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

# Guardrail Concepts

> Understand probes, profiles, rules, and deployment behavior

## Guardrail Request Lifecycle

Guardrails can evaluate content at multiple stages before and after model processing.

```mermaid theme={null}
flowchart LR
    A[Client Request] --> B[Input Guard Checks]
    B --> C[Model Inference]
    C --> D[Output Guard Checks]
    D --> E[Response Delivered]
```

## Core Building Blocks

### Providers

Providers supply detection capabilities. Bud AI Foundry supports Bud Sentinel and cloud moderation providers.

### Probes

A probe targets a specific risk area (for example, PII, toxicity, jailbreak, or safety categories).

### Rules

Rules are the detection units within probes. You can often enable/disable or tune behavior per rule.

### Profiles

A profile is your reusable policy package:

* selected probes
* guard type scope
* severity threshold and overrides
* deployment targets

### Deployments

Deployment activates the profile in runtime paths, either as standalone or attached to an existing endpoint.

## Guard Types and Evaluation Scope

| Guard Type                           | Evaluation Point                | Common Intent          |
| ------------------------------------ | ------------------------------- | ---------------------- |
| `input`                              | Before prompt reaches model     | Block malicious input  |
| `output`                             | Before response reaches user    | Prevent unsafe output  |
| `retrieval/tools` (where applicable) | During extended workflow stages | Govern tool/data paths |

## Severity and Policy Tuning

```mermaid theme={null}
flowchart LR
    A[Profile Threshold] --> B[Probe-Level Override]
    B --> C[Rule-Level Override]
    C --> D[Final Enforcement Decision]
```

Higher thresholds generally increase sensitivity and can reduce unsafe leakage, but may increase false positives. Calibrate with real prompts and staged rollout.

## Execution Patterns

| Pattern                  | Behavior                              | Use Case                           |
| ------------------------ | ------------------------------------- | ---------------------------------- |
| Parallel probe execution | Evaluate multiple probes concurrently | Lower latency under broad coverage |
| Sequential evaluation    | Process probes in a fixed order       | Controlled policy precedence       |
| Fail-fast handling       | Stop at first critical violation      | Strict compliance gates            |
| Aggregate handling       | Collect all violations                | Rich audit and analysis            |

## Operational Views in Bud Admin

* **Guardrails page**: profile discovery, filtering, and creation entry point.
* **Guardrail details**: General, Probes, and Deployments tabs.
* **Project Guardrails tab**: project-scoped list with status and management actions.