Analyze Experiments with PostHog AI

PostHog AI creates Experiments and analyzes their results. You can set up A/B tests, check statistical significance, and ask what the data means – all through natural language.

How it works

When you ask PostHog AI to create an Experiment, it sets up the Experiment with your specified split percentages and goal metrics, creates the feature flag with the right variants, and configures targeting rules if you specify a user segment.

For existing Experiments, PostHog AI can summarize results, interpret statistical significance, and explain what the data means in plain language.

Analyze results with PostHog AI

PostHog AI doesn't just show you the numbers, it interprets them. When you ask about Experiment results, it tells you:

Which variant is winning and by how much
Whether the result is statistically significant based on the confidence intervals
What to do next – whether to ship, extend, or stop the Experiment

You can also start a summary from the Experiment itself: on the results page, click the spark button next to the Primary metrics header. It opens PostHog AI with your Experiment's results ready to summarize. The button appears once your Experiment is running and has results.

Try it

Select a prompt to try it out in the PostHog app:

Tips for better results

Name your goal metric – "with conversion on purchase_completed" helps PostHog AI configure the right success metric
Specify split percentages – "70/30 split" or "equal split across three variants" tells PostHog AI exactly how to allocate traffic
Ask about significance – "Is this result statistically significant?" prompts PostHog AI to interpret the confidence intervals
Ask for recommendations – "Should I ship this?" prompts PostHog AI to weigh the evidence and suggest next steps

Get started

To start analyzing Experiments with PostHog AI, set up PostHog AI.