| Welcome, humans. | Dan Shipper built a document editor between meetings. It went viral. Then it went down. Then it consumed his entire week. | The most interesting part about this? Dan basically built this app entirely through "vibe-coding", using a framework he developed inspired by Claude Code that even the team at Anthropic is inspired by (more on that below). | So if you want to understand how software gets built in 2026, this is the episode. | Dan is the CEO of Every—a 15-person media company that publishes a daily AI newsletter, ships multiple AI-powered products, and runs a consulting arm. | Today, their engineers write virtually zero code by hand. Instead, they use what Dan calls "agent-native" architectures and "compound engineering"—two frameworks where AI agents are the core of every product, not just a feature bolted on top, and learning compounds as you go. | Today at 10 a.m. PT / 1 p.m. ET, Dan joins us live to walk through how this actually works in practice. Click the image below to join! |  | Click the image to watch LIVE on YouTube, or if tuning in late, to watch the recording! |
| Here's what we'll cover: | The Proof story in full: Dan vibe coded a collaborative document editor, launched it, watched it blow up—and then spent 12 hours+ watching Codex agents hunt bugs in a codebase he didn't fully understand. We'll ask what he learned about shipping agent-built software at production scale. Agent-native architecture explained: Why the core of an agent-native app is a prompt, not code. You give the agent three simple tools—read file, write file, search the web—and let it figure out the rest. Every feature becomes a goal to achieve, not a set of steps to follow. Dan's shorthand: it's "Claude Code in a trench coat." Compound engineering: Every's four-step process (brainstorm, plan, work, review) for software teams that don't write code. Their GM for Cora went from a one-line prompt to a working app in under an hour. Every's full product suite: Spiral (AI writing partner that builds style guides from your X posts and writing samples), Sparkle (AI file organization for Mac), Cora (AI email assistant, now on iOS), Monologue (voice dictation that writes the way you talk), Proof (the agent-first doc editor), and maybe we'll even touch on their brand-new tool: Plus One (a hosted AI agent for Slack, launching Fri). How to structure AI product teams: Why Every runs one GM per product with a shared resource layer—and why adding people too early actually slows you down.
| 👉 Join us live: YouTube | LinkedIn | X | If you haven't already, check out Every's product suite (all included in one subscription): | Spiral — AI writing partner that builds style guides from your posts and samples Sparkle — AI file organization and duplicate cleanup for Mac Cora — AI email assistant (now on iOS) Monologue — Voice dictation that writes the way you talk Proof — Agent-first collaborative document editor (free + open source) Plus One — AI agent that works alongside you in Slack (launching this week)
| If you're not already reading Every's writing, start here. Dan's agent-native architecture essay is the single best explanation of how software building is changing right now. | Their compound engineering guide is the playbook their team actually uses to ship products without writing code. And their daily newsletter is one of the few AI reads that's written by people who build with AI every day; not just cover it. We plug their stuff a lot in The Neuron for a reason. | Keep scrolling for more resources and recent podcast episodes we think you'll love… | Real quick: Want to see your AI-adjacent product or service show up right here, below these podcast promos? Click the button below to advertise to our 675K+ readers! | | | More From The Neuron… | Four recent interviews you'll definitely want to check out (pick whatever looks interesting to you and dive in!): | Your AI Chats Can Be Subpoenaed. His Can't. — Proton's Eamonn Maguire on the privacy nightmare hiding in every AI chat. YouTube | Spotify | Apple Podcasts Solo Founders Are Taking Over (Carta's Data Proves It) — Carta's CMO reveals what's really happening in the startup world. YouTube | Spotify | Apple Podcasts NVIDIA's Kari Briski Breaks Down Nemotron 3 (GTC 2026) — Recorded live at GTC, the future of NVIDIA's open-source AI strategy. YouTube | Spotify | Apple Podcasts This AI Agent Compressed 8 Years of R&D Into 2 Weeks — SES AI's CEO on AI agents transforming scientific discovery. YouTube | Spotify | Apple Podcasts
| 🎧 Post-game listening: After the livestream, make sure to watch this: Dan just sat down with Mike Krieger (co-founder of Instagram, now VP of Product at Anthropic Labs) for a conversation about building products in the agent era. Mike had Claude rebuild Bourbon—Instagram's failed predecessor—in two hours, feature complete. | They dig into why AI makes it dangerously easy to overbuild V1, how Anthropic's labs team kills features as aggressively as they ship them, and why the best product teams pair "founder-level conviction" with senior systems expertise. | Watch the full conversation here. | Dive deeper into Dan and company's writing: | | And if you haven't subscribed yet, please do! Click the image below to go to our channel and hit "subscribe" to get notified right when new videos go live. | | We have a goal to hit 50K subscribers by the end of the year (if not 100K), and we're only 33K away! If you like learning about AI, and already watch some of our videos, do us a favor and click here to subscribe today. | Stay curious, | The Neuron Team | | | That's all for today, for more AI treats, check out our website. | | What'd you think of this podcast episode?Pick an answer below, then tell us why with the "additional feedback" option. | |
|
| | P.P.S: Love the newsletter, but don't want to receive these podcast announcement emails? Don't unsubscribe — adjust your preferences to opt out of them here instead. |
|
No comments:
Post a Comment
Keep a civil tongue.