Hidden instructions given to an AI model before the conversation starts. Defines role, personality, boundaries, and behavior. The first place coordination rules live before they get extracted into an OOS.
Related terms
CLAUDE.md
A configuration file that gives Claude instructions about how to behave in a specific project or organization. Loaded automatic...
Guardrails
Rules and checks that prevent an AI agent from doing things it should not do. Built into prompts, code, or review processes. Pr...
Prompt Engineering
The skill of writing instructions that get an AI model to do what you actually want. Includes role framing, few-shot examples, ...
Build with this on OTP
OTP encodes coordination intelligence so AI agent teams can run on it. If this term shows up in your team's playbook, it belongs in your OOS.
Found an issue with this definition? Tell us and we'll fix it.