Blog
Build Log · how we actually run D3X
Home Lab Documentation That Keeps Itself Current: Gitea, GitHub and a Nightly Snapshot
Every repo in our lab lives on a self-hosted Gitea first and is mirrored to private GitHub as a backup. A wiki rebuilds itself minutes after each change, and every night the live configs of the lab are copied into git with the secrets taken out and the inventory pages are rebuilt from the live systems.
Home Assistant Local Voice Assistant: Bilingual for $2 a Month
How we built a mostly local English and Polish voice assistant on Home Assistant with Whisper, Piper and a small hosted LLM, what broke along the way, and why it costs about $2 a month.
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.
Latest articles
Automate Manual Data Entry: From Keying to Reliable Workflows
A practical guide to replacing manual data entry with a validated, auditable pipeline where people handle only the exceptions and stop retyping every field.
Practical AI for Mid-Sized Companies: What Actually Works
Practical AI for a mid-sized company means automating the repetitive middle of two or three high-volume workflows, with people approving what matters, not launching a transformation programme.
AI Manufacturing in Ireland: What Actually Works on the Floor
A practical look at where AI and automation are delivering on Irish factory floors, where they stall, and how to pick a first project that survives contact with production.
How to Build Software Systems That Compound Over Time
Software compounds when each thing you build makes the next one cheaper, faster and more accurate, and this guide shows how to design for that from your first workflow.
Identifying Bottlenecks: Which Business Processes Should You Automate First?
Find the step where work waits longest, fix the process around it, then automate the frequent, rule-based work on that constraint first. A scoring method included.
Data Security and Privacy in AI Projects: Best Practices for 2026
The default controls for secure AI projects: data mapping, minimisation, EU hosting, zero-retention providers, permission-aware retrieval, audit logs, tool limits, DPIAs and EU AI Act dates.
Integrating Large Language Models (LLMs) into Legacy Enterprise Systems
Put a thin, tested façade in front of the legacy system, decouple model calls with queues, retrieve rather than retrain, and keep people on the consequential writes.
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.