Output guardrail
A guardrail that checks or filters what comes out of a model before anyone sees it or it takes effect.
Also called
- Output filter
- Content filter
- Output validation
Kind of
- Guardrail A check, built into the harness or written into the instructions, that screens what goes in, what comes out, or what an agent tries to do.
Related
- Data exfiltration A type of AI system attack which attempts to have the system send private data outside your company or to anyone not permitted to see it.