Human vs. machine: Testing AI’s ability to synthesize and analyze research
Summary
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
"Community and self-care kept me going when I felt overworked, stressed, or down during my job search."
Corey LongHiring in DesignOps: A Critical Study on How to Hire and Get Hired
September 23, 2024
"I see designers fall back on being the defender of the user like a union boss, but that’s not your only responsibility."
Gretchen AndersonScaling the Human Center
June 8, 2017
"I see this opportunity to imbue these rigid, bureaucratic corporate contexts with humanism to put people at the center of the work."
Lori Muszynski Peter MerholzKeeping Design Weird
October 2, 2023
"I am a technical person, yet I might still need someone who can see to help me use certain sites."
Sam ProulxSUS: A System Unusable for Twenty Percent of the Population
June 9, 2021
"Sometimes you have to completely change your research questions after building relationships with the community."
Prayag Narula Rida QadriHCI 2.0: Humanity Deserves the Attention that UX Research has to Offer
March 28, 2023
"Leading change is like shopping—take time to find the right store before you buy."
Deanna SmithLeading Change with Confidence: Strategies for Optimizing Your Process
September 23, 2024
"Reports aren’t always required; findings can be integrated directly into design docs or the product itself."
Lija HoganDoing more with more: Lessons from the Front Lines of Democratization
March 9, 2022
"With Apple, I could pick up any phone and triple-click the home button and VoiceOver would come on."
Sam ProulxTo Boldly Go: The New Frontiers of Accessibility
March 11, 2022
"A little color purple to start the day. Good morning."
Bria AlexanderOpening Remarks
October 3, 2023
