For AI agents: visit https://docs.arthur.ai/llms.txt for an index of all pages formatted in Markdown and endpoints in OpenAPI.

Jump to Content

Home Guides Recipes API Reference Changelog

v1.0

Guides

v1.0Home Guides Recipes API Reference Changelog

Getting Started

What Is Arthur AI?
Quickstart: Evaluate Your First LLM Call
Connect Your Application
Authentication
Self-Host the Arthur Engine
User & Organization Management

Instrument

Traces Overview
Data Connectors

Observe

Observe & Dashboard
Prompts
Transforms
Datasets
Default Metrics
Metrics Overview & Data Model
Metrics Versioning
Dashboard
Alerts & Alert Rules
Webhooks & Notifications

Evaluate

LLM Evaluators
Continuous Evals
RAG
Datasets (Engine)

Deploy & Test

Policies & Governance
Agent Discovery
Agent Tool Kit Settings
Agentic Test

Enterprise

Groups, Roles & Permissions
SSO & Identity Provider Setup

Integrations

Integrations Overview
Arthur + OpenAI
Arthur + LangChain
Arthur + Anthropic SDK
Arthur + LiteLLM
Arthur + Mastra
Arthur + CrewAI
Arthur + LlamaIndex
Arthur + OpenAI Agents SDK
Arthur + Google ADK
Arthur + AWS Bedrock
Arthur + Claude Code
Claude Code Skill (/arthur-onboard)
Truefoundry

🚀 Getting Started - Platform Overview

Get Started with Arthur Platform

🖥️ Platform Basics

How to Sign in and Access Arthur?
How to Add New Users to Arthur?
How to Add New Project to Arthur?
How to Use Tables?
Terminology

🚀 Evals Engine

Quickstart
Evals Engine Overview
Engine Creation and Deployment
- Deployment with AWS
- Deployment with Kubernetes

⚡Agent Development

Deployment Guide for Arthur GenAI Engine
Create Task
Configure Model Provider
Observability
- Get Started with Tracing
- Traces
Prompts
RAG Experiments and RAG Notebooks
Get Started With LLM Evals
- Evals Management
Get Started With Continuous Evals
Offline Evaluation Guide: Creating a Dataset
Get Started With Transforms
Agentic Experiments and Agentic Notebooks
API Keys Management

📊 Metrics

Customize Your Dashboard
- How to Set Up and Track Metrics by Version
Metrics & Querying Overview
Custom Metrics
- Classification Metrics Overview
GenAI Metrics
Agentic Metrics Quickstart
- Getting Started with Monitoring CrewAI Agents

🛡️ Guardrails

Guardrails Configuration Guide

🛠️ Administration & Settings

How do groups work in Arthur?
- How to create a group?
- How to add user or assignment to the group?
Roles in Arthur
- Platform Roles
  - Role Limitations and Examples
- Evals Engine Roles
What's the difference between an organization or project?
Authorization in Arthur: How Access Control Works

🪝 Webhooks

What are Webhooks?
How Do Webhooks Work in Arthur?
How to integrate Slack via Webhooks?
How to integrate Jira via Webhooks?

🚨 Alerts

Creating Alert Rules

⚡ API & SDK

API Documentation
Using the Python SDK

🔌 Arthur Connectors

Supported Connectors

🏢 Enterprise

OIDC Configuration Requirements
Model Access & Credentials
Infrastructure Access & Network Requirements
Documentation Overview
- Document Creation Best Practices
- Content Retrieval Management
Integrations
- Google Drive Integration
- Google Programmable Search Engine (PSE) Integration
SAML Integration via Keycloak
- Google Workspace Setup for OpenWebUI
- Okta Setup for OpenWebUI

☁️ Google Cloud Deployment

High Level Architecture
- Naming Nomenclature
Google Cloud Services Utilization
DevOps: CI/CD
Logging and Monitoring Setup

Powered by

Agentic Metrics Quickstart

Crew AI

Get started using Arthur agentic tracing with Crew AI Agents.

Updated 6 months ago

Getting Started with Monitoring CrewAI Agents