Blog
Build Log · how we actually run D3X
Blue Iris vs Frigate: Why We Moved Our CCTV to Docker
We replaced Blue Iris with Frigate in Docker so our CCTV could run alongside Home Assistant, detect objects locally and live in Git, and the real cost turned out to be memory rather than money.
My Wife’s Claude Code Talks to My Agents: Two Claude Accounts, One Home Lab, Six Locks in Between
My wife has her own Claude subscription. Now she has her own Claude Code session too, on her account, opened from her phone. It can message me, run everyday things in the house and ask my agents to find things. It can’t touch the lab. Here is how it’s wired, and the two bugs that hid my replies.
An Unattended Windows 10 USB Stick, Built on a Mac: Wipe, Install, Drivers and Apps in One Boot
We rebuilt a family member’s ThinkPad T14s from a USB stick made on a Mac: plug in, press F12, walk away. Polish Windows 10 Pro, Lenovo’s drivers, no bloat, five apps. Here is every script, and every way it broke first.
Latest articles
AI Automation in Northern Ireland: Costs, Grants and Use Cases
What AI automation really costs a Northern Ireland business, which public support is realistic to get, and which workflows to automate first.
Process Automation ROI: How to Calculate It Properly
A practical method for calculating process automation ROI and payback, covering baseline measurement, full costing, adoption ramps and a worked example you can adapt.
AI Wake-Up Music: A New Track Every Morning, Tuned to the Day
Our morning briefing used to play over the same loop of music every day. Now Lyria 3 Pro writes a new piece each morning, and three inputs decide how it sounds: the day of the week, the weather forecast and how full the to-do list is.
n8n vs Make vs Zapier vs Custom Code: Which to Choose
Zapier, Make, n8n and custom code each fit a different workflow, team and volume, and this guide covers how to choose and when to move between them.
How to Choose an AI Development Partner: 12 Questions to Ask
Twelve practical questions that separate an AI development partner who can ship a reliable production system from one who can only ship a good demo.
EU AI Act Compliance Checklist for SMEs: 2026 Deadlines
A practical EU AI Act compliance checklist for SMEs: which deadlines already apply, what changes on 2 August 2026, and how to tell whether your AI use is high-risk.
How Much Does It Cost to Build an AI Agent in 2026?
A practical breakdown of what a custom AI agent costs to build and run in 2026, tier by tier, with the cost drivers that actually move the number.
AI Security and Compliance: The Complete Guide for EU Firms
A practical guide to AI security and compliance for EU firms, covering the EU AI Act, GDPR, sector rules, the threats specific to AI systems, and the controls to put in place first.
LLM Integration: A Complete Guide for Production Systems
LLM integration is mostly about the layers around the model: a gateway, context assembly, validation, evaluation, observability and guardrails. This guide covers how to build each one for production.
Custom Software vs Off the Shelf: A Guide for Irish SMEs
A practical build vs buy guide for Irish SMEs: buy the commodity, build what makes you different, and integrate the middle so your systems compound instead of fighting each other.
AI Readiness Audit: How to Assess Your Software Architecture
A senior-engineer’s guide to running an AI readiness audit on your software architecture: what to inspect, how to score it, and what to fix first.
How to Reduce Technical Debt Faster with Automated Systems
Automation pays down technical debt fastest when it handles the mechanical work, such as upgrades, codemods, tests and guardrails, so engineers can spend their judgement on design.
Compliance Reporting Automation for Regulated Industries
How regulated firms can automate compliance reporting so every figure is traceable, every exception reaches a human, and the result holds up when a regulator asks how a number was produced.
How to Scale Operations Without Hiring: A Practical Guide
Hiring is the default answer to growing volume, but automating the transcription and coordination work that scales one-for-one with demand lets your existing team absorb growth without adding headcount.
AI Automation Challenges to Plan For Before You Build
The model is rarely what breaks an AI automation project; messy inputs, silent failures, missing evaluation, unplanned exceptions and unclear ownership are.
What We Do
Product
Consumer and enterprise software, built with taste and shipped fast.
Infrastructure
AI agents, automation, and orchestration - production systems, not demos.
Advisory
Hands-on engineering and strategy for teams shipping AI into production.