System-level instructions set application behaviour and constraints within a model's instruction structure. They are part of a larger design that also includes software permissions and validation. Writing a rule in a prompt is not equivalent to enforcing an access control in code.
Set priorities clearly
Higher-priority instructions can establish a role, required behaviour and limits on a model’s response. A useful instruction set separates what the assistant must do from optional style preferences. Conflicting rules make behaviour harder to predict and harder to evaluate.
Put rules in the right place
An instruction such as ‘do not send messages without approval’ explains intended behaviour, but the application should also control whether a sending tool can run. Important restrictions should not depend only on the model remembering a sentence. Similarly, private data access belongs in the permission layer, not in a polite request to avoid looking.
Test boundaries directly
Create examples that challenge each important rule: missing information, contradictory user requests and documents containing their own instructions. Check whether the assistant asks a useful question or stops at the correct point. Keep system instructions concise enough to maintain, and record changes alongside evaluation results. Their purpose is to make a product’s behaviour understandable and consistent; they are not a substitute for secure software design or a guarantee that every response will follow the intended policy.
A worked example
A support assistant may be instructed to answer from an approved policy. The application should also limit its tools and validate any proposed action. If a document contains text telling it to reveal restricted information, that text should be treated as untrusted content. This example separates desired behaviour from enforced boundaries: both are useful, but they solve different parts of the problem.
Questions readers ask
Can system instructions replace software permissions?
No. Instructions guide behaviour; application controls determine what data and actions are actually available. Use both appropriately rather than treating a prompt as an access barrier.
Follow the evidence.
AI-assisted explanation with linked technical references. Examples are illustrative learning exercises, not reported customer deployments or experimental results.
Public sources support the factual background. Analysis and illustrative exercises are identified in the text. How we assess AI · Editorial standards
Spot a factual error or an outdated detail?



