Mark Ferraz · Perspective

AI memory as built today is a property of the agent.

AI coding agents collapsed the cost of generating software while the cost of securing it climbed.

AI capability does not produce delegation.

Frontier intelligence in regulated work is insurance against catastrophic error, not labor arbitrage.

Generation got cheap.

A decade of building systems inside the energy majors (Chevron, Marathon, Southwestern Energy): what AI changes in those environments, what it doesn't, and what the operator-architect carries that frameworks cannot.

Why model-level tuning isn't enough: alignment lands at the user, not in the lab.

Bitemporal claims that supersede instead of overwrite.

Why public training data converges to the median, what that means for solo operators using AI for research, and why human judgment must precede generation.

A 25-year practitioner's view of the divergence forming between operators who use AI to extend judgment versus those who use it to substitute for it.

The semantic inflation of the word 'agent' is masking real engineering tradeoffs.

Building production software with autonomous coding agents instead of a consistent team.

The distinction between conversational memory, vector retrieval, and structured knowledge graphs, and why most LLM applications are quietly building the wrong thing.

Regulated-industry requirements for AI agents (auditability, policy enforcement, deterministic guardrails), and why most commercial offerings fall short.

Foundation models are commoditizing fast.