# System Prompt **Entity class:** AI control artifact **Domain:** Artificial intelligence / Model behavior **Maturity:** Developed ## Definition A system prompt is a high-priority instruction supplied to a model to define role, behavior, constraints, context, and tool-use policies for an interaction. ## Mechanism and significance It can strongly shape outputs without constituting an inviolable law, making testing, layered controls, and provenance necessary for consequential deployments. ## Relationships - **Research dossier:** [[research/ASI and RSI Timeline Research Moonshots|ASI and RSI Timeline Research Moonshots]] - **Ontology route:** [[ASI and RSI Timeline Ontology#AI Control, Law, and Alignment|AI Control, Law, and Alignment]] - **Primary fields:** [[AI Control]] · [[AI Safety]] · [[AI Infrastructure Consent]] - **Adjacent concepts:** [[Liability-Driven Alignment]] · [[Criminal Penalties for Recursive Self-Improvement]] · [[Supervised Fine-Tuning]] · [[RL-Based Alignment]] ## Sources and provenance - [[research/ASI and RSI Timeline Research Moonshots|ASI and RSI Timeline Research Moonshots]] — immediate source for this node's role in the broadcast research map. ## Evidence boundary The research dossier establishes why this entity or concept belongs in the Moonshots ontology. Time-sensitive organizational, product, policy, and performance claims should be checked against the linked primary source or a current authoritative source before reuse as settled fact.