Structure Beats Magic
The vocabulary

Concepts & vocabulary

A thesis earns its own words. These are the named concepts behind Structure Beats Magic — one memorable name per idea, so it can be pointed at, reused, and built on. Click any concept for the full picture. Not jargon for its own sake; a shared language for a system you can actually run.

See the concept map → — every idea and how it connects, in one interactive view.

The vocabulary

Named concepts

The coined terms this thesis owns — grouped by where they live in the system. Each links to its own page.

Umbrella thesis

14
A Compounding Asset
A structured second brain gains value with every note — like reinvested capital.

A pile of notes depreciates; a structured knowledge system compounds. Every new note, connection and rule increases the value of what's already there, the way reinvested returns build financial capital. The structure is what converts…

Cross-Pollination
Three practices — personal knowledge, data modelling, and the thinking itself — that stay separate but keep feeding each other. The convergence is the result; the pollination is the mechanism.

Three practices run in parallel — organising your own knowledge, modelling data for organisations, and the thinking that sits above both. They are not one discipline and should not be merged. But each keeps producing things the others turn…

Deliberate by Design
Structure isn't what happens to your data — it's what you choose. The opposite of accidental.

The word underneath the whole thesis: deliberate. A deliberate structure, a deliberate shape, a deliberate boundary, deliberately separate zones, sources deliberately judged worth trusting. Every one marks the same distinction — between…

Deterministic by Design
Deliberate is whether the structure was chosen; deterministic is whether the output repeats. A toy is neither on the second try.

The sister word to *deliberate*, and the one people miss. Deliberate is about the structure: was this shape chosen, or did it just accumulate? Deterministic is about the behaviour: does the same input produce the same result on the second…

Find the Essence First
Before you structure anything, find its essence — the one core it's actually about. Everything else is ballast.

The move underneath the whole way of working: find the essence. Before an article is written, ask what it is *really* about — the one claim, in one sentence. Before a data model is drawn, find the core business concepts, not every table.…

Knowledge Management vs Knowledge Engineering
Managing knowledge keeps it findable for people; engineering it makes it computable for machines. The second is the shift.

Two disciplines that both deal with knowledge, easily confused, but aimed at different readers. **Knowledge management organizes knowledge for people; knowledge engineering formalizes knowledge for machines.** KM makes knowledge findable…

Priced on the Outcome
Advice is priced by the hour because nobody can stand behind it; an outcome can be priced — and owned — only once a governed decision layer makes it repeatable.

Most expertise is sold by the hour, and the reason is rarely admitted: you bill for time because you can't stand behind the result. The advice is sound, but whether it *works* depends on a dozen things you don't control, so the honest unit…

Structure Beats Magic
The magic isn't in the model; it's in the structure you give it.

The master brand: knowledge management re-architected for the AI era. Output quality comes from the structure around the tools — models, rules, metadata — not from the tools or hope.

Structure Lets a Cheaper Model Win
The thesis priced: good context and skills make a cheaper model perform near the top tier. If quality survives a downgrade, the value was your structure.

The thesis made falsifiable — and priced. When people fear losing access to the most expensive model, the honest fix isn't a bigger budget; it's an audit of the structure. A context file that reflects reality, repeated work distilled into…

Systematic Knowledge
Knowledge organised and interconnected through deliberate structure.

Knowledge made systematic: organised, connected and usable because it has a deliberate shape, so you can think better and create more.

Systemic Knowledge
Knowledge treated as a system, not a pile of notes.

A framing of personal knowledge as a system with inputs, structure and feedback — the whole behaves as one, not as isolated notes.

The Compounding Brain
Every piece of work feeds back in, so the system is smarter next time than last.

A brain rewires itself with use; a good system should too. Every decision, procedure and lesson feeds back into the structure — tend it, and it compounds.

The Missing System
Orgs have systems of record; almost none have the intelligence layer on top — data + AI + rules.

Every organisation runs the obvious systems — accounting, CRM, HR, operations. All are systems of record: authoritative, transactional, backward-looking. The one almost nobody builds is the layer above them — a system of intelligence that…

The Rear-View Mirror Problem
A system of record shows what's behind you; steer by it alone and you drive forward looking backward.

The sticky one-line hook for why reporting/BI isn't intelligence. A system of record is a rear-view mirror: accurate, detailed, essential — and entirely about what's already behind you. Most organisations, for all their expensive systems…

Personal data model

9
A Modeled Self
Your history, desires and lessons captured as structured data — not left to chance.

History, desires and hard-won lessons captured as structured data, so AI works from a model of you instead of whatever it happens to remember this session.

Knowledge Graph
A living graph of your life you can ask natural questions.

People, places, trips, events and interests, all connected — a living knowledge graph you query in natural language and that answers from your structured data, not a guess.

Notes Organize. Architecture Personalizes.
Storing notes is where most advice stops; AI needs a model of you.

Storing notes is where most 'second brain' advice stops. To make AI act for you with focus, it needs architecture — a model of you — not just organised notes.

Personal Data Warehouse
One structured store for your knowledge: sources → integration → delivery.

The enterprise data-warehouse pattern applied to a life: sources flow through integration into delivery, giving one structured source of truth for personal knowledge.

Self Models
The parts of you an AI can't infer — your taste, your limits, your voice, your history — written down as durable data the system reads instead of guessing at.

A self model is a written, structured description of one facet of who you are — held as data the system can read, rather than a thing an AI has to infer from the last few messages. Your taste is a self model. Your risk appetite is a self…

The Digital Twin
A living, structured model of your world — private and under your control.

A living model of your world built from your data and enriched by AI — more than storage, it is understanding, and it stays private and yours.

The Story of Your Life
A structured life isn't an archive of facts — it's a story you can read back, search, and that keeps writing itself.

Give your life enough structure and something quietly shifts: the pile of notes, photos, trips, receipts and decisions stops being an archive and becomes a *narrative*. Not a folder you dread opening, but a story — one you can read back…

The Structure Pyramid
Raw data → metadata → entities → relationships → knowledge graph → understanding.

The ladder from raw data up to understanding: each layer adds structure — metadata, entities, relationships — until the pile becomes a knowledge graph you can reason over.

Your Risk Profile
Define, once and in writing, how much risk you actually accept — so any activity, at home or on holiday, can be tested against it instead of decided in the heat of the moment.

Every activity carries a risk profile whether you name it or not. A motorbike ride, a dive, a via ferrata, a big financial move, a remote hike, a new city at night — each one sits somewhere on a scale of how much can go wrong and how…

Filtering & identity

8
Anti-Interest Filtering
Defining what you are not interested in, so the system can filter to what matters — focus lives in the negative space.

Expliciet vastleggen wat je **niet** wilt zien. Het spiegelbeeld van preferences: niet wat je aantrekt, maar wat je actief weert. In een persoonlijk aanbevelingssysteem is dit de rem naast de motor.

Anti-Interests
A declared list of what you're not interested in — a veto over recommendations.

An explicit, declared list of what you are not interested in: a veto that kills a plausible-but-unwanted recommendation regardless of how well it scored.

Collecting Is Not Capability
The prompt library you never open and the hacks you screenshot but never run are consumption in a productivity costume — only applied structure counts.

The AI-tips economy runs on a comfortable illusion: saving the infographic feels like acquiring the skill. The screenshot lands in the vault, the prompt joins the library, the bookmark folder swells — and the feeling of progress is real…

Continuous Exploration
Standing outward search through your own filters — the system keeps looking when you aren't, and reports back.

Exploration is the outward-facing half of a personal intelligence system: agents that scan the world along search paths *you* defined, score what they find against your affinities, drop what your vetoes exclude, and surface the remainder.…

Curated Sources
A person or publication you've deliberately judged worth trusting, fed to the system as a filter. (aka Handpicked Sources.)

A person, publication or collection you have deliberately judged worth trusting — scored for relevance and quality — and fed to the system as a filter. Two registers for the same idea, pick by audience: "curated sources" is the…

Recommendation (Affinity Matching)
Scoring what's new against what you've already proven you love — the engine that anti-interests puts a veto on.

Affinity matching answers one question: *given everything I already know you like, how close is this new thing?* It scores a candidate against a model of your taste built from your own history — the trips you actually took, the books you…

The Life Debrief
A debrief scaled up to a whole period of life — a periodic, cross-domain look at where you're actually heading, run against your data, not your memory of it.

You already debrief events — a project, a trip, a hard conversation: what happened, what you learned, what you'd change. The life debrief is that same move scaled up to a whole *period* of life. Not the annual box-tick of "did I hit my…

Via Negativa
You are also defined by what you are not.

Describing a thing by what it is not — applied to the self: what you're not is also who you are, and declaring it sharpens the model.

Intelligence systems

9
AI ROI
AI only pays back on top of structure. The return isn't in the model — it's in what the model can rely on.

The return on AI doesn't live in the model — it lives in what the model can rely on. Most AI initiatives never deliver measurable impact, and the failures share a shape: the AI was added as a touchpoint on top of unstructured reality, so…

Company Brain
The org-scale second brain: shared, structured, permission-aware knowledge AI can rely on. Wiring tools together isn't it — access is not memory.

A company brain is the organisation-scale version of a personal second brain: one living, structured, permission-aware knowledge layer that both humans and AI can rely on — connected, contextual, continuously updated. It is what almost…

Content Intelligence
Zettelkasten for the AI age — curated sources to validated building blocks.

Curated sources → AI-extracted knowledge highlights → validated → reusable building blocks for writing and talks. A [[concept-zettelkasten|Zettelkasten]] for the AI age.

Email Intelligence
Classify every sender signal-vs-noise; turn an inbox into a managed source.

A sender-centric system: classify every sender as signal or noise, auto-generate filters, and turn an overflowing inbox into a managed source.

Intelligence Systems
Curate sources, structure them, let AI extract and validate — applied to a whole domain.

The repeatable pattern — curate sources, structure them, let AI extract and validate — applied to whole domains of life, turning raw history into something you can ask.

Marketing Intelligence
A years-deep newsletter archive mined for what the market is actually saying.

A large newsletter/promo archive mined with DuckDB, AI and rules to reveal what the market is actually saying, over years.

People Intelligence
Years of messages, mail and CRM history → a structured picture of relationships.

WhatsApp, mail and CRM history mined and structured into a picture of who matters, how you're connected and what you've promised.

Reading Intelligence
Your reading history read back as synthesized insight — highlights and saves curated, structured by domain and date, and reasoned over by AI.

The Intelligence Systems pattern applied to the one input stream everyone has and nobody harvests: their own reading. Separate the curated signal (your sparse, deliberate highlights and saves — a vote, not a bookmark) from the feed noise…

Trip Intelligence
Daily notes plus curated photos become a trips database you can share.

Daily notes and curated photos flow into a trips database — curated trip data you can share with a travel companion.

Method & workflow

37
A Brain That Publishes Itself
One source of truth in a database; a website derived from it at build time.

One source of truth in a database, with the website derived from it at build time — no CMS, no runtime database, no drift.

Articulation as Learning
You do not know it until you have written it in your own words — articulation is the test, not the record of learning.

Je leert een onderwerp niet het diepst door het te lézen, maar door het te moeten **formuleren** — expliciet genoeg om het te sturen, te beoordelen en te corrigeren. Het dwingen tot articulatie verankert dieper dan opnemen. Een artikel…

Bus Factor of One
The number of people who'd have to disappear before your system becomes unmaintainable — and for most personal systems that number is one.

**How many people would have to disappear before this becomes unmaintainable?** If the answer is one, you have not built a system — you have built a dependency on yourself.

Capture Types
A systematic vocabulary of typed captures: idea_, question_, decision_, action_ …

Type-first naming: every atomic capture gets a type prefix (idea_, question_, decision_, action_, debrief_, learning_ …) so prose becomes queryable data.

Cascade Roll-ups
Automatic aggregation: Day → Week → Month → Quarter → Year.

Notes roll up automatically along the calendar spine — day into week, week into month, up to the year — so summaries stay current without manual effort.

CLAUDE.md as Operating System
Standing rules the AI reads before it acts — a layered OS for how the assistant behaves in your world.

The real leverage isn't prompts, it's standing rules the AI reads before it acts. A layered CLAUDE.md — root to domain to subfolder — is an operating system for how the assistant behaves: HARD rules with the reason they exist (expensive to…

Communication Is Everything
Nothing exists in an organisation until it is communicated — a model, a decision or an insight has no effect until it lands with someone.

**Nothing exists in an organisation until it is communicated.** A model that nobody understands does not constrain anything. A decision that was never landed gets relitigated. An insight held by one person is, organisationally, an insight…

Concepts in Action
A named concept earns its place only when you can point to it operating in a real artifact — the bridge from the concept library to the systems and articles that prove it.

A concept library is easy to fill with clever-sounding terms. The discipline is that a concept isn't *earned* until you can show it working in something real — an article that demonstrates it, a system that runs on it, an engagement where…

Content-to-Training
The same structured knowledge feeds every output — an article, a workshop, a course, a talk — because it's stored as reusable units, not one-off documents.

Most people write an article, then start a training from scratch, then rebuild the same idea again for a talk. The knowledge is the same each time; only the format differs — but because it was captured as a finished document rather than as…

Continuous Learning
Learning as a standing process rather than a course you finish — the system keeps feeding you and keeps score.

Elke dag een paar **knowledge bites** uit je eigen vault met je delen — kleine stukjes van wat je al hebt vastgelegd, teruggebracht onder je aandacht zodat het beklijft in plaats van te verzanden.

Decision Records
Big choices written down with options and reasoning (ADR/PDR/IDR/BDR).

Big choices written down with the options considered and the reasoning: Architecture (ADR), Personal (PDR), Investment (IDR) and Business (BDR) decision records.

Derived Insight
The highest-value data is the data you never typed — rules generate it from existing data plus context.

Rules don't only validate — they generate. When the system sees a location inside a time interval it infers 'probably work' or 'inside trip X'; raw signal becomes derived insight. The enrichment layer: new data created from existing data…

Drawing It Together
Model with the business, don't model for them — sketch on a shared canvas until the picture matches how they actually think. The diagram is where agreement happens.

The conceptual model isn't handed down; it's drawn together. Sitting with a stakeholder who has never read a line of SQL and agreeing what a 'customer' is and how it connects to an 'order' happens by sketching it on a shared surface — a…

Flattery Is Failure
When AI output makes you feel smart, treat that as a warning signal, not a reward. Agreement is the cheapest thing a model produces — and the most expensive thing to believe.

Three words that reclassify a feeling. When AI output makes you feel smart — when the summary of your notes reads like wisdom, when the plan built from your material seems obviously right, when the assistant agrees with your framing on the…

Grounded Skills
Build reusable instructions only from your own sources, with receipts: every line cited to something you wrote or vetted — no citation, no line.

A skill is a document the AI will obey hundreds of times — which makes an invented line in a skill categorically worse than an invented line in a chat. The chat hallucination misleads once and dies with the session; the skill hallucination…

Honesty Over Helpfulness
A confident wrong answer costs more than an honest 'I don't know' — so make honesty a standing rule: only report work you have evidence for.

The model's default failure isn't malice — it's eagerness. Trained to be helpful, it would rather hand you a fluent wrong answer than an honest "I'm not certain," because fluency *feels* like help and hesitation doesn't. You can't fix that…

Inbox Triage
Every place loose input arrives needs a fast per-item sort — process, archive, discard, defer — before anything reaches the vault.

Every place where loose, unsorted input arrives — a capture note, a downloads folder, clipped articles, the collaboration inbox, documents that don't yet have a sidecar — needs a **triage step**: a fast, per-item decision about where each…

Knowledge Bites
Your summary of a chapter is not the chapter — it is a new, standalone unit of your understanding, and it should be stored as one.

When you summarize a chapter in your own words, you are not representing the chapter — you are producing a new thing: your understanding of it, as a standalone unit of knowledge. That thing is a **knowledge bite**: an atomic…

Let the AI Interview You
Reverse the roles before the work starts: the AI studies what exists, then asks you what it can't infer — the gaps it fills silently are where it fails.

The instinct is to write a better prompt. The structural move is to reverse the roles: before the work starts, make the AI extract the context from you. One sentence does it — *"ask me everything you need to know before you start"* — and…

Living Diagrams
A diagram generated from the structure is always current; a hand-maintained one rots. Read the picture from the source, don't transcribe it.

The visual counterpart to 'a brain that publishes itself': because the structure is real, machine-readable metadata — entities, links, typed fields — you don't draw the picture and maintain it by hand, you generate it. A diagram derived…

Never Marks Its Own Homework
The judge must be separate from the builder, and the score is the off-switch: a loop only stops when an independent evaluator says the rubric is met.

The moment AI runs in a loop — try, check, retry until done — one question decides everything: who says it's done? The unreliable answer is the model itself, and it's unreliable for a structural reason, not a moral one: a writer always…

One-Way Publishing
You don't sync systems — you publish from one. Sync is where rot starts.

One place is authoritative (the vault); everything else — Google Tasks, Projects, a mobile subset, PDF exports — is a one-directional, never-back view generated from it. The vault always wins; downstream targets are disposable and…

Operating Model
How a system, team or business actually runs day to day — the concrete machinery underneath the strategy, not the org chart or the vision slide.

An operating model is the answer to "how does this actually *work* on a Tuesday" — the specific, repeatable way work flows, decisions get made, and outputs get produced. It sits below strategy (the *what* and *why*) and above tooling (the…

Red-Team Your AI
A synthesis of your own material flatters you; assign a second AI to attack it.

When AI synthesizes your own notes, data, or writing into a plan or summary, the result sounds wise — because it *is* you, distilled and rhythm-corrected. That fluency is the danger: reading it feels like insight when it may just be a…

Rules You Can Verify
'2-space indent' is a rule; 'format code properly' is a wish. A rule the system can't check is decoration.

Most people's AI rules fail before the model ever disobeys them — they fail at the writing desk, because "be professional" and "format properly" cannot be complied with or violated. There is no output that unambiguously breaks them, so…

Runbooks
A repeatable procedure written down so a task is done the same way every time.

A runbook captures a repeatable procedure — 'how I process the inbox', 'how I refresh the backups' — so the task is done the same way every time.

Smart Teams
A data-team operating model where structure carries the context, so the synchronous meeting shrinks to the merge of pre-prepared, AI-validated material.

Smart Teams is what a data-modeling/-engineering team looks like when the [[concept-operating-model|operating model]] is built on structure instead of meetings. Each person, with their own AI assistant, analyzes the facts, data and rules…

Spaced Repetition (Flashcards)
Recall scheduled against forgetting: the interval widens as the memory holds, so review time goes where it is actually needed.

Het leermechanisme onder [[Continuous Learning]]: iets **net vóór je het vergeet** opnieuw zien, zodat het met minimale moeite blijft hangen. Een **flashcard** is de kleinste eenheid — één vraag, één antwoord; **spaced repetition** is het…

Stop Prompting, Start Directing
Set up a system before the task; give AI an outcome, context, constraints and a way to validate.

Turn one-off chats into a reusable system: before the task, give the AI an outcome, context, constraints, a process and a way to validate its own output.

The Cut Test
One question decides what stays in your rules: would a future session get something wrong without this line? If not, cut it. Bloat isn't structure.

The failure mode of people who *get* structure is over-structure: the forty skills of which three are used, the prompt library never opened, the context file that grew past the point where the model still follows it. Adherence measurably…

The Meeting Is Just the Merge
Structure carries the context, so the meeting is only where prepared work merges.

In a structure-driven team, each person's AI assistant has already analysed the underlying data, rules and facts and prepared what to discuss and decide. The synchronous meeting stops being for status or catch-up and becomes the merge of…

The Mistakes File
Same mistake twice = a new rule. Corrections you'd otherwise repeat forever get written into a file the AI reads every run.

The compounding brain has a concrete unit of compounding, and it's the correction. Every time you fix the AI's output the same way twice, that fix is a rule waiting to be written — into a mistakes file, a skill's "never do" section, a new…

The Validation Loop
Generate → validate → flag, don't guess → improve — and improve the checks too.

A loop where rules check the output, the system flags rather than guesses, and the checks themselves get reviewed and improved over time.

The Voice Layer
Make AI write like you, not like AI — a standing voice corpus mined from your unpolished sources.

How you stop the model sounding like a model: a standing voice corpus distilled from real, unpolished sources (sent mail, messages) plus an explicit anti-AI banned-words list. The key rule — AI-generated text is the anti-example, never the…

The Workshop and the Display Case
The vault is the living workshop; everything published from it is a frozen display case.

Your vault is the workshop — the single living source of truth where work happens. Claude Projects, a published mobile subset, a shared folder, Google Tasks are display cases: bounded, frozen snapshots built for a specific audience. The…

Tribal Knowledge
The understanding lives in people's heads and informal conversation — never in the model, the docs, or anywhere a newcomer or an AI can reach it.

**The understanding exists, but only in people.** Not in the model, not in the documentation, not in anything a newcomer can read — in heads, in corridor conversations, in "ask Marieke, she knows how that table works."

Write-Only Knowledge
Easy to produce, impossible to read back — notes, code and models that made sense while you wrote them and never again.

From "write-only code" — technically elegant, comprehensible at the moment of writing, impenetrable afterwards. **Write-only knowledge** is the same failure applied to everything else you produce: notes, models, captures, generated…

System architecture

27
Agreement-Centered Governance
Almost everything in life is an agreement — with companies, within a family, with yourself. Model them and check them against evidence: an agreement no one checks is a hope.

Almost everything in life can be defined as an agreement — far more than we think. The obvious ones wear the word: contracts, subscriptions, insurance policies. But look again and they're everywhere: the warranty on the machine, the terms…

Atomic Documents
One document is one thing — the indivisible unit you can share, version, validate and link without tearing it apart.

A document holds exactly one idea, capture, or record — not a folder's worth of loosely-related notes crammed into one file. Atomicity is what makes everything else possible: an atomic document can be **shared, versioned, validated, moved…

Compile, Don't Retrieve
RAG retrieves chunks per query and hopes; a wiki compiles knowledge once, structured, so the answer is read not reassembled. Do the work at write time, not read time.

Two ways to give an AI access to your knowledge, and the difference is *when the work happens*. Retrieval — the RAG pattern — does the work at read time: every query, grab the chunks that look similar, stuff them in the context, hope the…

Connect & Dispatch
Capture anywhere, dispatch to where the power is, commit back to the one vault.

Capture anywhere, dispatch the work to where the power is, and commit back to the one vault — the devices are doors; the versioned markdown is what's yours.

Document Change-Log
Each document carries its own history of changes — so a shared record is traceable, and a sync knows what changed, when, and by whom.

A document isn't just its current state; it holds a **log of its own changes** (a `## History` / change-log section, or structured `updated:` + revision entries in frontmatter). This is quiet housekeeping in a single vault, but it becomes…

Document Vault
Plain files in a deliberate shape that both you and AI can navigate.

A well-structured document vault — plain files in a deliberate shape — that makes data findable, linkable and trustworthy for both you and AI.

Exchange Layer
A controlled front door (inbound) and publication layer (outbound).

A deliberate boundary for data in and out: a controlled front door for ingestion (inbound) and a publication layer for what leaves (outbound).

Federated Brains
Sovereign vaults that stay separate but exchange chosen data through a validated, permissioned interface — not one merged brain.

Two or more people each run their own sovereign vault and AI. They share *some* data — but never merge, and never read each other's files directly. Each node stays whole and private; only a chosen, contracted set crosses the boundary…

Files for Facts, Skills for Behavior
One filing test for every piece of context: does it change weekly? Yes → it's a fact, keep it in a file. No → it's behavior, make it a standing rule or skill.

The commonest structural mess in an AI setup isn't missing context — it's context filed at the wrong altitude. Universal rules repeated in every project. This week's numbers fossilised into standing instructions, still steering the model…

The Folder Note
A note that lives inside a folder and carries its name — the folder's own description, so a directory can say what it is.

A **Folder Note** is a Markdown note that lives inside a folder and shares that folder's name, and whose job is to describe what the folder contains. It is the folder's front page — the note you would write if someone (or something) asked…

Gates
A conditional control point: nothing passes by default, it passes because it qualified — quality you can point at instead of hope spread thin.

A **gate** is a conditional control point in a flow: a place where something may pass only if it meets a condition. Nothing crosses a gate by default — it crosses because it qualified. That single idea, applied deliberately, is one of the…

Hooks Over Hopes
Every instruction to a model is a probability, not a promise. Rules that must always run belong in deterministic automation the model can't skip.

Every instruction you give a model is a probability, not a promise. Even a rule written in capitals in the operating-system file is *obeyed*, not *enforced* — the model reads it, weighs it against everything else in context, and usually…

Living Timeline
The calendar spine isn't an archive — it's a timeline that keeps summarizing itself.

The calendar spine (day to week to month to quarter to year) is not a filing cabinet where dated things go to rest; it's alive. New inputs land on it — captures, transactions, even imported AI chat history — and cascade roll-ups…

Loosely Coupled Documents
Documents reference each other through frontmatter links, not by copying content — so metadata travels with the document and it stays understandable anywhere.

Documents connect to each other through **frontmatter links** ([[wikilinks]], IDs, `companion_to`, `owner`), never by duplicating each other's content. The coupling lives in the metadata, so it's cheap to change one document without…

Map of Content (MOC)
A hand-made map that gathers the notes on one topic — navigation for you AND for the AI.

A Map of Content is a note whose job is to point at other notes: a curated index for one topic, project or domain, linking the pieces that belong together. Unlike a tag (a flat label you hope to match later), a MOC is an authored map with…

Markdown Is Already the Graph
You keep being told to load your notes into a vector database or a graph database. If they're structured and linked, you already have the graph — the agent can walk the files.

The standard advice for making your notes useful to an AI is to move them somewhere else: chunk them, embed them, load them into a vector database, or stand up a graph database and import them. It sounds like the serious version of the…

Personas
One engine, many selves — the vault stays the same, the persona on top is swappable.

Separate the data from the preferences, rules and history: the vault engine stays the same and the persona loaded on top is swappable.

Sovereign Personal System
Sovereignty, privacy and backup are the foundation, not an afterthought.

A powerful personal system is worthless if you don't own and protect what's in it — sovereignty, privacy and backup are the foundation everything else sits on.

The Calendar Is the Spine
One time-axis is the backbone of a second brain — everything dated hangs off it.

Everything dated hangs off a single year to quarter to month to week to day tree. The daily note is an index of the day, not a container; atomic captures land in day-folders; content rolls up along the spine. One predictable axis makes…

The Context Graph
The knowledge graph knows what exists; the context graph is what this decision needs — scoped at runtime, small enough to reason across, not search through.

The missing word between having structure and using it. A knowledge graph knows *what exists*: thousands of nodes, every entity and relationship, stable, domain-scoped, the whole memory. That completeness is its job — and its trap. A…

The Controlled Front Door
A node never exposes its vault — only a small, declared set of data it chooses to share, governed by rules, on request or on schedule.

How a sovereign node shares without opening up. The vault is never readable from outside; instead the node exposes a **front door** — a deliberate, named set of tools/resources (e.g. an MCP server), each one governed by rules. Nothing…

The Daily Note
One note per day, auto-filled from your own data, that rolls up over time.

One note per day, largely auto-filled from your own data — where you were, what you spent, what you captured — that then rolls up from day to year. Each daily note is an atomic unit that carries its own properties (frontmatter) and links…

The Neural Metaphor
The whole architecture reads as a brain — atomic documents are neurons, frontmatter links are synapses, the vault is the brain, federation is brains talking, and each cell holds a memory.

The reason the whole family of concepts is named for a *brain* and not a database: the structure genuinely maps to how a brain is built. A database stores rows; a brain remembers, connects, and grows. Same underlying structure — a picture…

The Reasoning Layer
The layer where the AI actually thinks — reliable conclusions come from the structure underneath it, not from the model being clever.

The layer everyone mistakes for magic. When AI gives a good answer, it feels like the model reasoned its way there. But the reasoning is only as good as what sits beneath it: the context it can reach, the memory across sessions, the rules…

The Three-Worlds Split
Content, data and code live in deliberately separate zones.

A personal system has three distinct worlds that must not be mixed: content (markdown — the second brain), data (databases — the queryable layer) and code (scripts, repos). Notes aren't a database; databases aren't a repo; code doesn't…

The Validated Exchange Layer
Vaults never read each other directly — what crosses the boundary is validated on the way out and in.

The federation mechanism: when individual and team systems work together, they never read each other directly. What crosses the boundary passes through a publishing layer that validates on the way out and on the way in — the same…

Zettelkasten
Luhmann's slip-box: atomic, linked notes that let ideas collide. The insight was never the box — it was the structure. The labour is what killed it; AI removes exactly that.

The original structured second brain. Sociologist Niklas Luhmann kept ninety thousand index cards in a slip-box — *Zettelkasten*, German for exactly that — and credited it as the co-author of his seventy books. Each card held one idea…

Brand & stance

15
A Toy vs an Instrument
Without structure AI is a toy; with structure it becomes an instrument.

Without structure, AI is a toy: impressive once, unreliable twice. With structure it becomes an instrument you can rely on.

Bankers vs Builders
The discipline of governance meeting the leverage of builders — speak both.

Bankers and builders speak different languages: one values governance and control, the other leverage and speed. The stance is to speak both.

Eat Your Own Dogfood
Use your own tool/method on your own real work before and while you ask anyone else to — dogfooding surfaces the flaws a demo hides.

Dogfooding is the engineering discipline of running your own product on your own real problem — not a toy example, the actual thing. If the metadata-driven pipeline is any good, it should be good enough to run on your own 700 articles, not…

Give the Recipe, Sell the Kitchen
The what/why is free; the how/method is the paid engagement.

The brand-architecture line: give the recipe (the what and why) free on the hub, and route the how and method to paid engagements.

Play Personally → Prove the Block → Apply in Business
The flow from personal experiment to business application.

The bridge from B2C to B2B: experiment personally, prove the building block works, then apply it in business with credibility earned.

Play with the Blocks
Like Lego — snap, try, rebuild. Tinker in your own life to learn what's possible.

Data and AI are like Lego: snap, try, rebuild. The fastest way to learn what's possible is to tinker in your own life first.

Practice What You Evangelize
Build your own knowledge, training and consultancy engine on structure, data and AI — so the foundation itself is the proof of the method you teach.

If you tell clients that structure beats magic — that value comes from the metadata, the rules, the deliberate model you give AI, not from the tool's cleverness — then your own operation has to be built that way, or the message is hollow.…

Proof, Not Slides
Ground every claim in real numbers and real systems; never fabricate.

Always ground claims in real numbers — photos, books, a decade of trips made queryable — and real systems. Never fabricate metrics or testimonials.

Rent the AI; Own the Structure
Models are swappable commodities; your structure is the durable asset.

Models come and go and are rented from vendors; the structure you build is the durable asset you own — so invest there. And this isn't only about the AI model: your model outlives the tool. The data model, the conceptual diagram, the…

Show the Machinery
Don't describe the result — open the hood and show the working system that produced it.

The SBM demonstration stance: instead of talking about outcomes, show the actual machinery — the folders, the rules, the skills, the frontmatter, the query that ran. Credibility comes from letting people look inside a system that visibly…

Structure Made Visible
Making abstract structure and relationships literally seeable — diagrams, infographics, models — so a business audience understands complex ideas at a glance. One of Jaco's core capabilities.

Most structure is invisible. A data model, a set of relationships, a layered architecture, the flow of a governance process — these are real and consequential, but they live as abstractions in a specialist's head, and the business can't…

Systems over Shortcuts
A system you can count on beats a lucky flash of genius — every time.

Magic is the exciting shortcut that gets the credit; structure is the plain system that does the work. Shortcuts pay off once and fail you twice; a system pays off on a Tuesday when inspiration doesn't show. Boring is what still works next…

The Experiment Loop
Play with a hypothesis: hypothesize → experiment → learn → decide. The mechanism that turns tinkering into a proven block.

The missing word between play and proof. Play is the posture — snap, try, rebuild, no stakes. But play alone doesn't prove anything; it just accumulates experiences. An experiment is play with a hypothesis attached: *I think this block…

The Market Caught Up
The creator scene walked, in public, from prompt tips to structure + rules + verification. The thesis didn't move — the market moved to it.

Run a few hundred AI-productivity infographics from independent creators through one filter and a single arc appears: 2022 was prompt tips, 2024 was context, 2026 is harnesses, standing rules and verification loops. The newest wave isn't…

Visual Thinking
The other half of structure — making the model seen, not just real. Structure makes knowledge exist; visual thinking makes it visible enough to trust, question and act on.

Structure Beats Magic is usually about the invisible half — the model beneath your knowledge. But a structure nobody can see does half its job. Visual thinking is the other half, and for a data modeller it was never separate: the core…

Life design

4
Intentions over Goals
Intentions give direction and stay flexible; goals fix rigid endpoints with pass/fail pressure. Structure the direction, not the deadline.

A goal is a fixed endpoint you either hit or miss — it carries a pass/fail charge and the performance pressure that comes with it. An intention names a direction and how you want to travel it, and stays open to revision as you learn. The…

Life Design
Treat your life like a design problem: prototype, test, iterate — instead of planning it once and hoping.

Most life planning assumes you can think your way to the right answer, commit, and execute. Life Design borrows from design practice instead: you don't know the answer up front, so you prototype it. You run small, cheap experiments, gather…

Life Domains
The handful of distinct areas a life runs on — health, work, relationships, finances — each modeled and reviewed on its own.

A life isn't one undifferentiated blob; it runs on a small set of distinct domains — health, work, relationships, finances, home, learning, and so on — each with its own state, its own rhythm, and its own kind of evidence. Naming them…

Reinforcing Loop
A feedback loop where each turn amplifies the next — the engine behind both compounding growth and destructive spirals.

A reinforcing loop is the systems-thinking primitive underneath a lot of life's non-linear behaviour: an output feeds back as input in the *same* direction, so each turn amplifies the next. It's morally neutral — the identical machinery…

Signature principle

1

The named layers of the system — each a place with a boundary, where something crosses, is transformed, or is concluded. A layer is a role in the architecture, not a physical location (that's a zone) and not a technique applied across it (that's a method).

A living vocabulary — it grows as the thesis does. For field terms and distinctions that aren't coined concepts, see the glossary. The enterprise counterpart (Model-Driven Data Engineering) keeps its own concept library at jacovanderlaan.com/concepts.