Skip to main content

System prompt

A standing set of instructions the operator places above every user message, usually hidden from the user, that sets the assistant's role, rules, tone, and refusals. It is the most powerful everyday governance surface most organizations have, and functionally it is policy: it decides what the AI does for every user until someone changes it.

Defined in 2 GAGE programs, which carry 3 distinct definitions of it. The wording above is taught in AI Governance: Applied Mastery.

How each discipline defines it

The same term does different work depending on who is using it. These are the definitions as each program teaches them, unedited.

AI Governance: Applied Mastery

A standing set of instructions the operator places above every user message, usually hidden from the user, that sets the assistant's role, rules, tone, and refusals. It is the most powerful everyday governance surface most organizations have, and functionally it is policy: it decides what the AI does for every user until someone changes it.

Agentic AI Governance: Applied Mastery

the specific text implementation of the instructions component in most LLM-based systems, sent to the model ahead of the user's own input to establish role, capability, and constraint.

AI Governance: Applied Mastery

The hidden instructions that tell the model who it is and what rules to follow. It is powerful (it shapes all behavior) and fragile (it can be overridden by injection and leaked to attackers), and it should never contain secrets, because a leaked system prompt hands the attacker your rules.

Where it is taught

The exact lessons this term appears in. The first 7 topics of every program are free with a free account.

Terms it appears with

Not an alphabetical neighbourhood: these are the terms taught in the same lessons, ranked by how often they appear together.

Prompt injectionContext windowAgentRAG (Retrieval-Augmented Generation)Training DataRetrieval-Augmented Generation (RAG)ConfigurationGeneral-purpose AI (GPAI)