Can We Trust AI to Moderate UX Interviews?

Back to Devoured - August 07, 2026

DEVOURED

Can We Trust AI to Moderate UX Interviews?

Design airesearch MeasuringU

Research suggests AI excels at structured job interviews but continues to struggle with the nuance required for open-ended, semi-structured UX research.

What: Studies from 2025 and 2026 indicate that while AI can effectively handle structured interview tasks, organizations like NN/Group emphasize that AI fails to replicate the real-time judgment and interpretive depth needed for UX interviewing.

Why it matters: This underscores the distinction between data-gathering tasks suited for LLMs and deep qualitative analysis that remains dependent on human intuition.

Decoder

UX (User Experience) research: The process of investigating user needs and behaviors through qualitative methods, such as interviews, to inform product design.
NN/Group (Nielsen Norman Group): A prominent UX research and consulting firm known for establishing industry standards in usability.

Original article

A three-year-old prediction about AI replacing UX moderators is revisited, as AI now handles interactive interviewing beyond simple comment coding, prompting 419 researchers to sign opposition letters. A 2025 Philippines study of over 70,000 job applicants found AI-interviewed candidates were more likely to be offered, start, and remain employed, though humans still made hiring decisions for structured, closed questions. Anthropic's December 2025 study of 80,000 users found AI interviews elicited surprisingly candid disclosures, but NN/Group's research suggests AI still falls short for semi-structured, open-ended UX interviews requiring real-time judgment.

Explore all 49 articles in today's digest