Category: AI Strategy

The extraction protocol works. The pivot signal lexicon is learnable. The four-layer descent can be taught. The question is whether it can be deployed without a trained human interviewer in the room — and if so, how much of the value survives the translation.

This is the duplication problem at the center of the Human Distillery business model. Will can run an extraction session. An app cannot run the same session. But an app can run a version of the session — and for a large subset of extraction use cases, the version is sufficient.

Understanding what transfers and what doesn’t is the whole architectural question.

What Transfers to an App

The four-layer question structure is codifiable. A stateful conversational agent — not a chatbot, a system that maintains a running knowledge map of what’s been surfaced and what’s still needed — can execute the question sequences in order, navigate the domain-specific question libraries for a given vertical, and detect the linguistic markers of pivot signals in real time.

“It’s hard to explain” is detectable by NLP. Hedging patterns are detectable. Energy shifts in voice are detectable by acoustic analysis. Deflection to process — “the policy says…” — is detectable. The app can recognize these signals and adjust its question path, slowing down at tacit knowledge boundaries and applying the correct follow-up from the signal response library.

The processing pipeline from transcript to structured concentrate is fully automatable: chunking by topic boundary, entity extraction, claim isolation, confidence scoring, contradiction flagging across multiple sessions, multi-model distillation rounds. This is where AI earns its keep. A human doing this manually would take days per session. The pipeline does it in minutes.

Domain-specific question libraries can be built from prior extractions and expanded with each new session. The more sessions the app runs in a given vertical, the richer its question library becomes. This is the compounding effect that makes the app more valuable over time.

What Doesn’t Transfer

Three things resist automation in ways that won’t be resolved by better models:

Micro-hesitation reading. The half-second pause before an answer that signals the subject knows more than they’re about to say. The slight change in phrasing when someone moves from what they’re comfortable saying to what they actually think. These are real-time, embodied, relational signals. A text-based app misses them entirely. A voice app gets closer but still lacks the visual channel that carries a significant portion of this information.

Protocol abandonment. The decision to stop following the four-layer sequence because the subject just said something unprompted that is more important than anything in the protocol. Expert interviewers make this call constantly. They recognize the thread that, if followed, goes somewhere the protocol would never reach. An app will follow the signal response library. It won’t recognize when the library should be put down.

Trust calibration. Whether the subject is performing for the recording or actually sharing. This is not detectable from content analysis. It requires the social intelligence to know when to lower the formality, when to match the subject’s energy, when to say something self-deprecating to signal that this is a peer conversation and not an evaluation. Subjects share differently with someone they trust. The app cannot build that trust.

The Honest Architecture

The tiered model that emerges from this analysis:

Tier 1 — App-led extraction. Well-mapped domains with accessible knowledge. The subject is cooperative. The question library is deep. The knowledge being sought is in Layers 1 and 2. The app handles the session. Will reviews the concentrate before delivery.

Tier 2 — Human-led extraction with app processing. High-stakes sessions. Guarded subjects. Knowledge at the outer edge of verbalization (Layer 3 and 4). Will conducts the session. The app runs the processing pipeline. Will reviews and approves the concentrate.

Tier 3 — Full human extraction and distillation. Strategic engagements. Subjects who will only speak candidly to a person they know. Knowledge so embedded that it requires real-time relational judgment to surface at all. Will does everything.

The business model implication: Tier 1 is volume. Tier 3 is premium. The ratio shifts over time as the app’s question libraries deepen and its signal detection improves. What begins as mostly Tier 2 and 3 eventually becomes mostly Tier 1, with Will’s direct involvement reserved for the sessions where only a human can get the door open.

The app is not a replacement for the protocol. It’s a multiplier for the protocol — allowing it to run at a scale that a single human operator never could, while preserving the human layer for the cases that actually require it.

---

A transcript is not a knowledge artifact. Neither is a summary. Both are containers for words. Neither is optimized for the thing that needs to consume them.

When you capture an expert’s knowledge and then feed the transcript to an AI system, the AI gets the words. It does not get the structure. It does not know which claims are firsthand vs. secondhand. It cannot distinguish a confident assertion from a hedged one. It has no way to chain the decision logic — the “when X, do Y because Z” sequences that constitute the operational core of what the expert knows. It just has a long document full of things that may or may not be true, with no metadata to tell it which is which.

This is why most knowledge capture projects fail to deliver on their promise. The content is there. The structure that makes it usable isn’t.

A knowledge concentrate is the alternative. It is the distilled, structured artifact produced by the Human Distillery extraction protocol — smaller than a transcript, denser than any summary, and specifically formatted for the AI systems that will consume it.

The Five Components of a Knowledge Concentrate

1. The Entity Graph

Every named concept, process, role, piece of equipment, regulation, and decision point that surfaces in extraction gets represented as a node. The edges between nodes are typed: causal, conditional, hierarchical, associative. The graph is not a list — it’s a map of relationships, and the relationships are the knowledge.

An AI system with a list of entities knows vocabulary. An AI system with an entity graph knows how the domain works — how a change in one thing propagates to another, which concepts are upstream of which decisions, which relationships are conditional and which are structural.

For a water damage restoration operation: the graph connects moisture readings to drying equipment selection to drying time estimates to invoice amounts to adjuster response patterns. None of those connections are in the documentation. All of them are in the head of a senior project manager who has run 400 jobs.

2. Decision Logic

The most directly usable component of the concentrate. Every when-then-because statement extracted from the session, structured as:

• Condition: When this situation is present
• Action: This is what we do
• Because: This is why (the reasoning, not just the rule)
• Exceptions: The cases where this breaks down
• Confidence score: 0.0–1.0, based on how many independent sources confirmed it

The “because” is what makes this different from a policy. A policy says do Y. A knowledge concentrate says do Y because Z, which means an AI system can recognize when Z is absent and adjust accordingly — rather than applying the rule in cases where the underlying condition that made the rule sensible doesn’t apply.

The exceptions are equally important. Expert judgment is largely the accumulation of exceptions — the cases where the standard answer is wrong. Capturing those is the whole point of Layer 2 extraction.

3. Benchmarks

Every number that surfaces in extraction: thresholds, timelines, costs, rates, ratios, counts. Stored with context, source count, and variance.

A benchmark from a single extraction session has low confidence. The same benchmark confirmed by six independent subjects in the same domain and market has high confidence and is ready to be used as ground truth in an AI system’s reasoning. The concentrate tracks the difference.

This is the component that makes the concentrate valuable as a competitive intelligence product. The numbers in an industry that everyone knows but nobody has published — the real margin thresholds, the actual response time expectations, the price per square foot that experienced operators actually charge vs. what appears in public pricing guides — these exist only in people’s heads. The concentrate captures them with provenance.

4. Tacit Signatures

The things that are hard to explain. Captured as best as they can be verbalized, with a confidence flag.

A tacit signature sounds like: “The drywall feels wrong before the moisture meter confirms it.” Or: “You can tell within the first five minutes of a call whether the adjuster is going to be cooperative or difficult, and it’s not anything specific they say.” These are not mysticism. They are pattern recognition operating below the level of conscious articulation — real knowledge that has never been verbalized because no one asked slowly enough.

The confidence flag on tacit signatures signals to the consuming AI: this is approximate. This is the residue of knowledge the extraction process got close to but couldn’t fully surface. Don’t treat it as ground truth. Treat it as a signal that this is where human judgment is concentrated, and flag it for human review when it’s relevant.

5. Provenance

Traceable but anonymized. For every claim in the concentrate: how many independent sources confirmed it, what their roles were, what domain and market the data came from, and whether the claim is individual knowledge or cross-validated pattern.

Provenance is what makes the concentrate auditable. An AI system that gives an answer based on a knowledge concentrate should be able to say: this answer comes from claim X, which was confirmed by three independent subjects with 10+ years of experience in this domain. That’s a very different epistemic standing than “I was trained on this.”

The Density Test

A useful heuristic for evaluating whether you have a transcript, a summary, or a true knowledge concentrate:

A transcript contains everything that was said. It’s large, raw, and unstructured. An AI can search it but cannot reason from it efficiently.

A summary contains the main points. It’s smaller. It has lost specificity, exceptions, confidence information, and relationships. It’s optimized for human reading, not AI consumption.

A knowledge concentrate is smaller than the summary in tokens but larger in information. It contains relationships the summary dropped. It contains confidence scores the summary didn’t capture. It contains decision logic the summary flattened into assertions. An AI system can reason from it, not just retrieve from it.

If what you have could be produced by someone reading a transcript and taking notes, it’s a summary. A knowledge concentrate requires the extraction protocol — it can only be produced from a session where the tacit layer was deliberately surfaced.

---

Every organization has two kinds of knowledge. The documented kind — processes, policies, SOPs, training materials — lives in manuals and wikis. The other kind lives in people’s heads: the adjustments made without thinking, the thresholds learned from expensive mistakes, the pattern recognition that executes in a second but couldn’t survive a PowerPoint slide.

The first kind is easy to feed into an AI system. The second kind is what makes the organization actually work. And it almost never gets captured before it walks out the door.

This gap — between what’s written and what’s known — is where most enterprise AI implementations quietly fail. The system gets the documentation. It never gets the knowledge. The result is an AI that gives the same answer a new employee would give, while the 15-year veteran shakes their head and does it differently.

The Human Distillery methodology exists to close that gap. It is a structured extraction protocol for converting tacit knowledge into dense, structured artifacts — books for bots — that AI systems can actually use. Not summaries. Not transcripts. Knowledge concentrates: information-rich artifacts that encode relationships, decision logic, and confidence alongside the facts themselves.

This article is the methodology reference. It covers what tacit knowledge is and why it resists standard capture methods, the four-layer extraction protocol that surfaces it, the pivot signal lexicon that tells you when you’re close, what a knowledge concentrate looks like as a structured artifact, and where human judgment remains irreplaceable in the pipeline.

---

Why Standard Methods Don’t Work

The instinct when trying to capture organizational knowledge is to reach for one of three tools: a survey, an interview, or a documentation request. All three fail at tacit knowledge for the same reason: they ask people what they know. Tacit knowledge is knowledge people don’t know they know. It operates below the level of conscious articulation. You cannot survey it out of someone. You cannot ask them to write it down. You have to create the conditions under which it surfaces — and then recognize it when it does.

Forms and surveys capture what people think they do. Conversations capture what they actually do and why. The difference between those two things is the entire product.

A 20-year insurance adjuster asked “what’s your process for evaluating a water damage claim?” will give you the documented version: inspect the loss, review the policy, scope the damage, issue the estimate. This is accurate and useless. Ask them about a claim that went sideways and they will, unprompted, tell you that they always check the crawlspace first on older properties in this zip code because the contractor community there has a pattern of scope creep on foundation moisture that the initial inspection never catches. That’s the knowledge. It lives in the deviation from the process, not the process itself.

---

The Four-Layer Descent

The extraction protocol descends through four distinct layers in sequence. Each layer unlocks the next. Skipping a layer produces thin output. Rushing a layer produces performed output. The full descent, executed correctly, surfaces knowledge the subject didn’t know they were carrying.

Phase 0: Disarmament

Before any extraction begins, the status dynamic has to be neutralized. The subject needs to stop performing expertise for an evaluator and start explaining their world to a curious outsider. The difference in what comes out is dramatic.

The disarmament move: position yourself as someone who genuinely doesn’t know. “I’ve never seen a job like this — walk me through it like I’m shadowing you.” This does two things. It forces explanation of steps the subject considers so obvious they wouldn’t otherwise mention — which is exactly where embedded knowledge concentrates. And it signals that there’s no correct answer being evaluated, which reduces the filtering that kills tacit knowledge capture.

Open with failure. “Tell me about a job that went sideways” surfaces edge cases, exceptions, and judgment calls that success stories never reveal. People tell the truth in their failure stories. They’re not protecting anything.

Layer 1: Surface Protocol

The question: “What’s your process when X happens?”

What it gets: The documented version. What the subject would write in an SOP. What they’d tell a new hire on day one. Accurate. Insufficient. Necessary baseline.

Why you need it: The surface protocol establishes the frame. It’s the map. Everything that comes after is about finding where the territory diverges from the map — and those divergences are where the knowledge lives.

Layer 2: Exception Probing

The question: “When do you deviate from that?”

What it gets: The adaptive layer. The judgment calls that experience produces. The cases where the checklist gets ignored because the situation demands something the checklist can’t accommodate. This is the first layer where genuine tacit knowledge begins to surface.

The follow-up sequence: “And when does that happen?” → “How do you know it’s that situation?” → “What would you have done three years ago that you wouldn’t do now?” Each question peels back one more layer of accumulated judgment.

Layer 3: Sensory and Somatic

The question: “How do you know it’s that and not something else?”

What it gets: Pattern recognition so ingrained it operates below conscious awareness. The knowledge the subject has never verbalized because no one has ever asked them to. This is the hardest layer to surface and the most valuable thing in the concentrate.

What it sounds like: “The smell is different.” “The drywall feels wrong.” “Something about the way the insurance company rep is phrasing the emails.” These are not vague — they’re ultra-specific to a domain. The job is to slow down at these moments and press: “Describe the smell.” “What does wrong feel like compared to right?” “What in the phrasing specifically?” The subject usually thinks they can’t explain it. They can. They just haven’t been asked slowly enough.

Layer 4: Counterfactual Pressure

The question: “What would break if you weren’t here tomorrow?”

What it gets: The knowledge hierarchy. What actually matters versus what’s ritual. Most organizations don’t know which is which until the person who knows leaves. This layer surfaces the load-bearing knowledge — the things that if absent would produce visible failures, not just suboptimal outcomes.

The follow-up: “Who else knows that?” The answer is almost always “no one” or “maybe [one person].” That’s the knowledge risk. That’s also the product.

---

The Pivot Signal Lexicon

Proximity to tacit knowledge produces specific signals in conversation. Recognizing them in real time is the skill that separates a good extraction session from a great one. Miss these signals and you stay in Layer 1. Catch them and you descend.

Signal	What It Means	The Move
“It’s hard to explain…”	The subject is about to verbalize something they have never articulated before. This is the most valuable signal in the lexicon.	Slow everything down. “Try anyway.” Do not fill the silence. Do not offer a simpler question. Wait.
“You just kind of know”	Layer 3 boundary. The subject is pointing directly at tacit knowledge they don’t know how to surface.	“Walk me through the last time you just knew. What did you notice first?”
Hedging and qualifiers	The subject is filtering. They have an answer but aren’t sure it’s acceptable to say. “Generally speaking…” “In most cases…” “It depends…” are all hedges.	“Off the record — what actually happens?” Or: “What’s the version you’d tell a colleague vs. what you’d put in the manual?”
Sudden energy or animation	You’ve touched something they care about. The subject’s pace increases, their posture changes, they lean in. This is a live thread to a knowledge cluster.	Follow it immediately. Drop the protocol. “Tell me more about that.” The protocol can resume. This thread may not come back.
Deflection to process	The subject is avoiding the judgment layer. When asked what they do, they tell you what the process says to do. Often accompanied by “the policy is…” or “we’re supposed to…”	“But what do you do when that breaks down?” The emphasis on ‘you’ reframes the question from institutional to personal, which is where the knowledge actually lives.
Pausing before a number	The subject is calculating from experience, not retrieving from documentation. The pause is the gap between “what the spec says” and “what I know from doing this 200 times.”	Ask for the number, then: “Where does that come from?” The answer to the second question is often the most valuable thing in the session.
Unprompted stories	The subject has moved from answering your questions to accessing their own knowledge map. Stories they tell without being asked are almost always pointing at something important.	Let it run. If the story ends without the embedded knowledge surfacing, ask: “What made that one different from a normal job?”

---

The Knowledge Concentrate: What the Output Actually Looks Like

A transcript is raw. A summary is thinner in size but barely denser in information. A knowledge concentrate is smaller than either and more information-rich than both — because it encodes relationships, decision logic, and confidence alongside the facts themselves.

The schema for a knowledge concentrate has five components:

Entity graph. Every named concept, process, person-role, piece of equipment, and decision point that surfaces in the extraction, mapped as nodes with typed edges between them. Not a list — a graph. The relationships are the knowledge. The entities alone are just vocabulary.

Decision logic. Every when-then-because statement extracted from the session. “When the moisture readings are above X in a crawlspace with Y flooring type, we always do Z because A.” Structured with confidence scores: is this firsthand knowledge, observed pattern, or secondhand information?

Benchmarks. Every number that surfaces in extraction — thresholds, timelines, costs, rates, counts — with context, source count, and variance. A benchmark from one interview has low confidence. The same benchmark confirmed across six interviews in the same market has high confidence and is ready to be used as ground truth.

Tacit signatures. The things that are hard to explain — captured as best as they can be verbalized, with a confidence flag that signals to the AI system consuming them: this is approximate. This is the residue of knowledge that the extraction process got close to but couldn’t fully surface. It’s still valuable. It tells the AI where human judgment is concentrated.

Provenance. Traceable but anonymized. How many sources contributed to each claim. Whether a given piece of knowledge is individual or cross-validated. What industry and market it came from.

An AI system consuming a knowledge concentrate in this format doesn’t just know facts — it knows which facts to trust, how to chain them into decisions, and where the knowledge is thin enough that human judgment should be called in.

---

What the App Can Do and What It Can’t

The four-layer protocol and the pivot signal lexicon can be partially codified. A stateful conversational agent — not a chatbot, a genuinely stateful system that maintains a running knowledge map of what’s been surfaced and what’s still needed — can execute the question sequences, detect linguistic pivot signals, navigate domain-specific question libraries, and run the processing pipeline from transcript to structured concentrate.

What it cannot do is the thing that makes the difference between a good extraction and a complete one:

It cannot read the half-second of hesitation before an answer that signals the subject knows more than they’re about to say. It cannot decide, in the middle of an unprompted story, that this tangent is the most important thing in the session and the protocol should be abandoned to follow it. It cannot calibrate trust — cannot sense whether the subject is performing for the recording or actually sharing, and adjust accordingly. It cannot distinguish a valuable tangent from genuine noise in real time.

These are not gaps that better models will close. They are inherently relational and embodied. They require a human who is genuinely present in the conversation, not processing a transcript of it.

The honest architecture for a distillery operation is therefore tiered. The app handles extraction volume — the sessions where the knowledge is relatively accessible, the domain is well-mapped, and the question library is sufficient. The human handles the sessions where the stakes are highest, the subject is guarded, or the knowledge being sought is at the outer edge of what can be verbalized. And the human is always the quality gate on the final concentrate, regardless of which path produced it.

---

Why This Works in Any Industry

Tacit knowledge is not a property of any particular field. It is a property of human expertise at depth. Wherever humans have been doing something long enough to develop judgment that exceeds documentation — which is everywhere — the distillery protocol applies.

The domain changes the question library. The pivot signals are universal. The four-layer structure works in restoration, in legal practice, in medicine, in financial services, in manufacturing, in competitive sports coaching, in culinary production. Any field where experience produces something that training cannot replicate is a field where a knowledge concentrate has value.

The buyers are the organizations trying to make that knowledge portable. The AI system that needs to give the same answer a 20-year veteran would give. The consultant whose insights live only in their head. The franchise trying to replicate the judgment of its best operators across 400 locations. The company that just lost its most important employee and is only now discovering what they actually knew.

The product is not content. It is not a report. It is a structured knowledge artifact that makes someone else’s irreplaceable expertise replicable — at least partially, at least for the cases the documentation currently handles worst.

That’s the distillery. Extract. Distill. Deploy.

---

Frequently Asked Questions

---

The instinct, when building a complex operation, is to find one tool that can hold everything. One source of truth. One dashboard. One system of record for all data types.

This instinct is wrong, and it produces exactly the kind of system it’s trying to avoid: a single tool that does everything poorly, a migration project that costs more than the original implementation, and a team that has learned to distrust the data because the tool was never designed for the behaviors it was forced to support.

The behavior-first alternative for data architecture doesn’t start with “what tool can hold everything.” It starts with: what are the distinct behaviors this data needs to support, and which tool is genuinely best suited for each one?

The Four Data Behaviors

In a multi-site AI-native content operation, four distinct data behaviors emerge:

Machine-generated operational data needs to be written and read by automated systems at high speed. Batch job results, embedding vectors, image processing logs, Cloud Run execution histories. No human looks at this data directly. It needs to be fast, cheap, and structured for programmatic access. GCP serves this behavior — Firestore for structured operational state, Cloud Storage for large artifacts, BigQuery for analytical queries across the full dataset.

Human-actionable signals need to be displayed clearly enough that a person can take action without wading through noise. Site health alerts, content gaps, client status changes, task assignments. This data needs to be readable, filterable, and connected to the people who need to act on it. Notion serves this behavior — not because it’s the most powerful database, but because it’s the most human-readable one, with views that can surface exactly the signal each role needs.

Published content needs to be delivered to web visitors and search engines at performance standards those audiences require. WordPress serves this behavior. It was designed for it. The mistake is asking WordPress to also serve as the storage layer for unpublished content, the analytics layer for content performance, or the task management layer for content production. It wasn’t designed for those behaviors and it’s not good at them.

Files and documents need to be stored, versioned, and shared across tools and collaborators. Google Drive serves this behavior. Skills, SOPs, brand guidelines, exported data — anything that exists as a file rather than as structured data belongs in Drive, not in a database trying to handle file attachments as a secondary feature.

Why Separation Produces Better Systems

A four-layer architecture feels like more complexity than a single-tool approach. In practice it produces less complexity, because each tool is operating within its design constraints instead of being stretched beyond them.

The signal-to-noise problem in most dashboards comes from forcing machine-generated data and human-actionable signals into the same view. The machine data overwhelms the human signals. The solution is usually “better filtering” — which is the wrong answer. The right answer is storing machine data where machines can read it and surfacing human signals where humans can act on them.

The performance problem in most content operations comes from asking WordPress to be a content management system when it’s a content delivery system. The content that belongs in a CMS — drafts, revisions, briefs, research notes — should be in Notion. The content that belongs in a CDS — published articles, page templates, media files — should be in WordPress. When you separate these, both tools perform their actual function better.

The data loss problem in most operations comes from treating the most convenient tool as the system of record. When content lives only in WordPress, a site failure is a data failure. When operational state lives only in a Cloud Run service, a deployment change is a state failure. The four-layer architecture ensures that each data type has a permanent home in the tool designed to hold it — and that the tools interact through APIs rather than through manual migration.

---

The conventional wisdom about ADHD and work is built around a simple premise: the ADHD brain is deficient in the behaviors that work requires, and management strategies exist to compensate for those deficiencies. More structure. Better schedules. Accountability systems. Tools designed to impose the consistency the brain doesn’t generate naturally.

This is tool-first thinking applied to a human brain. And like most tool-first thinking, it produces systems that fight the behavior instead of serving it.

The behavior-first alternative asks a different question: what does the ADHD brain actually do, at its best, and what system design would allow it to do more of that?

What the ADHD Brain Actually Does

Three behaviors characterize high-functioning ADHD cognition when the environment supports them:

Hyperfocus. Sustained, intense concentration that arrives unbidden and runs at extraordinary depth for an unpredictable duration. Not concentration on demand — concentration that seizes the operator when a problem activates the interest system. The output of a hyperfocus session is disproportionate to the time invested, and the quality often exceeds what deliberate, scheduled work produces.

Interest-based attention routing. The ADHD attention system allocates based on interest, novelty, urgency, or challenge — not importance. High-interest work gets exceptional focus. Low-interest work gets almost none. This is not a failure of will. It’s a feature of a different attentional architecture.

Cross-domain pattern recognition. Rapid context-switching, which looks like distractibility in sequential-task environments, produces something valuable in environments that reward synthesis: the ability to connect observations across unrelated domains and identify patterns that single-domain experts miss.

The System That Serves These Behaviors

An AI-native operation designed around these behaviors looks different from a conventional productivity system:

For hyperfocus: The system captures whatever the hyperfocus session produces — immediately, in full, without requiring the operator to organize it mid-session. The Second Brain stores the output. The cockpit session for the next day picks up the thread. The non-linearity of hyperfocus (jumping between connected insights, building in spirals) becomes productive because the AI can hold the full context of the spiral across sessions.

For interest-based attention: Low-interest, deterministic work routes to automated pipelines. Haiku runs taxonomy fixes at scale. Cloud Run handles scheduled publishing. Batch jobs process a hundred posts while the operator is doing something that has activated their interest system. The attention that would have been coerced onto low-interest work is freed for the high-interest work where ADHD attention genuinely excels.

For pattern recognition: The cross-domain synthesis that ADHD cognition produces naturally — connecting a restoration industry CRM insight to an AI architecture principle to a neurodiversity research finding — is exactly what generates the novel frameworks that constitute a knowledge operation’s core asset. This isn’t compensated for. It’s the product.

The Architecture Principle

The systems that emerged from designing around ADHD constraints are not ADHD-specific. They are better systems. External working memory (the Second Brain) outperforms internal working memory for complex multi-client operations regardless of neurology. Routing low-value-attention work to automation is better for any operator. Pre-staged context reduces friction for everyone.

The ADHD constraints forced designs that a neurotypical operator would also benefit from — because the constraints that neurodivergence makes extreme are present in milder form in everyone. The behavior-first design process, applied to an ADHD brain, produced infrastructure. The same process, applied to any operation, produces the same result: systems that serve the actual behavior, compound over time, and don’t require the operator to fight their own cognition to function.

---

AI systems are good at identifying problems. Automated systems are good at fixing them. The failure mode that kills most AI automation projects is building them as one thing instead of two.

When you couple intelligence and execution in a single system, you get something that can do everything slowly and nothing reliably. The intelligence layer needs to be conversational, contextual, and judgment-driven. The execution layer needs to be deterministic, fast, and parallelizable. These are fundamentally different behaviors, and they require different tools.

The Work Order as the Bridge

The behavior-first design for AI automation has three distinct stages: identify (Claude analyzes a system and surfaces what needs to be done), deposit (Claude writes a structured work order to a persistent queue), and execute (a Cloud Run worker reads the work order and runs the fix).

The work order is the key artifact. It’s the contract between the intelligence layer and the execution layer. A well-formed work order contains everything the execution layer needs to run without asking Claude any follow-up questions: the target (site, post ID, endpoint), the operation (what to do), the parameters (how to do it), and the success criteria (how to know it worked).

When the work order is well-formed, the execution layer is a dumb runner. It doesn’t need to understand context, history, or judgment. It reads the work order, executes the operation, and writes the result back. The intelligence that produced the work order stays in the intelligence layer — which is exactly where it belongs.

What This Looks Like in Practice

In a multi-site content operation, Claude might analyze a WordPress site and identify 47 posts with missing FAQ schema. The tool-first approach runs Claude in a loop, generating and publishing schema for each post sequentially. This is slow, context-dependent, and fragile — if Claude loses context mid-run, the job is incomplete and the state is unclear.

The behavior-first approach: Claude generates 47 structured work orders, one per post, and deposits them in a Notion database with status “Queued.” A Cloud Run service reads the queue and processes each work order independently, in parallel, writing results back to each row. Claude is done in minutes. The Cloud Run service finishes the execution while Claude is doing something else entirely.

The behaviors are clean. The tools serve them. The system scales horizontally without requiring Claude to be in the loop for execution.

The Two Lanes of AI Automation

Not everything belongs in the work order queue. Some operations require judgment that the execution layer can’t replicate: content quality assessment, strategy decisions, anything where “it depends” is the correct first answer. These belong in a different lane — one where Claude stays in the loop through completion.

A mature AI automation architecture has both lanes clearly defined. Deterministic operations (taxonomy fixes, schema injection, meta rewrites, image uploads, internal link additions) go to the work order queue and run without Claude. Judgment-dependent operations (content strategy, quality review, client recommendations) stay in the conversational layer where Claude’s judgment can be applied continuously.

The discipline is in knowing which lane each operation belongs in — and resisting the temptation to put judgment-dependent work in the queue just because it would be faster. Faster execution of the wrong thing is not an improvement.

---

Every organization has two kinds of knowledge. The first kind is documented: processes, policies, training materials, SOPs. The second kind is tacit: the adjustments people make without thinking, the thresholds they’ve learned from experience, the judgment calls they can execute in seconds but couldn’t explain in a meeting.

The documented knowledge is easy to feed into an AI system. The tacit knowledge is what makes the organization actually work — and it’s almost never in a format that AI can use.

The gap between these two knowledge types is where most enterprise AI implementations fail. Companies feed their AI the documentation and wonder why it can’t give the same answers a 10-year veteran would give. The answer is that the 10-year veteran isn’t running on the documentation. They’re running on the tacit layer — and nobody captured it.

What Tacit Knowledge Extraction Actually Requires

You cannot extract tacit knowledge through forms, surveys, or documentation requests. Tacit knowledge by definition is knowledge that the holder cannot fully articulate without a skilled interviewer pulling it out. The behavior that surfaces it is specific: a conversational sequence that descends through four distinct layers.

Layer 1 — Surface protocol: “What’s your process when X happens?” This gets the documented version — what people think they do, what they’d write in an SOP. Necessary baseline but not the target.

Layer 2 — Exception probing: “When do you deviate from that?” This surfaces the adaptive layer — the judgment calls that experience produces. The deviations are where tacit knowledge lives.

Layer 3 — Sensory and somatic: “How do you know it’s that specific problem and not something else?” This is the hardest layer to surface and the most valuable. It captures knowledge that the holder has never verbalized — pattern recognition so ingrained it operates below conscious awareness.

Layer 4 — Counterfactual pressure: “What would break if you weren’t here tomorrow?” This surfaces the knowledge hierarchy — what actually matters versus what’s ritual. Most organizations don’t know which is which until the person with the knowledge leaves.

The Behavior Determines the Tool Stack

Once this extraction behavior is understood, the tool selection for the AI system becomes clear. You need: a way to capture the conversation at high fidelity, a way to convert the transcript into structured knowledge artifacts, a storage layer that preserves the knowledge in a format AI systems can query, and an embedding layer that makes the knowledge semantically searchable.

These are four distinct behaviors served by four distinct tools. The extraction conversation is a human behavior — no tool replaces it. The structuring is where AI earns its keep: running the transcript through multiple models with different attack angles, identifying the tacit signatures embedded in the language, organizing the output into the knowledge concentrate schema. The storage is a database decision. The embedding layer is a vector store.

None of these tool choices could have been made intelligently without first understanding the extraction behavior. The behavior is the constraint that makes the tool selection tractable.

The Minimum Viable Experiment

For any organization that wants to capture its tacit knowledge layer before it walks out the door: four extraction conversations, transcribed and run through a three-model distillation round, produce a knowledge artifact dense enough to answer questions that the documentation cannot. The experiment takes a week and costs almost nothing. The cost of not doing it shows up when the person who holds the knowledge leaves and the organization discovers, for the first time, how much was never written down.

---

If your WordPress site goes down tomorrow, what happens to your content?

For most operations, the answer is: it’s gone until the site comes back, and if it comes back wrong, there’s a recovery process that takes hours and may not be complete. The content lives in WordPress because WordPress is the system — not just the distribution point, but the source of truth.

This is tool-first design. And it’s fragile in ways that only become visible when something breaks.

The behavior-first alternative separates the functions that WordPress conflates. Writing and storing content is one behavior. Publishing and distributing it is another. They require different things from a tool: storage requires permanence, searchability, and accessibility regardless of publishing status; distribution requires web performance, SEO infrastructure, and public availability. WordPress is genuinely excellent at distribution. It was never designed to be a durable content storage layer.

The practical implementation: every piece of content in a behavior-first operation goes to Notion first, WordPress second. The Notion page is the permanent record. The WordPress post is the published output. If the WordPress site goes down, the content is not at risk. If you need to migrate hosts, rebuild the site, or switch platforms, the content travels with you. If the WAF blocks your publisher, you mark the Notion entry “Pending WP Push” and execute when the path is clear — nothing is lost.

What This Looks Like in Practice

The write → store → distribute pipeline has three distinct stages, each with a clear tool responsibility:

Write: Claude generates the article, optimized for SEO/AEO/GEO, with schema markup and internal linking. This happens in conversation, in a batch pipeline, or via a Cloud Run service.

Store: The article lands in Notion — in a content tracker database with properties for status, target keyword, WP post URL, and a claude_delta metadata block at the top of each page. This is the permanent record. It’s searchable, linkable, and accessible to any future Claude session without reconstructing context.

Distribute: The article publishes to WordPress via REST API. The WordPress post ID and URL get written back to the Notion record. The content now exists in two places — one for humans and future AI sessions (Notion), one for search engines and web visitors (WordPress).

The Secondary Benefit: Portable Content

The deeper value of this architecture isn’t failure resilience — it’s portability. Content stored in Notion can be published to any destination: WordPress, a different CMS, an email campaign, a PDF, a social post. The content is decoupled from its distribution channel. When you need to repurpose an article as a lead magnet, extract a section for a social post, or adapt it for a different site, it’s all in one place in a structured format that Claude can read and reformat in seconds.

This is what “content as knowledge” looks like operationally. Not a metaphor — a literal architecture where content is stored as knowledge first and distributed as content second.

The tool that makes this possible (Notion) costs nothing for a solo operator. The behavior that makes it valuable — writing to storage before distribution — costs nothing but the discipline to do it consistently. Build the system around that behavior and the tool choice becomes almost irrelevant.

Frequently Asked Questions

---