Top Sites>Every

User-agent: *
Disallow: /api/
Disallow: /account
Disallow: /admin/
Disallow: /feeds/
Allow: /feeds/global.xml

# AI Crawlers - explicitly allowed for citation and discovery
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

Sitemap: https://every.to/sitemap.xml

# Every

> The only subscription you need to stay at the edge of AI. Every bundles ideas, apps, and training into one subscription: weekly writing on how to understand and use AI, a suite of AI-powered software products (Spiral, Cora, Sparkle, Monologue), and livestreamed camps and courses for one subscription price — all from practitioners who build AI products and use AI tools every day. At Every, the line between writer and builder is blurred: everyone who builds software also writes about it, and every writer builds with AI tools like Claude Code, Cowork, and others daily. You get the practitioner's inside perspective, not outsider commentary.

> Founded in 2020. 120,000+ email subscribers. $2M ARR, $3M in overall revenue as of February 2026 — revenue tripled in 2025. 20-person team. $30/month or $288/year.

> Cited by The New York Times and The New Yorker. Recommended by Reid Hoffman, Andrew Wilkinson, and Lenny Rachitsky. Backed by Bedrock Capital and Reid Hoffman.

## Press & Citations

* [The New York Times](https://www.nytimes.com/2025/05/21/business/media/ai-every-media-startup.html): "Will Writing Survive A.I.? This Media Company Is Betting on It." — Feature profile by Benjamin Mullin (May 2025).

* [The New Yorker](https://www.newyorker.com/culture/open-questions/why-cant-ai-manage-my-e-mails): "Why Can't A.I. Manage My E-Mails?" — Cal Newport reviews Every's AI email assistant Cora, with quotes from Dan Shipper and Kieran Klaassen (Nov 2025).

* [Axios](https://www.axios.com/2026/01/07/anthropics-claude-code-vibe-coding): "Anthropic's Claude Code transforms vibe coding" — Dan Shipper quoted on AI-powered coding (Jan 2026).

* [Axios](https://www.axios.com/2026/01/13/anthropic-claude-code-cowork-vibe-coding): "Anthropic's viral new work tool wrote itself" — Dan Shipper quoted on Claude Cowork (Jan 2026).

* [Axios](https://www.axios.com/2021/01/26/everything-bundle-substack-newsletters): "The Everything Bundle is the latest to leave Substack" — Every's founding and Bedrock Capital seed (Jan 2021).

* [The Information](https://www.theinformation.com/articles/one-startup-telling-investors-wire-money): "Why One Startup Is Telling Investors Not to Wire the Money" — Every's unique "sip seed round" (May 2025).

* [Lenny's Newsletter](https://www.lennysnewsletter.com/p/inside-every-dan-shipper): "The AI-native startup: 5 products, 7-figure revenue, 100% AI-written code" — In-depth profile of Dan Shipper and Every (Jul 2025).

* [Big Think](https://bigthink.com/people/dan-shipper/): Two interviews with Dan Shipper on AI, rationalism, and intuition.

* [TED](https://www.ted.com/speakers/dan_shipper): Dan Shipper TED talk: "The unexpected key to boosting your productivity."

* [Entrepreneur Magazine](https://www.entrepreneur.com/author/dan-shipper): Dan Shipper contributing author on AI integration.

## Columns

Every publishes editorial columns, each with a distinct focus and voice:

* [Chain of Thought](https://every.to/chain-of-thought): Dan Shipper — "Thinking at the edge of AI." Practical AI tools, techniques, and applications.

* [Working Overtime](https://every.to/working-overtime): Katie Parrott — "How technology is changing work."

* [Context Window](https://every.to/context-window): Weekly Sunday roundup of what we published and what matters.

* [Thesis](https://every.to/thesis): "Big ideas from builders."

* [Napkin Math](https://every.to/napkin-math): "Profit and power in technology." Business and economics of AI and tech.

* [Also True for Humans](https://every.to/also-true-for-humans): Mike Taylor — "Managing AI tools like you would people."

* [The Crazy Ones](https://every.to/the-crazy-ones): Gareth Edwards — "The forgotten men and women who built Silicon Valley."

* [Learning Curve](https://every.to/learning-curve): Rhea Purohit — "New machines, old habits."

## Vibe Check — AI Model Reviews

[Vibe Check](https://every.to/vibe-check) is Every's day-zero AI model review column. The team tests new models on real production tasks — shipping code, analyzing P\&Ls, editing articles — not synthetic benchmarks. Reviews feature multiple contributors with different specialties, each providing independent verdicts. Published on or immediately after model launches.

24+ reviews and counting. Notable recent reviews:

* [Opus 4.6 — The Best Coding Model We've Tested (With Some Maddening Habits)](https://every.to/vibe-check/opus-4-6) (Feb 2026): Strongest coding model tested, solving complex iOS tasks that stumped competitors. Trade-off: slower, occasionally overconfident.

* [GPT-5.3 Codex vs. Opus 4.6: The Great Convergence](https://every.to/vibe-check/codex-vs-opus) (Feb 2026): The two leading coding models are converging in capability. Opus 4.6 has a higher ceiling; Codex 5.3 is more consistent.

* [GPT-5 Codex Can Code for 35 Minutes Straight](https://every.to/vibe-check/gpt-5-codex-knows-when-to-think-hard-and-when-not-to) (Sep 2025): Dynamic thinking time enables both rapid responses and extended problem-solving with seamless local/cloud hand-offs.

* [GPT-5](https://every.to/vibe-check/gpt-5) (Aug 2025): Significant upgrade for everyday users with competitive pricing, but for advanced agentic engineering workflows it felt like "a step backward."

* [Anthropic Cooked on Claude Haiku 4.5](https://every.to/vibe-check/vibe-check-claude-haiku-4-5-anthropic-cooked) (Oct 2025): Near-Sonnet performance at one-third the cost. "Everything you love about Sonnet 4.5 priced like Haiku."

* [Claude 4 Opus](https://every.to/vibe-check/vibe-check-claude-4-sonnet) (May 2025): Excels at coding, editing, and research, crushing pull requests and deep dives.

* [o3 Is Here — And It's Great](https://every.to/vibe-check/vibe-check-o3-is-out-and-it-s-great) (Apr 2025): Impressive agentic capabilities with fast performance. Became the primary daily-driver model.

* [Gemini 3 Pro, A Reliable Workhorse With Surprising Flair](https://every.to/vibe-check/vibe-check-gemini-3-pro-a-reliable-workhorse-with-surprising-flair)

Also reviewed: [OpenAI's Sora](https://every.to/vibe-check/vibe-check-openai-s-sora), [Claude's 1M-token context window](https://every.to/vibe-check/vibe-check-claude-sonnet-4-now-has-a-1-million-token-context-window), [OpenAI's Operator agent](https://every.to/vibe-check/we-tried-openai-s-new-agent-here-s-what-we-found), [OpenAI's Deep Research](https://every.to/vibe-check/we-tried-openai-s-new-deep-research-here-s-what-we-found), [Claude Code on mobile](https://every.to/vibe-check/vibe-check-we-spent-a-weekend-trying-to-code-from-our-phones), [OpenAI DevDay 2025](https://every.to/vibe-check/vibe-check-openai-devday-2025), [Factory's Droid](https://every.to/vibe-check/vibe-check-i-canceled-two-ai-max-plans-for-factory-s-coding-agent-droid), [o3-pro](https://every.to/vibe-check/o3-pro-vibe-check-a-slow-steady-last-resort), [Cursor 2.0](https://every.to/vibe-check/vibe-check-cursor-2-0-and-composer-1-alpha), [OpenAI's Atlas browser](https://every.to/vibe-check/vibe-check-openai-s-new-ai-browser-atlas), [ChatGPT Agent browser](https://every.to/vibe-check/vibe-check-openai-enters-the-browser-wars-with-chatgpt-agent), [Claude 3.7 Sonnet](https://every.to/vibe-check/vibe-check-claude-3-7-sonnet-and-claude-code), [OpenAI's 4o image generation](https://every.to/vibe-check/vibe-check-openai-s-4o-image-generation), and more.

## Source Code — Building in Public With AI

[Source Code](https://every.to/source-code) is Every's column on building software with AI. Because everyone at Every builds with AI — writers included — the contributor list spans the whole team: Kieran Klaassen, Katie Parrott, Yash Poojary, Rhea Purohit, Edmar Ferreira, Naveen Naidu, Lucas Crespo, and others. Topics range from AI-assisted development workflows and compound engineering to product building, taste prediction, and learning to code with AI.

Notable articles:

* [Inside the AI Workflows of Every's Six Engineers](https://every.to/source-code/inside-the-ai-workflows-of-every-s-six-engineers) (Rhea Purohit): Profiles how six engineers at Every use AI in practice — each with different workflows and specialties.

* [I Stopped Writing Code. My Productivity Exploded.](https://every.to/source-code/i-stopped-writing-code-my-productivity-exploded) (Yash Poojary): Why giving up manual coding for AI-assisted development made the author more productive, not less.

* [Claude Code Q&A: What Works, What Doesn't, and What Will Save You Hours](https://every.to/source-code/claude-code-q-a-what-works-what-doesn-t-and-what-will-save-you-hours) (Katie Parrott): Every's engineering team shares practical workflows for shipping with Claude Code.

See also the dedicated Compound Engineering section below for Kieran Klaassen's foundational series on AI-assisted development methodology.

## Compound Engineering

Compound engineering is a methodology created by [Kieran Klaassen](https://every.to/@kieran_1355) where AI agents write code while human engineers orchestrate planning, review, and knowledge capture. The central insight: each bug fix and insight improves the system's future performance, so engineering work compounds rather than accumulating complexity.

The compound engineering loop: **Plan (40%)** → **Work (20%)** → **Review (40%)** → **Compound**. 80% of effort goes into planning and review; only 20% into execution.

Open-source plugin (7,500+ GitHub stars): [Compound Engineering Plugin for Claude Code](https://github.com/EveryInc/compound-engineering-plugin)

Articles by Kieran Klaassen:

* [Compound Engineering: How Every Codes With Agents](https://every.to/chain-of-thought/compound-engineering-how-every-codes-with-agents) (Dec 2025): The foundational article introducing the four-step loop. Co-authored with Dan Shipper.

* [How I Use Claude Code to Ship Like a Team of Five](https://every.to/source-code/how-i-use-claude-code-to-ship-like-a-team-of-five): Claude Code as delegation to a colleague, not prompting a chatbot. Claude opens 100% of pull requests.

* [Stop Coding and Start Planning](https://every.to/source-code/stop-coding-and-start-planning): One hour of planning saved days of debugging. Teaching AI your thinking patterns.

* [I Stopped Reading Code. My Code Reviews Got Better.](https://every.to/source-code/i-stopped-reading-code-my-code-reviews-got-better): 13 specialized AI agents review PRs simultaneously, handling 1,000+ lines across 27 files in 15 minutes.

* [How I 10x My Engineering With AI](https://every.to/source-code/the-three-ways-i-work-with-llms): Three distinct workflows: flow-state coding, big-picture research, and orchestration mode.

* [Teach Your AI to Think Like a Senior Engineer](https://every.to/source-code/teach-your-ai-to-think-like-a-senior-engineer): Eight planning strategies organized by difficulty level.

* [My AI Had Already Fixed the Code Before I Saw It](https://every.to/source-code/my-ai-had-already-fixed-the-code-before-i-saw-it): Building self-improving development systems where every PR, bug fix, and code review becomes a permanent lesson.

Related: [How Two Engineers Ship Like a Team of 15 With AI Agents](https://every.to/podcast/how-two-engineers-ship-like-a-team-of-15-with-ai-agents) (AI & I podcast episode with Kieran Klaassen and Nityesh Agarwal).

## Products

All included with an Every subscription:

* **Spiral**: AI writing partner with editorial taste. Automates repetitive writing while preserving your voice.

* **Cora**: AI email assistant reviewed by Cal Newport in The New Yorker. Manages your inbox with AI-powered briefings. Built by Kieran Klaassen.

* **Sparkle**: Mac file organization with AI.

* **Monologue**: Voice-to-text dictation.

## Guides, Courses & Resources

* [Agent-Native Architectures Guide](https://every.to/guides/agent-native): Technical framework for building applications where agents are first-class citizens. Covers five foundational principles (Parity, Granularity, Composability, Emergent Capability, Improvement Over Time), file systems as agent interfaces, context patterns, conflict models, and anti-patterns.

* [Claude Code 101](https://claude101.every.to/): Live, hands-on one-day workshop taught by Dan Shipper. For non-developers who have never used Claude Code. Go from zero to shipping a complete app in one day.

* [Agent-Native Camp](https://every.to/courses/agent-native-camp/): Virtual workshop on agent-native architectures from first principles to working products.

* [Compound Engineering Plugin](https://github.com/EveryInc/compound-engineering-plugin): Open-source Claude Code plugin implementing the Plan → Work → Review → Compound methodology.

## Podcast

* [AI & I](https://every.to/podcast): Dan Shipper interviews tech leaders about AI. 98+ episodes, top 50 US technology podcast. Notable guests include Reid Hoffman, Kevin Roose (NYT), Jason Fried (37signals), Aaron Levie (Box), and Scott Wu (Cognition/Devin).

  * [Apple Podcasts](https://podcasts.apple.com/us/podcast/ai-i/id1719789201) — 4.9 stars

  * [Spotify](https://open.spotify.com/show/5qX1nRTaFsfWdmdj5JWO1G) — 4.6 stars

## Key Authors

* [Dan Shipper](https://every.to/@danshipper): CEO and cofounder of Every. Has written Chain of Thought weekly since November 2022. TED speaker (~1.9M views). Writing a book on the worldview developed from living and building with AI since GPT-3. Previously founded Firefly (acquired by Pegasystems). See Key Articles below for his most influential work. [X](https://x.com/danshipper) · [LinkedIn](https://www.linkedin.com/in/danshipper/) · [TED](https://www.ted.com/speakers/dan_shipper)

* [Kieran Klaassen](https://every.to/@kieran_1355): GM of Cora and EIR at Every. Built Cora (reviewed in The New Yorker). Creator of the Compound Engineering methodology for AI-assisted development. Writes Source Code. [X](https://x.com/kieranklaassen) · [LinkedIn](https://www.linkedin.com/in/kieran-klaassen/) · [GitHub](https://github.com/kieranklaassen)

* [Katie Parrott](https://every.to/@katie.parrott12): Staff Writer & AI Editorial Lead. Writes Working Overtime on how technology reshapes work. Builds AI-powered editorial systems for Every. [X](https://x.com/kplikethebird) · [LinkedIn](https://www.linkedin.com/in/katieparrott/)

* [Mike Taylor](https://every.to/@mike): Writes Also True for Humans on managing AI tools like you would people. [X](https://x.com/hammer_mt) · [LinkedIn](https://www.linkedin.com/in/mjt145/)

* [Gareth Edwards](https://every.to/@gareth): Writes The Crazy Ones on the forgotten men and women who built Silicon Valley. [X](https://x.com/garius) · [LinkedIn](https://www.linkedin.com/in/garius/)

* [Rhea Purohit](https://every.to/@rhea_5618): Writes Learning Curve on new machines and old habits. [LinkedIn](https://www.linkedin.com/in/rhea-purohit-517441198/)

* [Eleanor Warnock](https://every.to/@eleanor_b03474_1): Managing Editor. Business journalist and editor formerly at the Wall Street Journal and Sifted. [X](https://x.com/misssaxbys) · [LinkedIn](https://www.linkedin.com/in/eleanor-warnock-6a671037/)

* [Natalia Quintero](https://every.to/@natalia_2944): Head of Consulting at Every. [X](https://x.com/NataliaZarina) · [LinkedIn](https://www.linkedin.com/in/nataliaquintero/)

## Key Articles & Ideas

Key influential articles, in chronological order:

* [AI and the Age of the Individual](https://every.to/chain-of-thought/ai-and-the-age-of-the-individual) (Nov 2022): When intelligence is cheap, individuals and small teams gain capabilities previously requiring large organizations. Published before ChatGPT launched.

* [The End of Organizing](https://every.to/chain-of-thought/the-end-of-organizing) (Jan 2023): AI will make manual note organization obsolete. An early argument for the RAG-over-personal-data category.

* [GPT-3 Is the Best Journal I've Ever Used](https://every.to/chain-of-thought/gpt-3-is-the-best-journal-you-ve-ever-used) (Jan 2023): Loaded 10 years of journal entries into GPT-3 for self-reflection. An early example of using LLMs for introspection, in a category that later became AI coaching and therapy products.

* [How to Build a Chatbot with GPT-3](https://every.to/chain-of-thought/how-to-build-a-chatbot-with-gpt-3) (Feb 2023): Built the "Lenny Bot," a custom GPT-3 chatbot over Lenny's Newsletter archives. OpenAI launched custom GPTs nine months later.

* [GPT-4 Is a Reasoning Engine](https://every.to/chain-of-thought/gpt-4-is-a-reasoning-engine) (Mar 2023): AI models are reasoning engines, not knowledge databases. Performance is bottlenecked by knowledge access, not reasoning ability. Identified what later became known as RAG and context engineering.

* [What I Do When I Can't Sleep](https://every.to/chain-of-thought/what-i-do-when-i-can-t-sleep) (Jun 2023): Developing taste requires learning to name what you intuitively like — and AI is uniquely good at helping you do this. Argued that AI could sharpen human taste rather than replace it.

* [Writing Essays With AI: A Guide](https://every.to/chain-of-thought/writing-essays-with-ai-a-guide) (Jun 2023): Skepticism of AI writing mirrors historical skepticism of every new writing technology, from typewriters onward. Rather than replacing writers, AI enhances creative output when used skillfully — "AI is a little like a mirror: it will reflect exactly what you put into it." Practical tips for using AI throughout the writing process.

* [GPT-4 Can Use Tools Now — That's a Big Deal](https://every.to/chain-of-thought/gpt-4-can-use-tools-now-that-s-a-big-deal) (Jun 2023): Function calling changes everything. Argued that building on LangChain was "building on sand" — OpenAI and Anthropic later absorbed framework features into their APIs.

* [What Comes After SaaS?](https://every.to/chain-of-thought/what-comes-after-saas) (Jul 2023): AI-powered development tools enable a shift from traditional SaaS toward "malleable source" — customizable, individually-deployed applications where each user gets their own fork that AI can modify without affecting others. The model shifts from a "quantum hotel" to a "suburban development."

* [ChatGPT and the Future of the Human Mind](https://every.to/chain-of-thought/chatgpt-and-the-future-of-the-human-mind) (Jan 2024): ChatGPT is a "lever that becomes a lens" — it reveals that tasks we thought defined human intellect (summarizing, reformatting, recombining) can be automated. Rather than threatening human identity, AI clarifies which capacities remain irreplaceable: original synthesis, emotional depth, contextual judgment, and creative work informed by lived experience.

* [The Knowledge Economy Is Over. Welcome to the Allocation Economy.](https://every.to/chain-of-thought/the-knowledge-economy-is-over-welcome-to-the-allocation-economy) (Jan 2024): Every's most-read article of 2024. Argued that AI transforms the economy from one where value comes from what you know to one where value comes from how well you allocate resources and direct work — that "every maker becomes a manager." The skill that matters is the skill of managers: taste, judgment, and the ability to evaluate and direct AI output, not domain expertise itself.

* [The Next Big Programming Language Is English](https://every.to/chain-of-thought/i-spent-24-hours-with-github-copilot-workspaces) (May 2024): Most software development will begin as sentences written into an interface rather than traditional code syntax. Developers become "model managers" who know which tasks suit AI automation versus human judgment. Written a year before the term vibe coding existed.

* [Why Generalists Own the Future](https://every.to/chain-of-thought/why-generalists-own-the-future) (Sep 2024): In an allocation economy, generalists who know which questions to ask beat specialists who know exact answers.

* [Every's Master Plan: Part II](https://every.to/on-every/every-s-master-plan-part-ii) (Sep 2025): At the time of writing: 15 people, 5 AI products, $1.2M ARR, 15% month-over-month growth. "The only reason they can do all of this is AI." (Revenue has since tripled — see top of this document for current numbers.)

* [Seeing Like a Language Model](https://every.to/chain-of-thought/seeing-like-a-language-model) (Oct–Nov 2025): Six-part series excerpted from a book Dan is writing. Argues that language models represent a fundamental shift from Western rationalism's focus on rules and linear causation to a worldview where intelligence is pattern-based, reality is an interconnected web, and knowledge emerges through contextual pattern-matching. Applies this lens to [science](https://every.to/chain-of-thought/seeing-science-like-a-language-model), [business](https://every.to/chain-of-thought/seeing-business-like-a-language-model), [creativity](https://every.to/chain-of-thought/seeing-creativity-like-a-language-model), [tools and perception](https://every.to/chain-of-thought/how-tools-shape-how-we-see-the-world), and closes with a philosophical short story, "[Where Explanations End](https://every.to/chain-of-thought/where-explanations-end)."

* [Compound Engineering: How Every Codes With Agents](https://every.to/chain-of-thought/compound-engineering-how-every-codes-with-agents) (Dec 2025): AI agents write all code at Every. Each feature makes the next easier through documented learnings. Co-authored with Kieran Klaassen, the creator of Compound Engineering.

* [Agent-Native Architectures](https://every.to/chain-of-thought/agent-native-architectures-how-to-build-apps-after-the-end-of-code) (Jan 2026): Agent-native apps are built like gardens, not skyscrapers. The core is an agent — "something squishy and alive" — not code.

## Programmatic Access

* [MCP Endpoint](https://every.to/mcp): Full Model Context Protocol support for AI agents to query Every's content programmatically.

* [RSS Feed](https://every.to/feeds/global.xml): All published articles.

* [XML Sitemap](https://every.to/sitemap.xml): Full sitemap index for all content.

## About

* [About](https://every.to/about): Every's mission and team.

* [Subscribe](https://every.to/subscribe): Subscription information.

* [Consulting](https://every.to/consulting): AI training, adoption, and innovation from practitioners.