Scott Morris

Software that keeps
your data yours.

Private AI running on hardware you own. Field apps that work without a signal. Data systems where the guardrails are built into the plumbing, not the policy document.

Scroll

Private by design

Your data never
leaves the building.

The language models run on a GPU in your own rack — not someone else's API. Indexing, retrieval and answers all stay inside your network, and it keeps working when the internet doesn't.

Structural guardrails

Rules the software
can't break.

An assistant on a read-only account physically cannot write. Compensation fields stripped server-side never reach the device that would render them. Guardrails belong in the data layer, where no prompt and no clever user can talk them out of it.

Agentic engineering

A fleet of AI agents
that ships real work.

Eleven specialised agents in production with persistent memory, a shared task board and automated weekly reviews. Not a demo — it runs every day, on local hardware.

Regulated data

Built for records
that matter.

Payroll, medical and personnel data, handled with least-privilege access, data minimisation and tamper-evident audit trails. Designed to HIPAA constraints — practices, not a certificate on a wall.

Mobile

Apps built for
the job site.

Native iOS for crews outdoors, wearing gloves, often with no signal. One binary whose modules the server decides at launch — granting someone a new tool is a permission change, not a release.

Payments

Money handling,
done carefully.

A raffle platform taking card payments for schools. Every purchase path is tested before it goes near a parent's card, because here the failure mode isn't a bug report — it's someone's money.

How it's secured

Privacy as architecture.

Local inference only

Retrieval and generation on owned hardware. No third-party model calls, no documents leaving the network, no API key to leak.

Read-only by default

Analysis runs against read-only mirrors. Write access is a deliberate, separately authorised exception — never ambient, and never blanket-approved.

Suppression at the source

Sensitive columns are withheld server-side, so the client cannot render what it was never sent. Enforced in the query, not requested in a prompt.

Grounded or silent

Answers cite the record they came from, or the assistant says it doesn't know. No confident invention over a company's own data.

Secrets stay out of reach

Credentials read from the environment, never written to disk, never committed, never echoed into a log or a working file.

Nothing exposed

Private-mesh networking instead of public endpoints. If a service has no reachable front door, it has no front door to attack.

Selected work

Things that are live.

product

RaffleDock

A raffle platform for schools and nonprofits: card payments, printed QR tickets, per-student attribution and live sales reporting.

raffledock.com →
case study

A live school fundraiser

Built on it and running: printed QR tickets, card checkout, automatic receipts, and per-student sales the office can actually reconcile.

mues-raffle.com →
private ai

Self-hosted assistants

Retrieval over a company's own documents and databases, answered by a model on its own GPU. Nothing indexed, sent or stored off-site.

ios

Field apps

Native iOS tools for construction crews — supply walks, ordering, daily logistics. Built for gloves and bad signal.

integration

ERP integration

Field-captured hours flowing into a production accounting system, read-only by default, with every money-affecting call reviewed before it runs.

On device

Built for people
who aren't at a desk.

supply walk

clip pending
ordering

clip pending
daily logistics

clip pending
11AI agents in production
35Bparameter model, running in-house
0documents sent to a cloud model
0public endpoints exposed

Got something
you need built?

I take on select side projects. If you've got a problem that needs real software rather than another spreadsheet, say hello.

Get in touch