Knowledge harvesting did not begin as a product. It began as a problem I could not stop seeing: the people who knew the most could say the least about how they knew it. Expertise becomes automatic, and automatic knowledge stops being sayable. It walks out the door at retirement, and the five-year onboarding clock starts over.
The work begins in a master's thesis at Auburn, EOR: Establish, Organize, Represent, directed by Charles A. Snyder, written under the influence of Doug Engelbart's unfinished work on augmenting human intellect. Its dialogue subsystem, Tutor, was a structured-questioning engine: the direct ancestor of everything that followed.
The thesis became shipping software. LearnerFirst pioneered "learning-while-doing" applications and delivered them to over 4,000 organizations: Benchmarking, Process Management, Implementing ISO 9000, Work Profiling, and more. The first operational proof that structured questions could carry expert knowledge to people who needed it.
From the mid-90s on, the method ran as Knowledge Harvesting®: thousands of elicitation sessions with top performers across industries: troubleshooting nuclear reactors, designing chemical plants, coordinating pandemic operations, writing patent claims, steering drill strings, capturing what a nurse's diagnostic instinct actually does. Clients ranged from Intel, Chevron, and Dow to Abbott, GE, and the Florida Department of Education. The paper trail, three decades of publications and conference work, 1997 to 2019, is older than most of the field it belongs to.
Human-to-human elicitation worked. It always worked. But it was labor-bound: one practitioner, one expert, one room. The method's ceiling was my calendar. What was missing was an instrumented way to run the questioning, something that could interview, structure, inspect, and redeploy expertise without the practitioner present for every hour of it.
That is what the instruments are. 8 makes the eight kinds of knowledge visible in any conversation and runs the work loop, live and shipped today. 96 is the same engine at professional resolution, in active build. The capture surface became repeatable. The method that took thirty-seven years to develop now runs without me in the room, which is the definition of scale.