Provider and Probe Strategy

Choose providers and probe combinations for layered safety

Overview

A strong guardrail program starts with the right provider and probe mix for your domain, risk profile, and latency targets.

Selection Framework

1) Define Risk Domains

Examples:

• Prompt injection and jailbreak
• Harm/toxicity and unsafe content
• PII and secrets leakage
• Industry or policy-specific requirements

2) Map Coverage to Providers

• Bud Sentinel for broad curated probe coverage and platform-native workflows.
• Cloud provider moderation where external alignment or ecosystem constraints apply.

3) Build a Minimal Viable Probe Set

Start with high-impact probes only, then expand based on real incident and false-positive data.

4) Tune Thresholds with Data

Measure flag rates and business impact, then refine profile/probe thresholds.

Example Layered Policy

Layer	Goal	Typical Probes
Input Gate	Stop malicious prompts	Injection, jailbreak, PII input
Output Gate	Prevent unsafe responses	Toxicity, violence, sexual content, PII output
Context Gate	Govern tool/retrieval stages	Secrets, unsafe data extraction

Rollout Pattern

1. Pilot on one project.
2. Monitor violations and false positives.
3. Calibrate thresholds and probe selection.
4. Replicate profile template across projects.