What do you wish you knew about AI-moderated interviews?

If you could get an inside look at how AI-moderated interviews work under the hood, what would you want to know?

A lot of AI research companies today are pushing “AI moderation,” where an LLM questions your participants directly.  The promise is exciting: the depth of interviews, at the scale of surveys.

But how well does AI moderation actually work?

It’s difficult to find unbiased answers. I did a review of the AI moderation training available for UX practitioners, and what I found was disappointing:

• 🛠️ Most of it (unsurprisingly) came from the tool companies themselves.

• 🦜 And the rest came from AI consultants parroting those same companies’ marketing claims.

There actually are academic and empirical studies that challenge these claims, but you have to do a lot more digging to find them.

So, I’ve decided to offer new training on AI moderation.

This will follow up on my previous behind-the-scenes workshops on AI synthesis and AI agents, with the specific goals of:

• 🔎 Showing how AI moderation tools actually work at the level of models and prompts; and

• 📊 Sharing the latest (unsponsored) empirical findings on their strengths and weaknesses for UXR.

If this sounds like something you’d be interested in, I’d love to hear from you!