AI-enabled knowledge harvesting is now ready for deployment inside your organization.
The old problem was not that experts had no knowledge to give. The problem was that their most valuable knowledge had become automatic. It lived in judgment, timing, sequence, exception handling, and feel. Ordinary interviews could not reliably reach it.
Now there is an instrument for reaching it.
96 turns expert knowledge into structured, inspectable, reusable information. It uses a 37-year elicitation method, rebuilt for AI, to help subject matter experts surface what they know before it disappears.
Before LT created 8 and 96, knowledge harvesting was difficult to scale. Today it is not.
For decades, organizations treated expert knowledge as something fragile, mysterious, expensive, and hard to capture. So they waited. They documented procedures. They ran exit interviews. They asked experts to "write down what they know."
That was never enough.
The expert knowledge that matters most is rarely sitting in a clean paragraph. It appears when the line should be shut down before the metric says so. It appears when the veteran knows who to call, what to ignore, what sequence to follow, and which small anomaly changes the whole situation.
The world should know: this can now be elicited at scale.
When the subject matter expert is ready, the project environment can be prepared quickly. Within the first working session, the expert should feel the difference: not a survey, not an interview, not a blank-page documentation exercise, but a guided process that helps them say what they did not know they knew.
Not because experts are holding back.
Because expertise becomes automatic. The better someone gets, the less they consciously narrate what they are doing. Their judgment compresses. Their language gets shorter. Their decisions become faster than explanation.
96 reverses that compression.
It asks structured questions across the kinds of knowledge an expert actually uses: facts, procedures, timing, people, body sense, awareness, systems, and story. The questions do not merely collect answers. They decompose expertise into information that can be inspected, tagged, transferred, and reused.
Your written procedures are not the whole operation.
The real operation also depends on the person who hears the machine differently. The manager who knows which vendor will actually answer. The field expert who sees a pattern before the dashboard does. The senior operator who knows which rule is safe to bend and which one is not.
That knowledge is not vague. It is not mystical. It is encoded in language, memory, judgment, sequence, and context.
The difficulty is that flat questions do not reach it.
"What do you know?"
"What should we document?"
"What should the next person understand?"
These questions are too broad. They ask the expert to perform the structure themselves. 96 supplies the structure. It asks the right kind of question for the right kind of knowledge, then turns the answer into something the organization can actually use.
The retirement clock is real. The onboarding clock is real. The knowledge loss is real.
So the question is no longer whether knowledge harvesting is possible.
The question is whether you are willing to do it before the knowledge walks out.
Knowledge Harvesting has three chapters.
Three decades of doing this by hand, one expert at a time. A structured-questioning method with a paper trail older than most of the field.
The AI version was built in public, dated, and tested in the open. The work left footprints while it walked.
96 becomes the final instance of the engine: the same elicitation logic, now running through AI so the method can scale without requiring the original practitioner in the room.
A competitor can copy a prompt.
They cannot copy the arc that produced it.
LT’s master’s thesis at Auburn, EOR: Establish, Organize, Represent, was directed by Charles A. Snyder and written under the influence of Doug Engelbart’s unfinished work on augmenting human intellect.
The thesis included Tutor, a structured-questioning subsystem and the direct ancestor of the 96 questions.
LearnerFirst followed in 1992. Then came decades of engagements, field use, revision, and pattern recognition.
The point is simple: 96 did not appear because AI made prompting fashionable. AI made it possible to scale a method that had already been worked out against the human mind.
When frontier models arrived, the engine already fit.
A human expert and an AI model are not the same kind of thing. But both hold usable patterns in language. Structured questions are how you surface what flat prompts miss.
The public trail includes:
For 37 years, the mechanism ran against the human mind.
Now it also runs against a second kind of mind: AI.
That does not mean humans and AI hold knowledge in the same way. They do not.
Pointed at a human, the engine surfaces knowledge that existed and was hidden.
Pointed at a model, the engine surfaces patterns: the residue of human cognition in training, language, and use.
Humans hold knowledge. AI holds patterns. Information is what moves between them.
That distinction matters. We keep it visible.
You experience it as a system prompt.
It feels simple because the complexity has been absorbed into the instrument.
Behind the surface are eight knowledge types, a 96-cell grid, an orchestration logic, and a decomposition pipeline that turns a live answer into structured information.
The product is not "a prompt." The prompt is the delivery surface. The product is the calibrated question set, the sequencing, the grammar, and the judgment about which question belongs where.
You are sold the surface. The architecture is why the surface can be trusted.
We tested the obvious threat.
A competing frontier model was given a generic description of 96 and asked to rebuild it.
It could derive the outer architecture: intake, parsing, classification, matrix, workflow.
Then it was asked for the thing that makes the architecture work: the empirical calibration. Which 96 questions? Why those? In what order? For which kind of knowledge? Under what operating conditions?
That is where the rebuild broke.
The architecture is derivable. The calibration is not.
The text of a prompt can be copied in a keystroke. Thirty-seven years of knowing which question to ask, in which order, for which kind of knowledge, cannot be lifted that way.
That is what you are buying.
A master practitioner’s elicitation used to require the master in the room.
That made knowledge harvesting powerful, but hard to scale. The engagement ended when the practitioner left. The cost stayed high. The knowledge often remained trapped inside the method.
96 changes the economics.
It lowers the marginal cost of structured elicitation while preserving the fidelity of the practitioner’s judgment.
The claim is not "we scale."
Everything scales now.
The claim is that we scaled the thing that usually does not scale: expert-grade elicitation.
Drop the 96 questions and you have another wrapper.
Keep them and the scaled output still carries the judgment of the method.
Behind 96 sits the larger engine.
It has appeared four times: Tutor (1989) → Builder-Player (the patent) → the Knowledge Harvesting steps → the 96 cells.
Same engine. Different surfaces.
The engine makes implicit knowledge explicit through structured questions.
Its honest limit is part of its strength. With humans, it surfaces knowledge. With AI, it surfaces patterns. In both cases, it turns what was hidden or compressed into structured information that can be inspected, improved, and reused.
The mechanism is general. The output is not the same in every case, and we do not pretend otherwise.
Doug Engelbart’s vision was never only the mouse or the window.
Those were the artifacts that got commercialized.
The deeper project was the co-evolution of tools, methods, training, and human capability. He called the goal collective IQ: improving how well people, together, solve harder problems faster.
Knowledge Harvesting is a 37-year contribution to that unfinished agenda.
The 1989 thesis was written under Engelbart’s influence. The connection is not decorative. It is load-bearing.
The work was always about augmenting human intellect.
AI did not replace that agenda.
AI made it urgent.