1import{u as o,j as e,L as t,F as s,aa as a}from"./index-BuZhJDdE.js";import{S as n}from"./SeoArticleShell-JxXbURnn.js";import{M as i}from"./MeetKonshusCta-BfkHeub8.js";import"./PatentNotice-XdrwjSAN.js";import"./StatusFooterIndicator-BtUT8W_X.js";import"./status.functions-B2G_pQBG.js";import"./shield-check-D2UUqTYU.js";import"./useSuspenseQuery-B9qBZF_L.js";import"./comments.functions-BhssvNSi.js";import"./arrow-right-BW_4nWa4.js";function w(){return o("notion_as_ai_memory_view"),e.jsxs(n,{children:[e.jsxs("article",{className:"mx-auto max-w-3xl px-6 pt-12 pb-4",children:[e.jsx("p",{className:"text-xs uppercase tracking-wider text-ink/50 mb-3",children:"A guide · ~6 min read"}),e.jsx("h1",{className:"font-serif text-4xl md:text-5xl leading-tight text-ink mb-5",children:"Notion as AI memory: the export playbook"}),e.jsx("p",{className:"text-lg text-ink/75 leading-relaxed",children:"A long-running Notion workspace is the most underused training dataset most knowledge workers own. Project briefs, quarterly reviews, meeting notes, the running personal CRM, the half-finished essay. Years of evidence about how you think. And almost none of it ever shows up in your ChatGPT conversations."})]}),e.jsxs("section",{className:"mx-auto max-w-3xl px-6 py-8 space-y-4 text-ink/80 leading-relaxed",children:[e.jsx("h2",{className:"font-serif text-2xl md:text-3xl text-ink !mt-4",children:"The export, in 4 steps"}),e.jsxs("ul",{className:"list-disc pl-6 space-y-2",children:[e.jsx("li",{children:"Open Notion in the browser (the desktop app exports too, but the browser is simpler)."}),e.jsxs("li",{children:["From the workspace root or any page, click ",e.jsx("strong",{className:"text-ink",children:"⯠â Export"}),"."]}),e.jsxs("li",{children:["Pick ",e.jsx("strong",{className:"text-ink",children:"Markdown & CSV"}),'. Check "Include subpages" and "Create folders for subpages."']}),e.jsx("li",{children:"Download the ZIP. For a 5-year workspace this might take 5â10 minutes to generate; the file itself is usually 50â500 MB."})]})]}),e.jsxs("section",{className:"mx-auto max-w-3xl px-6 py-8 space-y-4 text-ink/80 leading-relaxed",children:[e.jsx("h2",{className:"font-serif text-2xl md:text-3xl text-ink",children:"Why Notion AI alone isn't enough"}),e.jsx("p",{children:"Notion AI is genuinely good at searching and summarizing inside your workspace. But it's a Notion feature, not a you feature. It doesn't follow you when you open Claude to draft an email, or ChatGPT to think through a decision, or Gemini to plan a trip. The AI layer is welded to the surface it lives on."}),e.jsx("p",{children:"The point of treating Notion as memory is to take what you've put in there and make it work for you in every AI you use, not just the one that ships with Notion's logo."})]}),e.jsxs("section",{className:"mx-auto max-w-3xl px-6 py-8 space-y-4 text-ink/80 leading-relaxed",children:[e.jsx("h2",{className:"font-serif text-2xl md:text-3xl text-ink",children:"What the distillation layer actually does"}),e.jsx("p",{children:"Raw export â 500 MB of Markdown. No model can read that on every question. The job of a memory vault is to do the heavy lifting once and produce a compact persona."}),e.jsxs("ul",{className:"list-disc pl-6 space-y-2",children:[e.jsx("li",{children:"Pulls out projects you've worked on long enough to be a pattern, not a one-off."}),e.jsx("li",{children:"Surfaces people who appear across many pages â your repeat collaborators, your clients, your inner circle."}),e.jsx("li",{children:"Notices the frameworks you keep reaching for (the way you structure decisions, the questions you ask yourself)."}),e.jsx("li",{children:"Discards the noise â single-meeting notes, abandoned drafts, kept-for-posterity recipes."})]})]}),e.jsx("section",{className:"mx-auto max-w-3xl px-6 py-6",children:e.jsxs("div",{className:"rounded-xl border border-border/60 bg-muted/30 p-5",children:[e.jsx("p",{className:"text-xs uppercase tracking-wider text-ink/50 mb-2",children:"Short answer"}),e.jsx("p",{className:"text-ink leading-relaxed",children:"Export your Notion workspace as Markdown & CSV with subpages included. Load the ZIP into a memory vault that distills the workspace into a persona â your real projects, your recurring people, the frameworks you actually use. Paste the persona into any AI and it'll behave like one that's read your second brain."})]})}),e.jsxs("section",{className:"mx-auto max-w-3xl px-6 py-8 space-y-4 text-ink/80 leading-relaxed",children:[e.jsx("h2",{className:"font-serif text-2xl md:text-3xl text-ink",children:"The portable answer"}),e.jsx("p",{children:"Konshus has a Notion importer on Founding and above. Drop the Markdown ZIP in once a month; we extract atoms across the whole workspace and produce a persona that fits in any AI's prompt. The full pages stay in your vault for retrieval; the persona is the part the world sees."}),e.jsxs("p",{children:["See also"," ",e.jsx(t,{to:"/readwise-to-ai-persona",className:"text-gold underline underline-offset-2",children:"Readwise â AI persona"})," ","and"," ",e.jsx(t,{to:"/obsidian-ai-persona",className:"text-gold underline underline-offset-2",children:"Obsidian â portable persona"}
1)," ","if your second brain isn't only in Notion."]})]}),e.jsx(s,{items:a}),e.jsx(i,{variant:"bottom",headline:"Your second brain, in every AI.",body:"Konshus turns your Notion export into a portable persona â so the years you've spent writing in Notion finally show up in every other AI you use."})]})}export{w as component};
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.