Evaluation, Observability & Security

Covers tools and platforms for evaluating, testing, observing and securing AI systems — functional evaluation, observability, red teaming and security scanning increasingly overlap.

• Adopt
  • GitleaksChanged
• Trial
  • Deepeval
  • GarakChanged
  • LangfuseNew
  • OpikNew
  • Phoenix
  • PresidioNew
• Assess
  • AI-Assisted Penetration TestingNew
  • BetterleaksNew
  • Inspect (UK AISI)New
  • PromptfooNew
• Hold
  • RagasChanged
  • LangChain EvaluationChanged