Guardrails
Checks and limits (enforced in code) on what an agent can take in, put out, or do.
Checks and limits (enforced in code) on what an agent can take in, put out, or do.
Checks and limits — in the prompt or in surrounding code — on what goes in and what comes out, to keep behavior safe and on-policy.
Input/output filters around a deployed model that block unsafe or disallowed content. (M14)