● writing · the engineering blog
Notes on AI you can actually own
Hands-on writing about local LLMs, self-hosting, and the real economics of small-business automation — by dArt Studio.
AI Data Centers in Homes — Should Your Small Business Care?
NVIDIA and Span want to put AI compute nodes in customer homes. Here's what that actually means for a salon, dental office, or plumbing shop in South Florida.
read →
Finally documenting our environment properly
The senior sysadmin is the worst person to write the runbook. We've been watching how small IT teams are actually solving the "everything lives in my head" problem, and a pattern keeps showing up — one we didn't predict. The setup most people land on: voice dictation while the work is fresh. Fix something, narrate what you did for two minutes, clean it up later, drop it in the wiki. One team we've been talking to went from a 12-page wiki to 80 pages in four months this way. The surprise isn't that it works. The surprise is whose docs are better. The senior, dictating a procedure he's done a hundred times, skips the steps that have become invisible to him. The junior, narrating the same kind of work, explains it at the level someone unfamiliar would actually need — which is the level a runbook is supposed to be written at.
read →
Qwen 3.6 and why South Florida shops should pay attention
Alibaba's latest open model shipped with a notable upgrade in non-English quality. In any bilingual market, that actually matters.
read →Gemma 4 launched — why we're not using it for clients (yet)
Google shipped a new generation of open models. Benchmarks are good. Field notes on why a production switch isn't automatic.
read →On-prem AI for small businesses — hype vs. what works
Running AI "on your own server" sounds great until you price the GPU. Here's what's actually realistic at the small-operation end of the spectrum.
read →The full stack we use on our own chatbot (and why it's boring)
Next.js + FastAPI + MySQL + Ollama + Apache + systemd. Nothing on this list is new. That's the argument.
read →2025 in small-business AI — what actually changed
Five things that actually changed for anyone running small technical operations with AI in 2025. No predictions, just what shifted.
read →When to stop paying OpenAI — the break-even math
Cloud APIs win at volume zero. Local models win past a certain point. Here's the specific number where the line crosses for typical workloads.
read →Why we default to Ollama for small-business AI
The same toolchain that data engineers are using to run models locally turns out to be the right default for small, long-lived deployments. Here's why.
read →The real cost of an AI chatbot for a small business (spreadsheet included)
What an AI chatbot actually costs to run in 2026. Line by line, no vendor math, no hidden items.
read →Running AI on a $20/month VPS — what we actually measured
Can a cheap rented server really host a working AI chatbot? Three small models benchmarked on real small-business questions. Here's what held up.
read →The DeepSeek moment, and what it meant for your coffee shop
When a Chinese lab shipped a reasoning model you could run on your own hardware, the ground moved for everyone — especially anyone paying per token.
read →