Get started – free
  • Home
  • Self-driving product
  • Context warehouse
  • Pricing
  • Docs
  • Demo
  • Talk to a human
  • Why PostHog?
  • Changelog
  • Company handbook
  • Store
  • Careers
  • Trash
  • Home
  • Self-driving product
  • Context warehouse
  • Pricing
  • Docs
  • Demo
  • Talk to a human
  • Why PostHog?
  • Changelog
  • Company handbook
  • Store
  • Careers
  • Trash
Experiments
Overview
Getting started
Start here
Installation
Creating an experiment
Adding your code
Testing and launching
Analyzing results
Managing lifecycle
No-code experimentsBeta
Concepts
Traffic allocation
Exposures
Metrics
Running time
Bayesian statistics
Frequentist statistics
CUPED
Holdouts
Guides
A/B testing promptsBeta
Tracking long-term metrics
Changing distribution after rollout
Experiments without Feature Flags
New user experiments
A/A testing
A/B/n testing
Holdout testing
Redirect testing
Fake door test
LLM A/B tests
Data Warehouse experimentsBeta
Tutorials and framework guides
PostHog AI
Analyze experiments with PostHog AI
Create experiments with MCP
Resources
Best practices
Troubleshooting
Changelog

Getting started

Experiments

Test different variations of your product and measure the impact.

Roll out your first experiment

Questions? Ask PostHog AI.

It's easier than reading through 1762 pages of documentation.

Resources

Real-world use cases to get you started

  • Guide

    Running experiments on new users

    Test changes to signup and onboarding flows

  • Guide

    Run A/B tests in Webflow

    A guide to low-code experimentation

  • Guide

    Run experiments without feature flags

    Useful if you don't use PostHog feature flags

Explore guides
Visit the manual

Community questions