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
"The COO isn’t paying attention to ops silos—COOs focus on longer term strategic enablement beyond today’s operational teams."
Jon Fukuda Jake Burghardt Jose Coronado Natalie Dunbar Denise TillesAll the Ops: Successful cross-functional collaboration
September 10, 2025
"Natalie Dunbar will talk about the convergence of content strategy and design operations and charting a course together."
Alana WashingtonTheme 3 Intro
October 1, 2021
"You’ve got to take control of the backlog and position your team as value-driven, not just servicing individual teams."
Andrew MichaelBuilding a Product Insights Team
March 10, 2022
"I have a tagline my team is tired of hearing: about 50% of work is getting it done and 50% is getting it used."
Nalini P. KotamrajuTwo Jobs in One: Being a “Leader who is a Researcher” and a “Researcher who is a Leader"
March 10, 2021
"We shouldn't let the world of computer science make us forget our own power and what we bring to the table."
Prayag Narula Rida QadriHCI 2.0: Humanity Deserves the Attention that UX Research has to Offer
March 28, 2023
"Rapid low-fidelity prototypes let us get quick feedback without stakeholders focusing on minor visual details."
Yunyan Li Anna Le Jen KimUX Best Practices
June 11, 2021
"Ownership of VOC is a hot potato, so we built a coalition with a facilitator to keep it collaborative and effective."
Shipra KayanHow we Built a VoC (Voice of the Customer) Practice at Upwork from the Ground Up
September 30, 2021
"Just because they have a different opinion doesn’t mean they’re bad people."
Dorelle RabinowitzThe Magic Word is Trust
June 15, 2018
"Please continue to share your thoughts and questions as you’ve been doing over the past few days."
Sarah BrooksTheme 3 Intro
December 10, 2021