How do you separate policy enforcement from model style instructions?

Example Answer

The way I'd approach it in an interview is this: Style instructions shape how the model speaks. Policy enforcement shapes what the system is allowed to do or reveal. Those should not live in the same fragile place if the business depends on them differently.

I prefer policy enforced through orchestration, tool controls, validation, and dedicated safety logic where possible, while the prompt handles tone, format, and interaction style. If a critical rule exists only as a polite instruction in the prompt, it is too easy for adversarial or noisy context to weaken it.

Separation matters because policy is a control boundary. Style is a presentation preference.

What I always try to avoid is giving a process answer that sounds clean in theory but falls apart once the data, users, or production constraints get messy.

Common Poor Answer

A weak answer is saying you can solve policy and style with one strong system prompt. The stronger design gives policy its own enforcement path.