A step-by-step worked example of AI invoice processing automation, from the AP inbox to a draft bill, showing where the LLM fits, where plain code must take over and where a human still decides.
Automating the bottleneck first is usually right, but only once it is confirmed as the real constraint, its cheap fixes are exhausted, and the work there is rules rather than judgement.
Google Photos is free until your memories pass 15 GB. Ours were 565 GB. Here is how we moved 58,039 photos and 4,118 videos to Immich on our own NAS, what the Takeout tried to do to us, and the one thing Google really was doing for the money.
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.
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.
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.
A practical method for calculating process automation ROI and payback, covering baseline measurement, full costing, adoption ramps and a worked example you can adapt.
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.
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.
A practical guide to replacing manual data entry with a validated, auditable pipeline where people handle only the exceptions and stop retyping every field.
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.
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.
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.
Consumer and enterprise software, built with taste and shipped fast.
AI agents, automation, and orchestration - production systems, not demos.
Hands-on engineering and strategy for teams shipping AI into production.