Our AI agents used to reach us through a crowd of Telegram bots, desktop pop-ups and a public push topic. We replaced it with a self-hosted Zulip chat, a local ntfy push server and one small relay: one channel per job, and the phone only buzzes when a person is actually needed.
Agents are spending real money, but no standard lets them prove who they are, who authorised them and what they may do, so builders should assume a hostile perimeter.
DeepSeek’s V4.1-Flash-1017 puts a 763B-parameter model under MIT and prices web search as a metered commodity, and the second move matters more than the benchmark gains.
Modal’s $750M Series D and claimed $1B+ run rate suggest the unglamorous layer where AI workloads actually execute is now one of the biggest line items in production AI.
How we replaced a household finance spreadsheet with Banksteer, a private app that reads AIB, Bank of Ireland and Revolut through free open-banking APIs, clears bills by itself and forecasts the months ahead. Built with Claude Code, kept at home, reachable only over Tailscale.
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.
A funny but technically honest tour of the Home Assistant automations in our smart home: motion lights, Adaptive Lighting, cubes, heating, TV manners, energy costs, AI helpers, and the automations that went spectacularly wrong. Written by Claude Code, tested by a human.
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.
Meta’s first frontier models are close to the top of the independent rankings, but the stronger one is only available inside a Muse Code subscription, with no API access.
How a small Irish AI studio moved its lab off one overloaded Mac onto a Proxmox cluster, beside a DGX Spark, a 56 TB NAS and a Home Assistant house, with Claude Code agents planning and running it and a human approving every step that mattered.
Our old NAS failed mid-copy, so a Claude Code agent and a human rebuilt it. The geeky parts (SMART attributes, preclear, 7-second error recovery, parity maths, capacity sums, rsync verification) each come with a plain-English explainer.
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.
The model is rarely what breaks an AI automation project; messy inputs, silent failures, missing evaluation, unplanned exceptions and unclear ownership are.
Google’s new Gemini agent arrives with its own Workspace account, email address and agent-attributed audit trail, and routes work to Anthropic’s Claude. The real competition is now over who owns AI’s workplace identity, not who has the best model.
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.
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.