Glossary
Guardrails
Guardrails are rules and checks placed around an AI system to keep its answers and actions inside safe, intended limits.
What it means in practice
They can be written instructions, filters, permission lists or a required human approval. No guardrail is perfect, so test them with awkward input.
Example
A support bot that may only answer from your help pages and hands anything about refunds to a person.
Guide: Connect your assistant with a safe permission listGuide: A support assistant that answers from your FAQAll terms