AI & I

Two years ago, Katie Parrott was laid off from a crypto firm and couldn’t afford a career coach—so she turned to a $20-a-month ChatGPT subscription instead. The Every staff writer’s habit of feeding AI good context eventually became compound writing, a codified system for brainstorming, drafting, and editing with AI. Today, that system is a plugin any writer can use. On this week’s AI & I, Natalia Quintero talks with Katie about turning good ingredients into good writing, borrowing the taste of writers she admires, and why AI helped her fall back in love with the page. If you found this episode interesting, please like, subscribe, comment, and share! To hear more from Natalia Quintero: Subscribe to Every: https://every.to/subscribe Follow her on X: @NataliaZarina Go to https://attio.com/every and get 15% off your first year. Timestamps: 0:00 Start 0:49 Introduction 1:21 How Katie went from being laid off to using ChatGPT as a career coach 8:06 Turning AI into a “content agency of one” 10:59 Building the context files and style guides that make AI outputs useful 14:15 What makes a Claude project actually work 21:18 How AI helped with a mental health crisis and “computer errands” 27:03 Katie’s career coach, now a fully autonomous Codex project 32:27 What compounding means, and building the Compound Writing plugin 38:00 Borrowing Vonnegut, Hitchcock, and Sorkin as AI editing skills 44:49 Katie’s thesis: education and access will matter more than ever Links to resources mentioned in the episode: Katie Parrott on X: @kplikethebird Compound writing plugin: https://github.com/EveryInc/compound-writing⁠ Compound engineering plugin (Kieran Klassen): github.com/EveryInc/compound-engineering-plugin Parrott’s companion piece on compound writing: https://every.to/guides/compound-writing Parrott, “I Hired ChatGPT as My Career Coach”: every.to/working-overtime/i-hired-chatgpt-as-my-career-coach Parrott, “AI Turned Me Into a Content Agency of One”: every.to/working-overtime/ai-turned-me-into-a-content-agency-of-one

Will England is the CEO of Walleye Capital, a hedge fund managing nearly $10 billion in assets. An engineer by training with a math background from Oxford, he has spent his career at the intersection of machines and markets—and has made AI fluency mandatory for all 400 employees. England believes refusing to use AI is like refusing to use the internet in 1995 because it wasn’t perfect. His use of AI is public and effusive, including in a firm-wide email that opened with “I used ChatGPT to write this email. You should be using it, too, and be proud of it.” AI informs how Walleye drafts memos and selects stocks. On Every’s AI & I, Dan Shipper spoke with England about why he’s betting his entire organization on AI, why “results are what matter” more than blood, sweat, and tears, and what the American frontier can teach us about leading through technological change. Like, subscribe, comment, and share! To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow Dan Shipper on X: https://twitter.com/danshipper Go to https://attio.com/every and get 15% off your first year. Timestamps: 0:00 Start 0:51 Introduction 3:25 What pushed Will to go all in on AI 15:15 Inside the ‘AI-first’ memo Will shared at Walleye 17:02 Why you shouldn’t be afraid of using AI for work 31:25 How Will uses LLMs to sharpen his thinking 35:57 Walleye’s approach to using AI to reduce risk 39:35 What history can teach us about leading through change 57:10 Will’s first principles for making better decisions 59:23 Why Will journals every day—and how AI makes it easier Links to resources mentioned in the episode: Will England/Walleye Capital: https://walleyecapital.com/bio/will-england Every’s AI tools—Monologue, Cora, Spiral, and Sparkle: https://every.to/studio Every’s AI consulting: https://every.to/consulting

LLMs are a new medium for storytelling. That’s according to the creators of Portola, the company behind Tolan: an embodied AI companion that lives on its own planet and chats to you with a distinct personality. In 2025, Portola's founder and CEO Quinten Farmer and Head of Story Eliot Peper joined Dan Shipper to explain how they’re building this new medium from scratch. Their aim is to help users go from overwhelmed to grounded through conversations with Tolan that feel personal and spontaneous, not scripted. On this week’s AI & I, Dan revisits his conversation with Quinten and Eliot. They discuss why response time is everything for voice-based AI interfaces, how Portola designs AI personalities users will click with, and why character-driven AI could become a new computing interface. 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 Go to https://attio.com/every and get 15% off your first year. Timestamps: 00:01:30 - Introduction 00:04:07 - Talking to the Portola CEO's Tolan, Clarence 00:09:11 - How Portola went from building software for kids to AI companions 00:23:40 - Why response time is everything for voice-based AI interfaces 00:29:54 - Tolans don't use scripted prompts—they're taught to improvise 00:37:23 - How to know which AI personalities your users will click with 00:42:27 - Developing the character traits of an AI companion 00:49:48 - What does it mean to build technology that makes us flourish 01:01:10 - How Portola evaluates whether Tolans are resonating with users 01:11:01 - Inside Portola's viral growth strategy

In 2025, Kevin Scott bet that the agentic web would be the next big thing in AI. The Microsoft CTO argued that for agents to be genuinely useful, they'd need to be able to take action on our behalf—which would mean giving them access to the same sprawl of tools, data, and systems that make up the internet. Today, that bet is starting to pay off, as the foundational infrastructure for the agentic web is now being built. On this week's AI & I, Dan Shipper revisits his conversation with Kevin. They discuss Microsoft's role in the agentic web, why openness doesn't have to come at the expense of security, and why programmers should stay curious about new tools rather than resist them on principle. 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 Go to https://attio.com/every and get 15% off your first year. Timestamps: 0:00 Start 1:44 Introduction 2:49 The race to close the "capability overhang" 4:31 How agents will evolve into practical, useful tools 6:48 The role Kevin sees Microsoft playing in the agent ecosystem 12:05 How robust security measures can coexist with open ecosystems 15:39 Kevin's philosophy on being a craftsman in the age of agents 20:52 How the landscape of software development agents will evolve 25:33 The future of agentic workflows Links to resources mentioned in the episode: Kevin Scott on X: https://twitter.com/kevin_scott Model Context Protocol (MCP): https://modelcontextprotocol.io NLWeb: https://github.com/microsoft/NLWeb GitHub Copilot: https://github.com/features/copilot

Most consumer AI so far has been single-player: you and a chatbot, alone. Benchmark partner Sarah Tavel, one of Pinterest's first 30 employees, is betting that's about to change. She's looking for a product genius who can build an AI product with social DNA: status, network effects, and multiplayer dynamics. That'll enable users of ChatGPT and other models to learn from how others use AI and level up. On this week’s AI & I, Dan Shipper revisits his conversation with Sarah. They talk about why technical founders dominate the early days of a platform shift while product-minded founders win later, what ChatGPT is still missing, and what separates a founder's real network effect from a slide with a flywheel diagram. 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 1:10 Introduction 2:26 Why the future of consumer AI belongs to founders with product intuition 11:09 What Sarah sees as ChatGPT's biggest weakness 18:45 How Sarah would design a consumer AI app with social DNA 24:10 The kind of founders Sarah invests in 28:33 How to know if your startup's network effects are real 35:40 What's catching Sarah's eye beyond AI 40:41 How AI will change the way top venture capitalists invest Links to resources mentioned in the episode: Sarah Tavel on X: https://x.com/sarahtavel Benchmark: https://benchmark.com Agentio (marketplace for YouTube creators and brands): https://agentio.com/ Chainalysis: https://chainalysis.com The Five Temptations of a CEO by Patrick Lencioni: https://www.amazon.com/dp/B007BZBRB8 Thinking in Bets by Annie Duke: https://www.amazon.com/dp/B0HBBW23PM

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

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.

“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.

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/

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.

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

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

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

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/

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

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

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

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

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

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