Reference architectures
Guardrails and human-in-the-loop
Checks before and after the model, and a human approval in front of risky actions.
Guardrails sit on both sides of the model. Input guardrails reject prompt injection and off-topic requests; a PII filter redacts personal data before it reaches the model. Output guardrails check the draft answer against policy. Actions that cannot be undone, such as a refund or an outgoing e-mail, wait for a human approval. Every decision is written to an audit log. The diagram is a template for systems that must be explainable to compliance.
