Writing · Page 2 of 5
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.
AI Security
AI created three security surfaces at once: code written faster than it can be reviewed, agents holding real credentials, and attackers using the same tools you are. Most security advice addresses one and ignores the other two. This is the working guide to all three, plus what the compliance picture actually requires rather than what the vendor deck claims.
IrenicTech · Sep 21, 2026 · 9 min read
AI Automation
TypeSafe AI released a model that cannot hold a conversation, which is the point of it. Jev takes unstructured state in and returns a typed decision with a calibrated probability, in 70ms to 500ms. We went through the 21 decision nodes in our published automation teardowns to see where a model like this actually belongs. The answer is six of them, and the reasoning matters more than the number.
IrenicTech · Sep 21, 2026 · 7 min read
Agentic AI
Anthropic's own research says developers use AI across roughly 60% of their work but can fully delegate only 0% to 20% of tasks. That gap is not a failure of the models. It is the actual shape of agentic development, and it changes what you should expect from an AI-native team.
IrenicTech · Jul 12, 2026 · 5 min read
E-commerce
Agentic commerce stopped being a demo. Three protocols now cover discovery, payment, and authorization, and as of June 2026 Shopify lets any developer register an agent without applying. The merchant-side work is concrete, and most stores have not started.
IrenicTech · Jul 12, 2026 · 6 min read
Cybersecurity
Microsoft says its agents automate 75% of phishing and malware investigations. That's real, and it's vendor-reported. Meanwhile the Gartner stat, the false-positive rate, and the SOC cost comparison everyone quotes trace back to nothing at all. Here's how to tell the difference.
IrenicTech · Jul 12, 2026 · 6 min read
Cybersecurity
Everyone braced for AI to flood their inbox with better phishing. Instead, AI-assisted phishing declined while attackers moved AI into malware development and autonomous intrusion. Here's what 832 banned accounts reveal, and what it changes for companies that aren't banks.
IrenicTech · Jul 12, 2026 · 5 min read
Cloud Security
The 2026 threat data says something uncomfortable: most attackers aren't deploying malware, they're signing in with credentials that work, and they're doing it in the cloud. Here's what the numbers mean and what to actually change.
IrenicTech · Jul 12, 2026 · 6 min read
Cloud Infrastructure
The State of FinOps 2026 says 98% of practitioners now manage AI spend, up from 31% two years ago. It also says the easy cloud savings are gone and teams are being asked to self-fund AI out of optimization. Those two facts collide.
IrenicTech · Jul 12, 2026 · 5 min read
Healthcare
81% of physicians now use AI, up from 38% in 2023. Meanwhile the compliance conversation is stuck on HIPAA, where no AI guidance exists, and ignoring Section 1557, where a binding obligation has been in force since May 2025.
IrenicTech · Jul 12, 2026 · 6 min read
Read us on Google
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 sourcesStart a conversation
Share the essentials and we’ll reply within 4 hours with a real next step, not an auto-responder.
What happens next