Private AI Automation · On-Prem · Fixed Scope

AI automation that runs on your hardware.
Your data never leaves the building.

I install local language models inside your office and build the document automation on top — drafting, summarizing, note generation — with zero data egress and zero per-word API fees. Built for law firms, clinics, and anyone else who can't paste client files into a cloud chatbot.

30 minutes. I'll tell you honestly if local AI fits your workflow — and what it would cost.

0 bytes of client data sent to the cloud $0/month API fees, forever 7 local-AI tools shipped & running 100% owned by you — code included
The problem

Your team wants AI. Your compliance obligations say no.

Every cloud AI tool asks the same thing: send us your documents. For most regulated firms, that's the end of the conversation. It doesn't have to be — the models can come to you instead.

Law firms · ABA Formal Opinion 512

"Where does client data go?" needs a one-sentence answer.

The ABA's guidance on generative AI requires lawyers to vet how AI tools handle confidential client information. With a local model the answer is: it runs on a machine the firm owns, on the firm's network, and no document ever leaves it. That's a sentence you can put in an engagement letter.

Clinics · HIPAA

No third party means no BAA, no new breach surface.

Cloud AI touching PHI means business associate agreements, security reviews, and ongoing vendor risk. A local deployment sidesteps the category entirely — no PHI is transmitted, so there's nothing new to disclose and nothing new to breach.

Everyone · Economics

Cloud AI is a meter. Local AI is a machine.

Per-token pricing scales with usage forever. A local stack costs what the hardware costs — often hardware you already own. Everything I ship runs at $0/month in API fees. The meter simply doesn't exist.

$ where-does-my-data-go --check

 cloud chatbot ......... 3rd-party servers
 "enterprise" AI tool .. 3rd-party servers + BAA
 local model (Ollama) .. your machine. full stop.

$ monthly-api-bill --forecast

 cloud, per token ...... grows with every document
 local ................. $0.00 — no meter running

$ what-it-actually-does

  dictation → structured clinical note
  intake email → client summary + draft reply
  document pile → extraction spreadsheet
  case notes → engagement letter draft
  feedback inbox → weekly themes digest

 all offline. all yours.
Packages

Fixed scope. Fixed price. You own everything.

Exact price quoted after a scoping call — and it doesn't move after we shake hands. Code, prompts, and documentation are yours outright.

Automation Audit

Find out exactly what to automate — with proof, not promises.

$2,000–5,000
⏱ 2 weeks
  • Workflow & data-sensitivity mapping
  • Hardware assessment (use what you have)
  • Working proof-of-concept on your real workflow
  • Prioritized roadmap, hours-saved costed
  • Fully credited toward a build within 60 days
Start with an audit

Pro Build

A connected multi-step system for your core workflow.

$8,000–12,000
⏱ 4–6 weeks · audit credited
  • Up to 3 connected workflows, one system
  • Works with your files, exports & folders
  • Multi-user access + time-saved dashboard
  • 2-week staff pilot with iteration built in
  • 60 days of included fixes
Scope a system

Care Retainer

Keep it fast, current, and quietly improving.

$300–800/mo
⏱ Month-to-month, cancel anytime
  • Monthly health check + updates
  • Model upgrades as better ones release
  • Bug fixes, next-business-day at top tier
  • Up to 4 hrs/mo of enhancements (top tier)
  • Quarterly "what's next" review
Keep it running

The guarantee: if the Audit doesn't identify at least one automation that credibly saves 5+ hours a week, the report will say so — and I'll refund half the audit fee. I'd rather keep the reputation than the invoice.

Proof of work

Seven shipped tools. All local. All $0/month to run.

This isn't a pitch deck — it's a portfolio of working software, live on GitHub and Gumroad. Every tool runs on local models via Ollama with no API keys and no cloud. Your build is the next iteration of a stack I already run in production.

Clinical Notes

Turns dictation and rough notes into structured clinical notes — entirely on-device. PHI-safe by architecture, not by policy.

Healthcare wedge
Review Miner

Mines hundreds of customer reviews for themes, complaints, and quotable lines. Same engine works on patient and client feedback.

Feedback analysis
Content Studio

One idea in, platform-ready drafts out. The drafting pipeline behind client updates, firm newsletters, and outreach.

Drafting pipeline
Market Scanner

Scans and summarizes market and news data on a schedule. The watch-and-summarize pattern, productized.

Scheduled automation
Content Dashboard

One view of output, queues, and performance — the same dashboard layer that ships with every Pro build.

Reporting layer
Listing SEO Generator

Product info in, optimized Etsy/Shopify listings out, at scale. Bulk structured-document generation on a local model.

Bulk generation
Trade-Review Journal

Logs decisions and runs AI-powered reviews against them. Structured record-keeping plus automated analysis.

Records + review
Yours, next

The eighth tool gets built for your workflow, on your hardware, to your spec.

Start the conversation
About

Solo builder. Which is exactly the point.

I'm Hugo Kuznicki. I build AI automation on local models — the kind that runs on a machine you own instead of someone else's cloud. Seven shipped tools on that stack so far, all running at zero API cost, all built in public.

When you hire me, the person who scopes the work is the person who builds it, deploys it, and trains your staff on it. No account managers, no handoffs, no junior devs learning on your invoice. Fixed scope, fixed price, and a bias for shipping something your team is actually using within weeks — not a transformation roadmap for next year.

I document the whole journey in my newsletter and on X — you can watch how I work before you ever pay me a dollar.

$ the stack
model runtime · Ollama
models · Llama / Qwen / Mistral
interface · local web UI
deployment · your hardware
data egress · none
api bill · $0/month
Next step

Book a free automation audit call.

30 minutes. You describe the workflow that eats your week — I'll tell you honestly whether local AI can fix it, what it would cost, and what I'd build first. If it's not a fit, I'll say so on the call.

kuznickicapital@gmail.com · replies within one business day