:33 Navigating enterprise customers while keeping pace with rapid AI change: 00:38:51 OpenClaw, personal agents, and the product question defining 2026: 00:40:54 Links to resources mentioned in the episode: Mike Krieger: https://x.com/mikeyk Agent-native architecture: https://every.to/guides/agent-native