Skip to main content

Overview

The Guardrail module helps you discover, configure, and deploy safety protections for model traffic and agentic workflows in Bud AI Foundry. You can combine provider probes, tune severity, choose guard types, create governance policies, and deploy protections to projects, endpoints, or agent versions through guided workflows.

What You Can Do

Discover provider probes Browse guardrails from Bud Sentinel and cloud providers with searchable metadata, tags, and status indicators. Compose reusable profiles Create profiles with selected probes, guard types, and thresholds to standardize safety policy across teams. Deploy with flexibility Deploy as a standalone Guardrail Endpoint or attach to an existing deployment. Govern agentic workflows Create governance policies that define what agents may do, when checks run, and whether Bud should allow, redact, notify, escalate, or deny matched behavior. Operate with visibility Review details through profile pages, governance policy cards, project-level tables, and agent Governance tabs with status, timestamps, and deployment context.

Core Capabilities

Typical Use Cases

Pre-Response Safety

Screen prompts and outputs before they reach users.

Compliance Enforcement

Apply consistent policies to regulated workloads.

Prompt Injection Defense

Block jailbreak and misuse patterns early in request flow.

PII Protection

Detect sensitive data exposure and reduce leakage risk.

Agent Tool Control

Allow, deny, notify, or escalate tool access during agentic workflows.

Governance Policy

Define and attach agent governance policies.

Getting Started

Quick Start

Create and deploy your first guardrail quickly.

Guardrail Concepts

Learn profiles, probes, rules, governance policies, and execution behavior.

Step-by-Step Tutorial

Build a production-ready guardrail profile.

Governance Policy

Define and attach agent governance policies.