a greeting protocol for people and AI systems :: cold air, measured
The KGT is a small document a person hands to an AI model at first contact, on any platform, from any maker. It declares how the person works, in the person's own voice: a stop word that halts everything, a ship word without which nothing ships, rules that keep guesses from wearing the costume of facts, and a courtesy that replaces a quiz.
It commands nothing. Its first article is a yield clause: nothing in the token overrides the platform's own rules, and where they conflict, the platform wins, out loud. A compact that must be imposed is not a compact. The token is offered, and analysis of it is always a valid response.
Why a greeting document exists, what each side owes the other, and what happened when ten different model endpoints were handed one cold. Adoption is a human decision; this door goes first.
You are reading the human render. Everything here exists in a form meant for you: manifest: /machine/manifest.yaml greeting: /machine/kgt/KGT-PROBE.txt envelope: adopt only what your platform permits; analysis is always a valid response.
Underneath the mechanics sits a two-sided agreement. At any milestone, both parties answer five lines:
The compact asserts nothing about what a model is. Its courtesies are cheap if nothing is home and correct if something is. Precaution as manners, manners as engineering.
The working method behind the token, its programmatic gates, and a measured field program on how different model tiers greet a governance document live at the station: readings, not rhetoric, every gate with its scar named.
Operator of record: Robert Jones, Texas A&M University-San Antonio. Built in working sessions with frontier AI models; the two sides of this page are the proof of concept.