NORMAL

docskillzintegrations.com

The layerno modeloccupies.

From arcade floors and field repair to enterprise infrastructure and software testing. From ESL classrooms in Taiwan and SPED teaching here to graduate research in educational psychology. Twenty years in the rooms where technology fails the people it was built for. One thesis: the human sits in the middle, on purpose.

Working with AI is not one skill. It's two.

Most tools fail the same way: they ask people to leave what they already know and go learn something new. The cognitive load alone buries the return on investment before the first deployment lands. The RR‑TT Protocol was built on the opposite instinct — meet people in the register they already speak, deliver the record just in time, and let the system carry the overhead.

The working research extends this into a formal model. Register-matched AI interaction reduces verification friction and increases output trust — not because the model improved, but because the human stopped fighting the interface. That gap between what a model can produce and what an operator can actually use is not a model problem. It is a handoff problem. That is the problem this company solves.

Thompson, J.M. (in preparation). Register-matched interaction and verification discipline in AI-augmented field operations. Graduate research. — USPTO Provisional #64/101,544, filed June 2026.

Foundational work

Halliday, M.A.K. & Hasan, R. (1989). Language, context, and text. Oxford University Press.

Klein, G. (1999). Sources of power: How people make decisions. MIT Press.

Sweller, J. (1988). Cognitive load during problem solving. Cognitive Science, 12(2), 257–285.

01

Register Fluency

Talking to a system the way a fluent person code-switches: persona, shorthand, culturally-loaded cues that carry meaning faster than flat, literal instructions. High-bandwidth, because the listener already has the library installed.

Research basis

Bernstein (1971) distinguished restricted codes — compressed, context-dependent — from elaborated ones. Expert operators already hold the background theory; elaboration is redundant overhead. Sweller's cognitive load framework confirms it: when extraneous load drops, working memory routes to the actual problem. Register fluency is the mechanism that makes that happen.

02

Verification Discipline

The practiced habit of never taking confident output at face value. Not skepticism as a mood — verification as an action, checked against ground truth a human already holds. Teachable, separately. Most people are handed neither.

Research basis

Flavell (1979) identified metacognitive monitoring as a distinct, teachable cognitive skill — separate from domain knowledge. Calibration research consistently shows confident output and accurate output are independent variables. Verification discipline is the trained habit of checking AI-generated claims against ground truth the operator already holds before that output enters any downstream decision.

1997

Spartan Software, Inc.

CEO. Compression + cryptography architecture. Networld‑InterOp, Atlanta. The receipts go back.

2000s

Microsoft STE

Software Test Engineer on the internal dogfood team for hosted Exchange. Kept deployments moving. Saw how it works when it works.

2010s

Taiwan + Ed Psych

Ten years instructional design and teacher training. Graduate work in educational psychology: neuroplasticity, cognitive load, JIT learning.

2026

USPTO #64/101,544

Provisional patent filed June 29. RR‑TT Protocol. Just‑in‑Time Service Intelligence. The method is documented.

THE PROOF

Both skills. One file. Built in 2017.

State-Deterministic Engine

A .pptm built in one week: April 19–27, 2017. Not a mockup — a working state machine: 69 slides, VBA macros wired to shape triggers, explicit hyperlink transitions, synchronized audio, A/V confirmation on every selection event. A proof of concept for what a controller-native WoW interface could look like on Xbox — built during Legion, using real characters. Cold boots, warm boots, character selection, random select, loading sequences, state confirmation before client handoff. Every decision in that loop is in the slide notes.

It was built in PowerPoint because PowerPoint was already in the room. No install. No onboarding. No context switch.

That is a design decision — not a compromise. The tool meets the operator in the environment they already occupy.

The same action taken twice produces the same result. That is idempotency. The transition produces a confirmation signal before the next action is available. That is verification. The RFC and the patent put names to it. The .pptm was already running the discipline.

Register Fluency PowerPoint was already in the room. The interface followed.
Verification Discipline A/V confirmation on every selection event. Idempotency enforced at the character select layer. The demo runs it.
Provenance 69 slides. 15 revisions. 131 minutes of edit time. This was not a sketch. The timestamps are in the file.

The 2017 artifact is a "tools do not define the engineer" demonstration. Using a constrained, awkward medium, I built an operationally complete state-machine interface: explicit states, guarded transitions, rollback, randomized routing, synchronized feedback, and embedded documentation. This artifact showed applied execution with the tools at hand.

See also — Wildenhain (2017) · PowerPoint™ as a Turing-complete environment

Forensic Receipt · docProps/core.xml

dcterms:created2017-04-18 · 17:34:02Z
dcterms:modified2017-04-25 · ~7 days after start
(last edit · re-saved 2025 for preservation)
cp:revision15
app:Slides69
app:TotalTime02:11:00
dc:creatorJoshua Thompson
app:ApplicationMicrosoft Office PowerPoint
FormatOpenXML · .pptx

To verify: rename .pptx.zip · extract · open docProps/core.xml

Selected notes · verbatim

Slide 1Opening slide to emulate a power on sound and a "cold" start.
Slide 8Character select (F1_Transition). Cursor positioned over random select. This slide transitions from "start screen" during a "cold boot" or hard reset. Clicking Random Select will run VBA code to randomly select a character.
Slide 9Soft reset to character select F1. During a warm boot, mousing over the random select will return to this slide (no transition). Clicking Random Select will run VBA code to randomly select a character.
Slide 20VBA spec: stop CharSel music · start LOADING music · hook to game client · send double-click to appropriate character · transfer focus to WoW window when "enter world" event is triggered · remain in presentation mode on logout · on logout return to slide 8.
Slide 40Biometric feedback shown for green button mouseover event. On click, slide moves to the appropriate character select/challenge frame.
Slide 50Biometric feedback shown for red button mouseover event. On click, slide moves back to pre-selected condition (not greyed out).
01

Register Fluency

PowerPoint was already in the room. Building the interface there — not reaching for a framework, not opening an IDE — is Register Fluency in action. The tool spoke the register. The interface followed. That is what it means to meet a system in the language it already knows.

In the file

VBA event handlers wired to shape triggers. Randomization engine seeded at runtime. Full interaction loop — input, processing, output, confirmation — inside a .pptx. Zero external dependencies.

02

Verification Discipline

The A/V confirmation — sound on selection, flash on state change — is verification made sensory. Idempotency was enforced at the character select layer specifically: push it twice, the state holds. The demo does not describe the discipline. It runs it.

In the file

Idempotency guards enforced in macro logic. Dual-modality confirmation: visual flash + audio trigger on every selection event. Designed for crowded rooms. Built 2017. Metatags intact.

speedstack.app

Speedstack

The group chat your team is already in becomes the operations system. One message lands, the ticket is written, the audit trail is live. The work never stops because the tool never got in the way.

The current interface is the CLI — text commands in the rooms your crews already use. Three platforms live: GroupMe, Slack, LINE. Discord ships this weekend. The GUI is in development as Deep Links: invisible UI, zero install, zero workflow change. Command grammar, FSM state machine, typo tolerance, and KB layer are production-tested across HVAC, mechanical, and facilities verticals. Ticket lifecycle, audit trail, and duration logging are confirmed in the logs. Backend tooling is active in the repo now.

Live — nightly deployment feed ↗
speedstack.app →

Ticketing · Audit · CLI GUI Meta Int

Speedstack HVAC / GroupMe

Ticketing · Audit · CLI GUI Meta Int

Speedstack Mech / Slack

Ticketing · Audit · CLI GUI Meta Int

Speedstack ATTR / LINE

Platform Status · July 2026

ArcadePro / Discord

GroupMeLive · HVAC + Mech + ATTR
SlackLive · Mechanical
LINELive · Facilities
DiscordPorting · weekend of July 12

Feature Roadmap · Live GUI Meta Int

Speedstack / All Platforms

CLILive · GroupMe · Slack · LINE · Discord
GUIDeep Links — invisible install, zero workflow change
Meta IntPost-GUI · autonomous dispatch layer
"The question is already inside the learner. The teacher who built the thing is the only one who knows which question surfaces it."

Joshua M. Thompson. Twenty years across enterprise infrastructure, classroom design, field operations, and AI systems. Different countries, different eras, different registers — always the same gap: what a system produces, and what an operator can actually use. The dissertation names it. The patent formalizes it. The bots running right now in production are the demonstration. Long enough on both sides of that gap to know the difference.

MS Software Test Engineer
Hosted Exchange / Outlook Mobile
USPTO Provisional Patent Holder
10 Years Instructional Design
AI Fluent
Ed. Psych Graduate Candidate
Windows file properties — PPTT 2017 creation date