The reports page helps you interpret experiment metrics using 

, a unique approach to statistics for the digital age developed in conjunction with leading researchers at Stanford University. Stats Engine embeds innovations combining sequential testing and false discovery rate control to deliver 

 making decisions based on real-time data.\

Run a multi-armed bandit optimization

Analyze results

ai_cta

ai_identity

ai_chat

ai_product


Data set that refers to a person or a role and contains at least one address via which the person or role can receive messages.

recipient

Tag events

feature-experimentation-docs

Feature Experimentation docs

Get started with Optimizely Feature Experimentation

Core concepts of Feature Experimentation

Custom Flags Dashboard

Handle user IDs in Feature Experimentation

Get started

Configure Feature Experimentation for Opal

Optimizely Opal Chat for Experimentation

Optimizely Opal

Manage flags

Flag statuses in Feature Experimentation

Flag variations and flag variables overview

Idea builder for Optimizely Experimentation

Create flag variables

Create flag variations

Target audiences in Feature Experimentation

Define user attributes to build audiences in Feature Experimentation

Create advanced audience combinations in Feature Experimentation

Build Feature Experimentation audiences in ODP

Manage scheduled changes in Feature Experimentation

Build flags

Run Feature Rollouts in Feature Experimentation

Manage rules

Flag and rule lifecycle management

Interactions between flag rules

A/B tests in Feature Experimentation overview

Run A/B tests in Feature Experimentation

Flag delivery (targeted delivery) overview

Run flag deliveries (targeted delivery)

Deploy a winning variation

Run a beta in Feature Experimentation

Run a multi-armed bandit optimization in Feature Experimentation

Configure flag rules

Manage events in Feature Experimentation

Choose metrics in Feature Experimentation

Manage events and metrics

Choose QA tests for Feature Experimentation

Allowlist for Feature Experimentation

Use a QA audience in Feature Experimentation

Two- and three-stage testing in Feature Experimentation

Launch and test your experiments

Granular roles and permissions

Custom fields in Feature Experimentation

Manage collaborators in Feature Experimentation

Manage projects in Feature Experimentation

Manage environments in Feature Experimentation

Project and account configuration

New A/B Results page

Warehouse-Native Experimentation Analytics

Data freshness

Optimizely Experiment Results page

Analyze results in Feature Experimentation

Segment your results in Optimizely Feature Experimentation

Export events in Feature Experimentation

What are impressions and decisions in Feature Experimentation

Measure and analyze results

Feature Experimentation FAQs

Change approvals in Feature Experimentation

Change history in Feature Experimentation

Mutually exclusive experiments in Feature Experimentation

Global holdouts

Local holdouts

Governance and strategy

Migrate existing experiment results

Upgrade to Optimizely Feature Experimentation from Optimizely Full Stack

Migrate legacy A/B test

Migrate legacy feature

Migrate legacy feature test

Migrate legacy targeted rollout

Migration considerations for the Contentful integration

Upgrade to Feature Experimentation from Full Stack

Open the developer console

Locate IDs for use with the Experimentation APIs

Slack notifications

Tools and utilities

End user docs

Introduction

Release notes

Optimizely Feature Experimentation - application and migration

Quickstarts

Core concepts

Optimizely Feature Experimentation

Create feature flags

Handle user IDs

Target audiences

Track user events

Create flags

Run A/B tests

QA and troubleshoot

Use mutual exclusion

Run Contextual Multi-Armed Bandit optimizations

Run flag rules

Manage config (datafile)

Scheduled changes

Notification listeners

Collaborators

Manage projects

Manage environments

Flag dependency

Change approvals

Change approval webhooks

Configure

Implementation checklist

Event tracking

IDE plug-ins

Microservices

Multiple SDK implementations

Mutually exclusive experiments

Two- and three-stage testing

Fetch datafiles

Self-service global holdout

Native global holdouts

Best Practice

Integrate real-time audiences for Feature Experimentation

Configure the Optimizely CMS (SaaS) integration

Integrate Optimizely Products

Configure analytics platforms

Configure Amplitude

Configure Contentful

Configure Datadog

Configure Google Analytics 4 (GA4)

Configure Localytics

Configure Mixpanel

Configure mParticle

Configure Segment

Configure Tealium

Next.js starter kit

Solid.js starter kit

Vue.js starter kit

Integrate other platforms

Content Delivery Networks and Optimizely Feature Experimentation

Get started experimenting at the edge

Akamai EdgeWorkers

AWS Lambda@Edge

Cloudflare Workers

Fastly Compute@Edge

Vercel Functions

Feature Experimentation edge workers and agents

Optimizely Feature Experimentation at the edge

Optimizely Agent

Quickstart for Agent

Install Optimizely Agent

Use Optimizely Agent

Configure Optimizely Agent

Agent API Reference

Agent GitHub Repository

Deploy as a Microservice

Deployment guide for Cloudflare Workers

Optimizely Edge Agent

Feature Experimentation API Reference

REST API

Index

SDK compatibility matrix

Android SDK

C# SDK

Flutter SDK

Go SDK

Java SDK

JavaScript SDK v6+

JavaScript (Browser) SDK prior to v6

JavaScript (Node) SDK prior to v6

PHP SDK

Python SDK

React SDK v4+

React SDK prior to v4

React Native SDK v4+

React Native SDK prior to v4

Ruby SDK

Swift SDK

SDK Reference Guides

Developer docs