> ## Documentation Index
> Fetch the complete documentation index at: https://docs.opper.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Guard

> Block or redact content before it reaches the model and before responses go out.

Guard checks every call at the gateway, both ways. It can scan the user's input before the model sees it, and the model's response before it reaches your code.

A typical use: redact credit card numbers from incoming messages, or block responses that look like a leaked API key.

## Two kinds of rule

Open **Controls → Guard** in [platform.opper.ai](https://platform.opper.ai) and add a rule.

### LLM Guard

A custom prompt that asks a model to classify content. Use it for fuzzy things like tone, intent, or categories.

| Field  | What it does                                                                                                     |
| ------ | ---------------------------------------------------------------------------------------------------------------- |
| Prompt | Classifier instructions. Example: *"Flag messages that include a plaintext password, API key, or access token."* |
| Model  | **Auto**, **Small**, **Medium**, or **Large**. Auto picks the cheapest model that supports structured output.    |
| Action | Flag, Block, or Redact (see below).                                                                              |
| Where  | Input only, output only, or both.                                                                                |

Templates: **PII**, **Toxicity**, **Secrets**.

### Regex Guard

Pattern matching. Use it for known formats like credit cards, emails, SSNs, and API keys.

| Field       | What it does                                                                                                                                                                                                                            |
| ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Patterns    | One or more regex patterns. Each has an optional name, the pattern itself, and standard flags: `i` (case-insensitive), `m` (multiline), `s` (dotall). The editor has a tester and an AI helper that drafts patterns from a description. |
| Replacement | What to substitute when redacting. Default: `***`.                                                                                                                                                                                      |
| Action      | Flag, Block, or Redact.                                                                                                                                                                                                                 |
| Where       | Input only, output only, or both.                                                                                                                                                                                                       |

Templates: **Email**, **Phone**, **Credit Card**, **SSN**, **API Key**.

## Actions

| Action | What happens                                                                                 |
| ------ | -------------------------------------------------------------------------------------------- |
| Flag   | The match is logged on the trace. The call proceeds.                                         |
| Block  | The call fails. Input-side: before the model runs. Output-side: before the response returns. |
| Redact | The matched text is replaced (default `***`, or your replacement text).                      |

## Where it applies

| Scope        | Applies to                     |
| ------------ | ------------------------------ |
| Organization | Every call in your org.        |
| Project      | Calls in one or more projects. |

You can layer rules. For example, run an org-wide secrets check alongside a stricter toxicity check on a customer-facing project. Each rule fires independently.

## Where you see the result

A **Guardrail** event appears on the [trace span](/control-plane/trace) with a Shield icon and status:

* **Passed**: the content was fine.
* **Flagged**: matched but the action was Flag, so the call proceeded.
* **Blocked**: the rule rejected the call.

Each event carries the rule name, a family label (*LLM guard* or *Regex guard*), and a scope badge. Redacted content appears already replaced in the span's input or output.

In the playground, Guard runs when **Project controls** is on. Open the **trace ↗** link to see the event.

<Tip>
  Start with **Flag** while validating a new rule. Once you trust it, switch to **Block** or **Redact**. Combine an LLM Guard (fuzzy: toxicity, intent) with a Regex Guard (exact: card numbers, API keys).
</Tip>