AI meets human insight: UX research at Consumer Reports

How do you design digital products that people actually want? Get UX tips and insights from experts behind some of the most successful digital transformations and experiences in the world. Listen to our Insights Unlocked podcast and learn firsthand from some of the most notable names and brands in experience research. Click here to listen and subscribe on your favorite streaming platform.

Artificial intelligence is revolutionizing industries, but at Consumer Reports, senior UX researcher Melissa Garber believes it’s research—not AI—that should continue to take the lead in shaping consumer experiences.

In this Insights Unlocked episode, Melissa shared how her team at Consumer Reports has been developing an AI-powered conversational agent to help consumers make better decisions. Her conversation with Brent Leary was recorded at The Human Insights Summit in October.?

Unlike traditional AI implementations, Melissa said, their approach is deeply rooted in user research.

“We're not just using AI for the sake of it,” she said. “We’re applying research to understand what consumers actually need, so AI can provide answers that are relevant, accurate, and easy to digest.”

Get the guide to building AI features that truly meet customer needs - download now!

The team has built a retrieval-augmented generation (RAG) framework, leveraging 90 years of Consumer Reports’ consumer research data to ensure AI responses are backed by trusted insights. However, Melissa warns that AI isn’t a one-size-fits-all solution. One major challenge? Users don’t always know what to ask.

“A lot of people struggle with search queries. They don’t know the right terms or how to phrase their question,” she said. “That’s why anticipating user intent is crucial—so AI can provide useful suggestions and guide them to the right information.”

“AI doesn’t reason—it recognizes patterns. That’s why human insight is still crucial.” — Melissa Garber

To maintain accuracy and brand trust, Consumer Reports employs a human-in-the-loop approach, where in-house experts with decades of experience fact-check the AI.

AI still hallucinates, even when it’s using Consumer Report’s own data, Melissa said.

"Even when you're using your own data, it still hallucinates,” she said. “That's why we have something at CR that we call human in the loop to make sure we are maintaining our brand integrity and the trust that we've built over almost 90 years."

Despite the challenges, Melissa sees AI as an opportunity to empower consumers rather than replace human expertise. “At the end of the day, AI should help people be the superheroes of their own lives.”

Listen to the full episode to hear more of their conversation.

How do you see AI impacting UX research? Should research guide how we implement AI? Share your perspectives in the comments.