A/B Testing with AI

In this webinar we'll use Claude to plan and analyze an A/B test from start to finish. Three analysts will take turns at the keyboard, each with a very different idea of how to work with AI.

Clueless Kayla has a dataset and a dream. She doesn't know a p-value from a pivot table, but she's heard AI can do magic. Her prompt: "Analyze this." Her strategy: hope.

Overconfident Ashley knows exactly what she wants and has no time for questions. She'll ask the AI to do specific things, and some of them are things nobody should ever do to an experiment. Will the AI push back, or will it happily help her shoot herself in the foot?

Methodical Megan asks the right questions, gives clear instructions, and knows what a good analysis should look like. That's the theory, anyway. We'll see whether doing everything right actually pays off.

We haven't scripted the AI's answers. Some may impress us, some may scare us, and at least one will probably make us laugh. Along the way you'll see where AI shines in experimentation, where it quietly goes wrong, and what separates a useful AI-assisted analysis from a confident-sounding mess.

Who it's for: analysts, data scientists, product managers, and anyone curious (or nervous) about letting AI near their experiments.

Your host

• 

  Allon Korem

  Chief Executive Officer

  LinkedIn