The forward deployed engineer is suddenly tech's hottest role. What FDEs actually do, what is expected of them, and the technical, product and human skills the job demands, from a practitioner who does forward-deployed AI work.
AI assistants write fluent Laravel code that hides the security mistakes the framework prevents. How AI code generation changes the risk picture, a review workflow for what the assistant hands you, and how it connects to the book You Are the Quality Control.
A practical hub for reviewing and hardening Laravel applications: authentication and authorization, the database layer, validation, file uploads, dependencies and logging, with the guides I use on real reviews.
How a two-sided tutoring marketplace was delivered with a PRD-first method, bulk code generation running entirely on private infrastructure (OpenCode and Ollama), and manual-first debugging assisted by Claude Code and OpenAI Codex.
Retrieval-augmented generation turns your company's documents into something you can ask questions of, grounded in your own material and running entirely on infrastructure you control. The private stack, the build order, and the failure modes (permission bleed, stale indexes, uncited answers) that separate a demo from a deployment.
I have been working with technology for more than two decades. I have programmed in more languages than I can now remember, worked with servers, databases, DevOps, cloud platforms and artificial intelligence, and written books…
ailane (AI Lane) is my free, open-source command line tool that inspects a machine's hardware and tells you which local AI models it can run. It answers the questions everyone has before running AI models…
Ollama is how most engineers first run an open model: one install, one pull, and a model is answering on your laptop. My Ollama guide covers that single-machine story. This guide is the next chapter:…
When I review a private AI deployment, planned or already running, I walk the same list every time. It exists because every item on it has bitten a real team somewhere: the endpoint that was…
Running an open model on your own laptop takes fifteen minutes; my Ollama guide covers that. Running LLMs for a whole company is a different job: shared hardware, concurrent users, access control, and a service…
I use AI coding tools every day, I help teams adopt them, and I wrote a book about staying safe while doing it. So let me say this clearly at the start: the security risks…
Every company adopting generative AI eventually faces the same question, usually sooner than it expected: should we call a cloud AI API, or run the models ourselves? I have sat on both sides of this…
Private AI means running generative AI entirely inside your own infrastructure: your models, your servers, your network, your data. Nothing leaves. I help organizations design, deploy, and operate these systems, from the first hardware sizing…
Run large language models on your own machine with Ollama — and offload the big ones to the cloud — with install steps, the local API, and Ollama Cloud.