Essay · 14 min read

What your search results are actually telling you.

The search bar is a mirror — and it doesn't lie. What your wiki's wall of undifferentiated results is actually showing you about the system underneath.

Matt Rathbun  ·  March 2026

You're looking for the deployment procedure. You know it exists because you wrote part of it six months ago. You type "production deployment runbook" into the search bar of whatever tool your company uses for knowledge, and you get back a hundred and forty results.

asks 5 seconds · gets the right answer 140 RESULTS DEAD END query YOU searches COLLEAGUE knows the answer was here
System path: dead end Bypass path: 5 seconds

A procedure has steps, conditions, prerequisites, failure modes. It's meant to be followed, not just read. At 2 AM during an incident, someone needs step-by-step instructions, not a narrative essay about the deployment philosophy.

A policy carries an authority source — a regulation, a board decision, an executive mandate. It has a scope and an expiration. When someone searches for a policy, the questions are different: what's the rule, who decided it, and is it still in effect?

A decision record links to options considered and evidence weighed. Meeting notes are the odd one out — useful for about a week while the actions are in progress, then they recede into historical context. They're not procedures. They're not policies. They're not meant to persist with the same weight.

These aren't categories I'm imposing. They're properties the knowledge already has. The problem is that every knowledge management tool strips them away and replaces them with a single, universal container: the page.

The mirror

Your knowledge base has no concept of what kind of thing it's holding.

The deployment procedure and the meeting summary are stored the same way, indexed the same way, surfaced the same way. From the system's perspective, they are the same kind of thing.

what you bring WHAT THE SYSTEM STORES procedure announce decision policy draft procedure notes policy — ARCS = COGNITIVE LABOR —

The dots are what the system stores. The persona labels are what you bring. The arcs between them are work — invisible, free, and done so fluently you've stopped noticing you do it.

You know the difference. You carry that knowledge in your head. When you scan that first page of results, you're doing a rapid, unconscious classification that the system never does: that's a procedure, that's meeting notes, that's a draft someone abandoned, that's an announcement that's expired, that's an architecture decision. You're running a sorting algorithm the tool doesn't have. And you're so practiced at it that you've stopped noticing you're doing it.

This is the hidden cost. Not the five minutes of searching — the invisible work of compensating for a system that treats all knowledge as the same shape. You've been doing this so long it feels normal. But it's not free. It scales with the size of the knowledge base, it fails when new people join who don't carry your mental model, and it completely breaks when you remove the human compensator from the loop.

Your sidebar, your folder hierarchy, your carefully maintained collection structure — those are compensations too. You built them to impose a shape on knowledge that the system refuses to model.

The search bar strips away all of those compensations and shows you the raw state: flat, undifferentiated, shapeless. The search engine is a mirror — and it doesn't lie.

The properties already exist

Knowledge has shapes. Your tools don't model any of them.

Different kinds of knowledge have fundamentally different structures. A procedure is a procedure regardless of what container you put it in.

Procedure

Sequence of conditional actions. Steps, prerequisites, failure modes. Meant to be followed.

Policy

AUTHORITY SCOPE

Anchored claim under an authority. Rule, scope, effective date. Meant to be referenced.

Decision

One choice among alternatives. Options considered, evidence weighed, path taken.

Notes

Record of a moment. Useful for a week. Then context only someone asking "why?" will want.

Scratch

Work in progress. No commitment. Quality scoring would be counterproductive.

A procedure has steps, conditions, prerequisites, failure modes. It's meant to be followed, not just read. At 2 AM during an incident, someone needs step-by-step instructions, not a narrative essay about the deployment philosophy.

A policy carries an authority source — a regulation, a board decision, an executive mandate. It has a scope and an expiration. When someone searches for a policy, the questions are different: what's the rule, who decided it, and is it still in effect?

A decision record links to options considered and evidence weighed. Meeting notes are the odd one out — useful for about a week while the actions are in progress, then they recede into historical context. They're not procedures. They're not policies. They're not meant to persist with the same weight.

These aren't categories I'm imposing. They're properties the knowledge already has. The problem is that every knowledge management tool strips them away and replaces them with a single, universal container: the page.

How the flattening happens

The tool gives you one container. You pour everything into it.

A procedure isn't prose. A policy isn't a page. But that's what they become, every time, because that's the only thing the tool gives you.

PROCEDURE POLICY DECISION NOTES SCRATCH THE PAGE
5 distinct shapes enter 5 identical pages exit

Think about the last time you wrote a procedure in your wiki. You opened a new page. You got a blank document with a blinking cursor. Maybe a title field at the top. And then you started writing — in prose, because that's what the tool gives you.

But a procedure isn't prose. A procedure is a sequence of conditional actions with defined prerequisites, expected outcomes, and failure modes for each step. Writing it as prose is like writing a recipe as an essay — the information is all there, but the shape is wrong. The container doesn't match the content.

And it's not just the visual shape. The system doesn't know it's holding a procedure, so it can't do anything useful with that knowledge. It can't check whether every step has a defined failure mode. It can't flag that step three references a service that was decommissioned last quarter. It can't present it differently in search results — as a procedure to follow rather than a document to read.

The inherited assumption runs deeper than any one tool. From the earliest wikis to the latest all-in-one workspaces, the fundamental model has been: knowledge is text, text goes in pages, pages go in a hierarchy. Some tools have added databases and tables and boards and timelines — but these are additions bolted onto the same page-first model, not a rethinking of the model itself.

The cost of compensation

It functions the way an office with no filing system functions.

Everyone knows where their own stuff is. New people struggle for months. Finding anything across teams requires asking someone. There are three specific failure modes.

01

The new hire

Every organization has a version of this: the new person who joins, tries to use the wiki, can't tell what's current from what's abandoned, can't tell what's a procedure from what's a brainstorm, and spends their first three months building the mental model that everyone else has internalized. The knowledge base is only useful to the degree that you already know what's in it. For someone new, it's almost worse than nothing — it creates false confidence.

DAY 1
02

The scale wall

Mental models work when you have fifty documents and five people. They work less well when you have five hundred documents and fifty people. They fail completely when you have five thousand documents and five hundred people. At that scale, no individual carries a comprehensive mental model. Everyone has a partial map. And the partial maps don't overlap perfectly — which leads to the thing every large organization eventually discovers: the wiki has become multiple wikis that happen to share a search bar.

A B C SHARED
03

The oral tradition fallback

This is the one that should concern you most, because it's the one already happening. When the knowledge base is flat and the mental models are partial and individual, people stop searching and start asking. "Hey, do you know where the deployment procedure is?" Each of those questions is a small failure — a moment where it would have been faster to find the information in the system, but it wasn't. This is how organizational knowledge reverts to oral tradition: not in a dramatic collapse, but in a slow accumulation of DMs and shoulder taps that gradually replace the system that was supposed to make them unnecessary.

WIKI · dim 47 DMs this week SOCIAL GRAPH · alive
The framing that helps

Three actors, not two.

Users have accounts, permissions, profiles. Agents have API keys, tool access, rate limits. Knowledge has… a title and a body.

Humans

account · identity
permissions · roles
profile · preferences
history · activity
team · org chart
presence · status

Agents

API keys · auth
tool access · scope
rate limits · quotas
capabilities · grants
audit · trail

Knowledge

title
body

— and that's it —

That third one is the one nobody treats as an actor. Knowledge is treated as the passive substrate — the thing that sits in a container and waits to be acted upon.

But knowledge has properties that matter. It has a lifecycle — is it current, historical, in progress, or superseded? It has a persona — is it a procedure, a policy, a decision record, a scratch space? It has quality dimensions that depend on its persona — a procedure needs step-completeness, a policy needs authority sourcing, meeting notes don't need either. It has relationships to other knowledge — this procedure implements that policy, this decision record supersedes that one.

None of this is modeled. The system stores the text and leaves everything else to the humans. Which was adequate when humans were the only ones reading. It is not adequate now.

When an AI agent queries your knowledge base, it sees what the search bar sees: flat, undifferentiated, shapeless. And the agent doesn't know that it doesn't know.

STRUCTURED FLATTEN-PIPE PAGE IDENTICAL reads AGENT SYNTHESIS confident · ungrounded

structured intent  ›  flatten-pipe  ›  identical pages  ›  ungrounded synthesis

It treats every result with the same confidence. It will synthesize an answer from a current procedure and an abandoned draft without blinking, because from its perspective they're both the same kind of thing — text with a title that matched the query.

The flattening that humans have been quietly compensating for becomes a failure mode. Not an occasional failure — a structural one. Every query. Every interaction. Every time the agent reaches into your knowledge base, it's navigating the same flat, shapeless landscape that your human users navigate, except without any of the compensating context that makes the human navigation work.

The agent can't call a colleague and ask "hey, is this doc still current?" The agent just uses what it finds, exactly as the system presents it.

Specification in a flat world

Quality depends on what kind of thing you're measuring.

A procedure that reads beautifully as prose but doesn't specify what to do when step four fails is a bad procedure, regardless of how clear the writing is. A policy missing its regulatory citation is a bad policy, even if the rule itself is correct.

A procedure is well-specified when every step has a defined precondition, action, expected outcome, and failure response. Quality looks completely different for a policy — authority source, scope, effective date, exception process. And a scratch space doesn't need specification at all. Applying formal quality standards to working knowledge in progress would be counterproductive.

But when everything is a page, you can't make these distinctions. You can't measure the quality of a procedure as a procedure when the system doesn't know it's a procedure. You can't check whether a policy cites its regulatory source when the system doesn't know it's a policy. You can't exempt a scratch space from quality requirements when the system doesn't know it's a scratch space.

The flattening makes knowledge harder to find AND harder to improve. The two failures compound: you can't find the right document because the system presents all documents the same way, and you can't improve the document you find because the system doesn't know what "good" means for that kind of document.

What if

What would change if the system knew what it was holding?

Start with the procedure — because that's where you started this essay. You're searching at 2 AM during an incident. If the system knew it was holding a procedure, it could present it as steps to follow, not a page to read. It could check whether every step has a defined failure mode. It could flag that the rollback instructions reference a service decommissioned last quarter. The document's lifecycle would be different — reviewed after every incident, not on a quarterly calendar.

That same awareness cascades across every persona. A policy surfaces its authority source and review date in search results without requiring you to open the document. When the regulation changes, the system flags every policy that implements it and every procedure that operationalizes those policies — a chain of dependencies that today only exists in the heads of the people who built them.

A scratch space gets exempted from quality scoring entirely. It wouldn't show up alongside authoritative content in search. It wouldn't confuse new hires or pollute an AI agent's context. And when the working draft graduated to a formal document, the transition itself could trigger the governance and specification requirements appropriate to its new persona.

This isn't a feature request. It's a structural shift. The system would need to model knowledge as a first-class citizen — not just text in a container, but an entity with its own identity, lifecycle, quality dimensions, and relationships. The way your organization already models users and increasingly models agents.

Before

Forty results. Same surface. No structure visible.

After

Same forty — typed. Procedures resolve as procedures. Policies resolve as policies. Scratch stops competing for attention.

procedure policy decision notes scratch

Three actors. Three sets of properties. Three kinds of intelligence the system needs to have.

The humans have always compensated for the system's ignorance about the third actor. But the humans are tired, and the agents can't compensate at all, and the knowledge base keeps growing.

At some point the compensation breaks, and what you're left with is what the search bar has been showing you all along: a flat, undifferentiated collection of text that looks the same because the system treats it the same, even though everyone who works with it knows it isn't.

Where we go from here

This is the problem we're building VanaMD to solve.

If these ideas resonate — if you've looked at your search results and felt the weight of a knowledge base that can't tell you what kind of thing it's holding — we'd love to hear from you.

Let's talk →