Human vs. machine: Testing AI’s ability to synthesize and analyze research
Summary
Nielsen Norman Group (NNG) has conducted and continues to conduct extensive research testing various large language model (LLM) tools designed for research synthesis and analysis. Our goal was to determine whether these AI-powered tools could meaningfully accelerate the work of experienced UX researchers. Through rigorous testing across multiple models and specialized research tools, we’ve found that while a few tools provide modest speed improvements for experienced researchers, none come close to replacing human expertise in research synthesis and analysis. The core problem is that these tools consistently exhibit critical flaws: they hallucinate findings, fail to identify meaningful patterns in qualitative data, cannot adequately consider nuanced research questions, and produce only superficial, high-level summaries of participant behavior. What makes this particularly dangerous is that these AI-generated outputs often have the veneer of legitimate research results—they look professional and sound plausible. However, closer inspection reveals significant gaps, inaccuracies, and missed insights that would mislead stakeholders and result in poor design decisions. The appearance of competence masks fundamental limitations that make these tools unreliable for serious research work. While we’ve found several places in the research process that can benefit from LLM usage, analysis and synthesis consistently falls short. In this talk, I can share the specific research we’re doing and explain what actually works.
Key Insights
-
•
AI tools frequently produce insight-shaped outputs but often lack the rigor and accuracy of trained human researchers.
-
•
AI moderators cannot currently assess user behavior beyond spoken words, missing key usability observations like failed or inefficient tasks.
-
•
Contextual elements such as environmental interruptions are critical in research but are invisible to AI tools.
-
•
Synthetic users generated by AI tend to produce overly positive, unrealistic feedback that can mislead product teams.
-
•
AI excels at finding semantic connections and grouping codes in large, already coded qualitative datasets quickly.
-
•
Meta-analysis of large repositories using AI can uncover recurring user themes, like change aversion, much faster than manual methods.
-
•
Integrating AI with organizational systems to pull in diverse data sources improves context but requires expert setup and is not yet simple.
-
•
AI’s context window limitations cause it to forget earlier input, affecting the accuracy of multi-turn interactions.
-
•
Even trained researchers must use AI outputs cautiously, vetting insights to maintain research quality.
-
•
Effective user research depends on human synthesis, collaboration, and contextual understanding, areas where AI currently fails.
Notable Quotes
"AI can generate insights, but it does not do them as well as a moderately trained human researcher."
"There is a world of difference between what a participant says and what they actually do, and AI misses that completely."
"AI tells you what you want to hear, which is dangerous if you’re making product decisions based on synthetic feedback."
"Our job as researchers is not making reports or interviewing users; it’s providing actionable, correct insights."
"AI tools are incentivized to produce final deliverables, but that’s an output, not the essence of research."
"AI is pretty good at finding semantic patterns among codes after human researchers have done the initial coding."
"Nobody is going to be satisfied by insight-shaped answers or high-level summaries masquerading as breakthroughs."
"AI cannot notice body language, tone, or environmental context during a research session."
"Using AI to scan large archives of research is a game changer for meta-analyses, even if it’s imperfect."
"Well-set-up AI systems pulling data from multiple company sources will have more context, but it’s still limited compared to human understanding."
Or choose a question:
More Videos
"We have never played together before and never rehearsed, yet we pulled off a great rendition spontaneously."
Jim KalbachJazz Improvisation as a Model for Team Collaboration
November 6, 2017
"You want someone who writes with equal parts empathy and authority, not just pure authority."
Louis RosenfeldCoffee with Lou: Should You Write a (UX) Book?
March 7, 2024
"You don’t have to become a manager or director to advance; becoming a principal IC role is equally influential."
Catt Small Micah Bennett Brian Carr Jessica HarlleeWhat's Next for ICs: Exploring Staff and Principal Designer Roles
February 22, 2024
"Typically we get stuck answering the questions we know we can answer but lose the chance to see the big picture."
Marieke McCloskeyUser Science: Product Analytics & User Research
March 11, 2021
"User recordings are your most valuable asset but have become riskier due to biometric privacy laws."
Llewyn Paine[Demo] Deploying AI doppelgangers to de-identify user research recordings
June 5, 2024
"You don’t want to overdesign just to make something more data interpretable because that can lead you down a dark path."
Joshua NobleCasual Inference
October 6, 2023
"Empathy doesn’t come from reading a report—you don’t get close to users by just reading data."
Sara LogelYour Colleagues are Your Users Too
March 29, 2023
"We'll have a centralized Slack channel for all discussion to come together as one community."
Bria Alexander Louis RosenfeldWelcome
January 8, 2024
"Confidence is a higher burden in retail because people are giving real money; inaccessible flows cause quick abandonment."
Sam ProulxOnline Shopping: Designing an Accessible Experience
June 7, 2023
Latest Books All books
Dig deeper with the Rosenbot
How can storytelling be used to extract deeper insights without being extractive in user research?
How does Rally’s research infrastructure facilitate participant management and integration with enterprise data systems?
What strategies help UX teams translate usability findings into stakeholder-relevant outcomes like cost savings or risk reduction?