# Reference - [Administration](https://docs.fiddler.ai/reference/settings.md): Dive into our guide to application settings in Fiddler. Learn to use the settings page to manage team setup, permissions, and credentials. - [AWS VPC Endpoint Setup](https://docs.fiddler.ai/reference/settings/aws-vpc-endpoint-setup.md): Automated script to create AWS VPC endpoints for secure communication with Fiddler Cloud using AWS Virtual PrivateLink. - [AWS Virtual PrivateLink Setup](https://docs.fiddler.ai/reference/settings/aws-vpl-setup.md): Step-by-step guide to configure AWS Virtual PrivateLink for secure communication between your AWS VPC and Fiddler Cloud. - [Supported Browsers](https://docs.fiddler.ai/reference/settings/supported-browsers.md): Discover our product guide on supported web browsers for accessing Fiddler, including Google Chrome, Firefox, Safari, and Microsoft Edge. - [LLM Gateway](https://docs.fiddler.ai/reference/settings/llm-gateway.md): Configure LLM provider credentials to enable AI-powered features in Fiddler using your own API keys from OpenAI, Anthropic, Gemini, and other providers. - [Access Control](https://docs.fiddler.ai/reference/access-control.md): Explore our guides on authentication options with leading IDPs like Okta and Ping. Dive deep into authorization topics using the Fiddler UI. - [Authentication Management](https://docs.fiddler.ai/reference/access-control/authn-authentication-management-console.md) - [Email Login](https://docs.fiddler.ai/reference/access-control/email-login.md): This page documents the details of Fiddler's native email-based authentication including user account creation and password policy. - [SSO Authentication Guide](https://docs.fiddler.ai/reference/access-control/sso-authentication-guide.md): Configure Single Sign-On authentication for Fiddler with Okta, Azure AD, Google, Ping, and others. Complete setup guide with troubleshooting tips. - [Google SSO](https://docs.fiddler.ai/reference/access-control/google-integration.md): Learn how to configure Fiddler with Google for seamless Single Sign-On (SSO) authentication. - [Microsoft Entra ID OIDC](https://docs.fiddler.ai/reference/access-control/single-sign-on-with-azure-ad.md): Learn to integrate Fiddler and Microsoft Entra ID, formerly known as Azure AD, for seamless Single Sign-On (SS0). - [Okta Integration](https://docs.fiddler.ai/reference/access-control/okta-integration.md): Learn how to configure Fiddler with Okta for seamless Single Sign-On (SSO) authentication. - [Okta SAML](https://docs.fiddler.ai/reference/access-control/okta-integration-saml.md): Learn how to configure Fiddler with Okta using SAML for seamless Single Sign-On (SSO) authentication. - [Ping Identity SAML](https://docs.fiddler.ai/reference/access-control/ping-identity-saml.md): Learn how to configure Fiddler with Ping for seamless Single Sign-On (SSO) authentication. - [Role-Based Access Control](https://docs.fiddler.ai/reference/access-control/role-based-access.md): Learn how Fiddler uses role-based access control with resources and roles. Discover how to manage access with resources, roles, and permissions in your company. - [Mapping IdP Groups to Teams](https://docs.fiddler.ai/reference/access-control/mapping-ad-groups-to-fiddler-teams.md): This document describes the naming convention and rules for mapping internal AD groups to Fiddler Teams automatically. - [Feature Maturity Definitions](https://docs.fiddler.ai/reference/feature-maturity-definitions.md): Review Fiddler's release and support policies for product features at different stages of maturity. - [ML Metrics Reference](https://docs.fiddler.ai/reference/ml-metrics-reference.md): Complete reference of all built-in ML metrics supported by the Fiddler monitoring platform, organized by category and model task type. - [LLM Observability Metrics Reference](https://docs.fiddler.ai/reference/llm-observability-metrics.md): Complete reference of all LLM observability metrics and enrichments supported by the Fiddler monitoring platform. - [Glossary](https://docs.fiddler.ai/reference/glossary.md): Review product concepts and terminology for the Fiddler platform to help get up to speed quickly when adopting Fiddler for your ML and GenAI monitoring. - [Agentic Observability](https://docs.fiddler.ai/reference/glossary/agentic-observability.md): Comprehensive monitoring, tracing, and analysis of AI agent systems that provides hierarchical visibility into agent reasoning, coordination, and decision-making across distributed multi-agent applica - [Baseline](https://docs.fiddler.ai/reference/glossary/baseline.md): Reference datasets in Fiddler that serve as comparison points for detecting data drift, evaluating model performance, and identifying when production data deviates from expected patterns. - [Custom Metric](https://docs.fiddler.ai/reference/glossary/custom-metrics.md): User-defined calculations in Fiddler that extend monitoring beyond standard metrics, allowing teams to track business-specific KPIs and specialized measurements for their AI applications. - [Data Drift](https://docs.fiddler.ai/reference/glossary/data-drift.md): The statistical change in data distributions over time that can impact model performance. Fiddler detects drift by comparing production data against baselines to identify degradation causes. - [Embedding Visualization](https://docs.fiddler.ai/reference/glossary/embedding-visualization.md): Interactive visualizations in Fiddler AI that transform complex embedding vectors into 3D displays, revealing semantic patterns, clusters, and outliers in LLM data. - [Enrichment](https://docs.fiddler.ai/reference/glossary/enrichment.md): Comprehensive overview of enrichments in AI monitoring and evaluation. Learn how Fiddler's enrichment framework transforms raw LLM data into actionable insights through specialized metrics and custom - [Experiments](https://docs.fiddler.ai/reference/glossary/experiments.md): Systematic assessment of LLM application quality through structured testing with datasets, evaluators, and experiments that enable data-driven decision-making for prompt optimization, model selection, - [Fiddler Guardrails](https://docs.fiddler.ai/reference/glossary/guardrails.md): Explore the Fiddler's administrative features and settings available to Org Admins. - [Fiddler Centor Models](https://docs.fiddler.ai/reference/glossary/centor-models.md): Purpose-built LLMs that evaluate AI outputs in real time, powering both monitoring metrics and real-time guardrails with significantly lower latency than general-purpose models. - [LLM Observability](https://docs.fiddler.ai/reference/glossary/llm-observability.md): Comprehensive monitoring of LLM applications that evaluates safety, quality, and performance metrics to detect issues like hallucinations, toxicity, and drift in generative AI systems. - [Metric](https://docs.fiddler.ai/reference/glossary/metric.md): Metrics in Fiddler AI are quantitative measurements that evaluate model behavior, data quality, and performance over time, enabling proactive monitoring and issue detection. - [Model Drift](https://docs.fiddler.ai/reference/glossary/model-drift.md): Changes in model performance over time due to shifting data patterns, concept evolution, or system degradation. Fiddler detects and diagnoses model drift to maintain AI reliability. - [Model Performance](https://docs.fiddler.ai/reference/glossary/model-performance.md): "Quantitative evaluation of AI model accuracy and effectiveness in production. Fiddler tracks performance metrics over time to detect degradation and identify opportunities for improvement. - [ML Observability](https://docs.fiddler.ai/reference/glossary/ml-observability.md): A comprehensive approach to monitoring AI systems that goes beyond performance metrics to provide insights into model behavior, data quality, and root causes of issues throughout the ML lifecycle. - [Trust Score](https://docs.fiddler.ai/reference/glossary/trust-score.md): Quantitative scores generated by Fiddler's enrichment processes that measure LLM output quality and safety. These numerical metrics enable monitoring, alerting, and real-time decision-making for AI go --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.fiddler.ai/reference.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.