Writing

Notes from the work.

Field notes from the IrenicTech team on building AI agents, AI automation, and custom software, and on shipping production AI products that actually reach real users.

Why Your Platform Needs to Be Secure: What We Can Learn From the Railway and Primcloud Incident

Cybersecurity

Why Your Platform Needs to Be Secure: What We Can Learn From the Railway and Primcloud Incident

A Railway engineer says agents he was running caused activity that Primcloud's founder calls an attempt on his infrastructure. The public argument is about intent. The more useful questions are what separates a penetration test from everything else, and what the reported steps would find on your own platform. Here is what is confirmed, what is only alleged, and what to do this month.

IrenicTech · Nov 5, 2026 · 19 min read

Ivanti Connect Secure: Three Chained Flaws, Root Access, and Why Patching Is Not the End of It

Cybersecurity

Ivanti Connect Secure: Three Chained Flaws, Root Access, and Why Patching Is Not the End of It

Attackers were using three chained Ivanti Connect Secure flaws by at least 3 October, before Ivanti had a fix for the 22.8 and 25.1.1 lines, or for the full chain, so the 29 October update closes the door without telling you who already came through it. This post gives a team with no security operations staff a way to judge exposure from dates, read the Integrity Checker honestly, and rotate the secrets a VPN appliance holds.

IrenicTech · Nov 2, 2026 · 16 min read

Nine Production Automations Have 31 Endings. Fewer Than Half Are the Happy Path

AI Automation

Nine Production Automations Have 31 Endings. Fewer Than Half Are the Happy Path

Almost nobody publishes the architecture of the automations they deliver, so almost nobody can say what one actually looks like. We publish nine, which means we can count them. Across 139 nodes and 148 edges in nine sectors, the systems fan out rather than funnel: 15 ways in against 31 ways out. And of those 31 endings, only 15 are the thing the system was built to do. The rest are refusals, holds, escalations and self-maintenance.

IrenicTech · Sep 23, 2026 · 7 min read

AI Agent Development in 2026: From First Prototype to Production

Agentic AI

AI Agent Development in 2026: From First Prototype to Production

Most writing about AI agents is either a demo or a warning. This is the working guide: what an agent is made of, how it reaches your systems through MCP, when one agent should become several, how much the model choice actually matters, why the majority never reach production, and what governance has to be in place before any of it is load-bearing. Every section links to the deeper piece on that question.

IrenicTech · Sep 21, 2026 · 16 min read

Read us on Google

Make IrenicTech a preferred source.

Tell Google you want our work first. It takes one tap, and IrenicTech is favoured in your Top Stories, AI Mode, and AI Overviews whenever you search the topics we write about.

Add to preferred sources

Start a conversation

Tell us what you’re building.

Share the essentials and we’ll reply within 4 hours with a real next step, not an auto-responder.

What happens next

  1. We reply within 4 hours, from a real person, not an auto-responder.
  2. A short scoping call to understand the goal, constraints, and timeline.
  3. A fixed-scope discovery sprint: a working prototype and a written estimate.
Office
Austin, TX, United States
Hours
Mon–Fri · Async + scheduled calls

Fields marked are required. By sending you agree to our Privacy Policy.