Skip to main content
This Quick Start Notebook introduces Fiddler Guardrails’ Safety Detection capabilities, an essential component of our enterprise solution for protecting LLM applications. Learn how to implement the Safety Model, which identifies harmful, sensitive, or jailbreaking content in both inputs and outputs of your generative AI systems. Inside you’ll find:
  • Step-by-step implementation instructions
  • Code examples for safety evaluation
  • Practical demonstration of harmful content detection
  • Sample inputs and outputs with risk score interpretation
Before running the notebook, generate a Fiddler API key from Settings → Credentials in your Fiddler environment. See the Guardrails documentation and FAQ for more help getting started.
Interactive TutorialRun the Safety Guardrail notebook end to end:Open the Safety Guardrail Notebook in Google Colab →Or download the notebook from GitHub →