A request for an isolated security-lab simulation can fit an internal research assistant and still fall outside a public customer-support assistant's policy. If both entry points use the same answering model, you need to decide which policy applies before generation. I built BoundaryDesk to explore that boundary in Java. It uses Shieldstral to score input and output against a supplied policy, with Quarkus LangChain4j connecting the answering model and guardrails. You will see how the cla...