Zenk ConsultingAI studio

Every problem needs a different thing built.

Geocoding infrastructure that answers in eight milliseconds. A memory app for parents. A platform for athletes. An equity calculator. A painter’s storefront. Five live products with nothing in common, which is the point.

Geocoding engine
8ms at P99

Address to coordinate, faster than anyone will do it.

Air-gapped inference
On-prem, Docker

Healthcare, defense, finance. Nothing leaves the network.

Voice to narrative
20s in, story out

Capture, transcription, and editing that keeps the voice.

Sensor reconciliation
Many devices, one record

Sources that disagree, resolved into something usable.

Five live, three detailed below
The evidence

Three products. Three industries that share nothing.

One is judged in milliseconds. One is judged by whether it made someone cry. One has to make a pile of disagreeing devices tell a single story. All three are live. Go use them.

01Infrastructure
zappymappy.com

Addresses in, coordinates out, in eight milliseconds.

Zappy Mappy is a geocoding API built for people whose delivery stops moving when the lookup is slow. Drop-off IQ layers delivery intelligence on top: driver instructions, fraud signals, fewer failed deliveries. For healthcare, defense, and finance, the Sovereign Geocoder runs entirely inside your own network, in a container, touching nothing outside it.

Latency
8ms P99
Versus Google
31× faster
Uptime
99.95%
Deployment
Cloud or air-gapped
Don't send us your data. We send you the API.
Address → coordinates · P99
Zappy Mappy8ms
Google248ms
31×faster, measured
at the 99th percentile
Drop-off IQ · liveTry it

A real model turns that sentence into the fields a dispatch system can actually route on.

Twenty seconds of talking, kept forever.

Your kid says something you’d give anything to keep, and you have about twenty seconds before it’s gone. Tucklet takes just your voice, no typing and no homework, and turns it into a written story worth rereading, with the original recording tucked underneath. A different discipline entirely from the work above: here the constraint is emotional, not technical.

Input
Voice only
Effort
~20 seconds
Kept
Text plus original audio
Sharing
Co-parent accounts
Tiny stories tucked away for someday.
Voice note0:19

She said the moon was following us home. I told her it does that for everyone. She said no it only follows people it likes.

No typing. Press play and a speech model reads it back.

Every device disagrees about the same night.

An athlete wears several devices and logs into more apps, and none of them tell the same story. Calibrated Athlete pulls training, nutrition, sleep, and recovery into a single record, then lets Cali, the AI coach, say something useful about it. Coaches see the whole squad at once; athletes see themselves against the bar.

Inputs
Wearables and apps
Domains
Training, sleep, fuel, recovery
For
Athletes and coaching staff
Layer
Reconciliation before insight
The model was the easy part. Agreeing on last night was not.
Last night’s sleep · 4 sources
  • Whoop7h 12m
  • Oura6h 48m
  • Apple Watch7h 31m
  • Manual log8h 00m
Cali7h 04m

Reconciled against your own history, then weighted by which device actually stayed on your wrist.

Who’s building

I build for work. I build for fun. Mostly I just build.

By day, last-mile delivery logistics at Nash, at a scale where a few seconds of latency is real money. By night the same problems follow me home — Zappy Mappy exists because delivery geocoding was never quite fast enough, and building one that was seemed easier than continuing to complain about it. The rest started the same way: something was annoying, or someone needed a thing.

At work

Principal Engineer. Last-mile delivery logistics — routing, dispatch, and fleet coordination for companies like Walmart, 7-Eleven, and Loblaws.

In my free time
Five things, live

Built on nights and weekends, all of them running on the internet right now rather than sitting in a repo.

Before that
PhD, Johns Hopkins

Chemical and biomolecular engineering. Mostly it taught me how far a good simulation will take you.

Also on the internet

Technically all of these are passion projects.

Some just got bigger than others. These two are smaller in scope than the three above and came from exactly the same impulse.

What's My Equity Worth
whatsmyequityworth.com

A startup equity calculator that models vesting, strike price, dilution across funding rounds, and what exercising would actually cost you. Open source, because the maths shouldn't be a secret.

Open source
David Steefel
davidsteefel.com

A storefront for a Colorado landscape painter. Twenty-odd originals, eight collections organised by the places they were painted, sold-state tracking, shipping. No AI anywhere in it, because it didn't need any.

Commissioned
What the work has needed

Most useful problems don’t respect categories.

So this list doesn’t either. It isn’t a service menu — it’s what these products, in unrelated industries, actually turned out to require.

Real-time infrastructure

Inference and lookup services held inside a 10ms budget, under load, at P99 rather than on average.

Regulated environments

Air-gapped, on-premises deployment where data cannot leave the building. Containerised, no vendor round-trip.

Consumer product

Interfaces people use while distracted, one-handed, in twenty seconds, and come back to for years.

Speech and language

Capture, transcription, and model-side editing that tightens writing without flattening whoever wrote it.

Messy data

Normalising sources that disagree with each other into one record the rest of a product can be built on.

Analytics surfaces

Dashboards for people who manage groups, and the different view for the individual inside that group.

Trust and safety signals

Fraud and anomaly detection where being wrong is expensive in both directions.

Deciding what not to build

Most of a good AI product is the part that is not the model. Drawing that line is most of the work.

Try the claimAnswered live by a model

What are you trying to build?

Start of a conversation

If you have something that needs building.

Say what the problem actually is and you’ll get a straight answer: whether this is a good fit, roughly what it would take, and what to do first.