Agent design
Preference inference as infrastructure: the MEE framework
Agent personalisation usually means hard-coded rules. Treating preference as a weighted, evidence-tracked signal layer changes what agents can do.
Reece Frazier
Operating principles
Honest bad news: writing leadership updates that don't lie
Most status updates are designed to protect the sender. Ours are designed to inform the reader.
Agent design
Why We Replaced Markdown With JSON: The Constitutional Stack
Prose specifications can't be verified. A constitutional stack needs a runtime, and a runtime needs structured data.
AI adoption
The oversight vacuum: why AI adoption without governance is tearing companies apart
I've watched the same pattern repeat across dozens of organizations in the past 18 months. A leadership team sees a demo. Someone in the room plays with ChatGPT over lunch. The conversation shifts from "should we" to "how fast can we" in a single