AI-Native Architecture
The four-properties test and everything that applies it: probabilistic behavior, inference economics, the context supply chain, and model lifecycle — architecture you can fail against the frame, not just articles that mention AI.
-
It Passed the Test. That Doesn't Mean It Works.
Every testing, monitoring, and reliability practice you own rests on one assumption: same input, same output. An LLM in the call path removes it. What replaces it is evaluation, thresholds, and verification as an explicit architectural layer with a cost and an owner.
Read more → -
From Cloud-Native to AI-Native: The Next Evolution of Enterprise Architecture
Every enterprise says it's adopting AI, the same way every enterprise once said it was in the cloud. Bolting AI features onto an existing system is the new lift-and-shift — the four-properties test for what genuinely AI-native architecture requires instead.
Read more → -
Prompt Injection Isn’t a Bug. It’s a Property
Prompt injection is the SQL injection of the AI era, except there's no equivalent of a prepared statement to fix it. Why the right question isn't "how do I prevent it" but "what can a compromised agent actually do" — and how least privilege and narrow blast radius answer that.
Read more → -
Why, exactly, should I care about AI?
AI has been around since the 1950s, but it's no longer optional knowledge for architects. Why data pipelines, AI model lifecycle management, probabilistic system boundaries, and ethics all become first-class architectural concerns once AI enters your stack.
Read more →