# Are a model provider's safety filters enough?

A model provider's safety filters stop content the provider forbids for everyone. They do not know your product's rules, your data or your agent's tools, which is what separate guardrails are for.

## Side by side

| | Provider safety filters | Your own guardrails |
| --- | --- | --- |
| Whose rules | The provider's usage policy | Yours |
| Covers | Broad harm categories | Any policy you write |
| Knows your data | No | Yes, through your policies |
| Tool calls | Not judged against your rules | Checked before they run |
| Across providers | Different for each model | The same everywhere |
| Evidence | Little | A log of each verdict and why |

## What the provider's filters are good for

They are free, already on, and catch the worst general content. Keep them.

## What they miss

- **Your rules.** "Do not quote another customer's order" or "do not discuss competitors" is no provider's concern.
- **Actions.** Whether a tool call is safe depends on your systems.
- **Consistency.** Change model or provider and the behaviour changes with it. Open-weight models you host come with no filter at all.
- **Tuning.** You cannot adjust a provider's threshold when it blocks your honest users.
- **Audit.** A refusal with no reason is hard to show a regulator.

## The usual setup

Provider filters as the floor, your own guardrails for everything specific to you. See [system prompt vs guardrails](/glossary/system-prompt-vs-guardrails) for why instructions to the model are not a third layer you can rely on.

## With White Circle

[Control](/products/control) works with any model or setup, through an API or as middleware, so the same policies hold when the model behind them changes.

