Fiddler AI

Model Monitoring

Production monitoring for performance, drift, data quality, and fairness regressions.

Bias & Fairness Testing

Automated statistical testing for disparate impact across protected attributes, with audit-ready reports.

Explainability

SHAP, LIME, counterfactual, and feature-importance explanations for model decisions.

Drift Detection

Automated detection of distribution shift, feature drift, prediction drift, and performance degradation in deployed ML/AI models.

Hallucination Detection

Automated scoring of LLM outputs for factual accuracy and groundedness, typically via retrieval-backed verification or reference comparison.

LLM Guardrails

Runtime input/output filtering for LLMs — PII redaction, toxicity blocking, prompt injection defense, policy enforcement.

LLM Evaluation

Systematic testing of LLM outputs for correctness, relevance, safety, and consistency using automated scorers, rubrics, or human review.

Agent Tracing

End-to-end visibility into multi-step LLM agent runs: tool calls, intermediate reasoning, token usage, latency, and errors at each step.

Audit Logging

Tamper-evident logging of governance events (approvals, model changes, policy decisions) required by EU AI Act Article 12 and similar regulations.

LLM Observability

Logging, tracing, and metrics for LLM applications in production — latency, cost, quality, and error rates across traces and users.

LLM Red Teaming

Automated adversarial testing of LLMs for jailbreaks, prompt injection, and unsafe outputs.

AI Model Inventory

Centralized registry of all AI/ML models in use across the organization, with ownership, lifecycle stage, and risk classification.