Engine and Agents

The "HOW": An honest account of LLMs and AI agents: what they are, how they fail, and how to govern a participant that isn't an employee.

17 hours ago1 min read

Hallucination? Nothing malfunctioned

AI agents and LLMs are probabilistic system and can hallucinate by design. It can't be stopped. Right architecture can manage it.

Jul 9, 20242 min read

Compares two automation approaches: designing processes for robots (Xiaomi) vs. replacing people in human-centric processes (Amazon).

Jul 1, 20243 min read

Posits that the real business threat of AI comes from competitors using it, not superintelligence. The opportunity is in process optimisation.

Jun 28, 20243 min read

Defines architecture as a method, instrument, and asset, using historical city plans to illustrate how architecture reflects priorities.