# Guardrails

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: guardrail, safeguards, safeguard, content filter, moderation, safety filter, AI safeguards

[Checks](https://ecosystem.samcarlton.com/automated-check) and limits built around a model inside a product. They screen what users send in and what the model sends back, and block or [flag](https://ecosystem.samcarlton.com/feature-flag) anything that breaks the rules.

**For example:** A tutoring app for children [checks](https://ecosystem.samcarlton.com/automated-check) each reply before showing it. A reply that contains violent content is blocked and replaced with a safe message.

## Connects to (9)

- [AI safety](https://ecosystem.samcarlton.com/ai-safety): The work of making AI systems behave safely and of measuring how safe they are.
- [System prompt](https://ecosystem.samcarlton.com/system-prompt): Standing instructions that the builder of an AI product gives the model before any user types.
- [Prompt injection](https://ecosystem.samcarlton.com/prompt-injection): A security weakness in AI products.
- [AI use policy](https://ecosystem.samcarlton.com/ai-use-policy): An organization's rules for which AI tools its people may use and what information they may put into them.
- [Permission mode](https://ecosystem.samcarlton.com/permission-mode): The rules that decide which actions an agent may take on its own and which need your approval first.
- [Human in the loop](https://ecosystem.samcarlton.com/human-in-the-loop): Designing an AI process so a person reviews, approves or corrects the AI's work at key steps instead of letting it act alone.
- [Deepfake](https://ecosystem.samcarlton.com/deepfake): Realistic fake video, audio or images of a real person made with AI, showing them saying or doing something they never did.
- [Alignment](https://ecosystem.samcarlton.com/alignment): Work to make AI models pursue what people actually intend and behave according to agreed values, such as being honest and refusing harmful…
- [NIST AI Risk Management Framework](https://ecosystem.samcarlton.com/nist-ai-rmf): A voluntary framework from NIST, the US standards agency, that helps organizations manage the risks AI can pose to people, organizations…

Map view: https://ecosystem.samcarlton.com/guardrails