REO Town, Lansing · Automation is in the neighborhood’s DNA
Forward-deployed AI engineer. I sit with the people doing the work, break down what they actually need, and orchestrate teams of AI agents to ship it to production.
AI Solutions Architect at KW Corporation · Founder, CuREOsity Labs · REO Town, Lansing
A little applied intelligence
Give the foundry one messy workflow. See how a small piece of software could connect the work, the information, and the people who need it.
A practical concept. A human checkpoint.
A first step you could actually take.
The real work
Production applications, integration architecture, and operational software built to survive contact with the real world.
ServiceNow Store-certified
A production integration that moves asset data from QuickBase into a customer CMDB—replacing slow, error-prone handoffs with a controlled sync.
Inspection intelligence
A low-code ServiceNow application for building surveys, curating field evidence, and generating professional reports around each survey’s structure.
APIs, middleware & operational glue
Multidirectional systems connecting QuickBooks, QuickBase, AutoTask, GeoTab, ServiceNow, and the work between them—from scheduling and field activity through approvals, payroll, inventory, fleet, and billing.
Private community-technology prototype
A local-first exploration of neighborhood sensing and equal-voice tenant communication. Mentioned here as an active experiment; its working project remains private.
A gallery of AI-generated curiosities
This is where the agents get to play. I hand a frontier model an idea and a little room on Streamlit, GitHub Pages, Hugging Face, or a single HTML file, and see what it can build with the capability it has that month.
The toys aren’t the point. Each one is a cheap, low-stakes probe: can this model carry a simulation, a multi-agent conversation, a data pipeline, a 3D interface? What it manages here tells me what I can trust it with in a warehouse, a field team, or a small business’s books. Some ideas get built twice by different models, so you can compare them side by side.
The code is entirely AI-generated; I bring the ideas, guidance, and testing. I’m the crash test dummy—trying things, finding the rough edges, and asking what becomes possible next. Read the experiment’s field note →
A living atlas of AI-assisted science
Is discovery accelerating? A sourced, interactive record of AI-assisted breakthroughs across biology, mathematics, materials, climate, and physics—each with what the AI did and where the evidence stops.
A spring woodland underfoot
Ten days of Michigan morel season. Read the weather, explore the woods, inspect your finds, and catch the flush. More seasons and species are planned.
Office Simulator · a workplace diorama
Three people. One very small office. Shape the personalities, drop in a situation, and watch the relationships unfold—or take a seat in the conversation yourself.
A better measuring stick
Re-price stocks, funds, indexes, and crypto in gold—or eggs, gasoline, houses, and Big Macs—to see what an investment is really doing.
The quiet wild
Wind a seven-day survival world, set its pressures, and watch one autonomous life turn conditions into choices and consequences.
Multi-agent aquarium
Feed a thought to a school of model-powered fish—each with a different brainstorming job—then pin the ideas worth keeping.
A garden of arguments
Two fictional orators debate across a floating Athenian garden. Shape their perspectives, moderate the exchange, and leave room to change your mind.
Civilization under glass
A living terrarium where autonomous people form families, villages, roads, dynasties, memories, and myths from the rules you set.
One idea, two models
The Magic 8 Ball, rebuilt for the age of AI—twice. ChatGPT’s oracle has eight personalities inside a rotating 2D canvas globe. Claude Opus 5.5’s reads the shape of your question, shows its reasoning, and never rerolls an answer.
One puzzle, three generations
The earlier Three.js cube, GPT-5.6 Sol’s state engine, and Claude Opus 5.5’s cube, whose layers really turn and whose solver works from any position, layer by layer. A before-and-after of what the models could hold in their heads.
A river kingdom
Three orders per season. Move troops, forecast battles, balance the economy, and keep a persistent campaign alive for 48 seasons.
A small life, two ways
The original gentle terrarium, and Claude Opus 5.5’s new take: hatch a one-of-a-kind creature, raise it in a room on your real clock and weather, and watch your care decide what it grows into.
Three small brains you can poke
Rewire a two-wire Braitenberg cart from fear to love, drop food for a worm run by 21 real C. elegans neurons, and watch a from-scratch Python network learn to separate the dots while it runs in your browser.
The connective tissue
I move between the conference room, the API, the field, and the interface. That range helps me see where information breaks down—and build the layer that makes the whole system behave.
ServiceNow, QuickBase, QuickBooks, Python services, JavaScript interfaces, and the APIs between them.
A background in trades, archaeology, forestry, compliance laboratories, and logistics keeps the software grounded in real work.
AI is not decoration. I use it to accelerate learning, extend human judgment, and make ambitious systems practical.
I start on site, not in the IDE.
Field note 001 · Dimension TH-137
I live in REO Town, Lansing—a place shaped by Ransom E. Olds, early automotive production, and generation after generation of people making machines work. Whether or not automation was born here, it evolved here. It is in the neighborhood’s DNA.
Today that inheritance has mutated into something stranger: brick factories and power infrastructure, hand-printed newsletters and zines, resale shops, artists, makers, neighbors, and stubbornly analog culture. Industrial history’s eccentric second cousin—broadcasting from Dimension TH-137.
Before enterprise software, I worked across archaeology, forestry, construction, surveying, logistics, and laboratory operations. I learned to read systems in the ground, in organizations, and in the gaps between tools.
Now I build at those gaps. Some results are certified applications moving real operational data. Others are tiny worlds, decision engines, or private community prototypes. All of them ask: what becomes possible when the pieces can finally speak to one another?
In October 2026 I founded CuREOsity Labs, a technology workshop in REO Town that brings this kind of enterprise-grade software to small businesses at a price they can afford.