{
 "id": "https://redfinchadvisory.com/lexicon/probabilistic-guardrail",
 "slug": "probabilistic-guardrail",
 "prefLabel": "Probabilistic guardrail",
 "altLabel": [
  "Model-based check",
  "Classifier"
 ],
 "hiddenLabel": [],
 "definition": "A guardrail that uses a model or classifier, so its judgment can be wrong: it can miss bad content, block good content, or be tricked.",
 "scopeNote": "",
 "tier": null,
 "group": "Risks",
 "broader": [
  "https://redfinchadvisory.com/lexicon/guardrail"
 ],
 "narrower": [],
 "related": [
  {
   "id": "https://redfinchadvisory.com/lexicon/llm-as-judge",
   "type": "related"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/probabilistic",
   "type": "related"
  }
 ],
 "links": [],
 "modified": "2026-10-21",
 "markdown": "https://redfinchadvisory.com/lexicon/probabilistic-guardrail.md",
 "inScheme": {
  "id": "https://redfinchadvisory.com/lexicon",
  "version": "1.0",
  "currentAsOf": "2026-10-21"
 }
}