Log in or create a free Rosenverse account to watch this video.
Log in Create free account100s of community videos are available to free members. Conference talks are generally available to Gold members.
AI-Assisted Qualitative Analysis: What to Automate and What to Own
Summary
Qualitative analysis is about more than summarizing common trends in your data. It’s about prioritizing and explaining what’s important, and that requires getting familiar with your data and thinking hard about what you're seeing. AI can support that process, but it can also short-circuit the thinking you need to do if you're not careful. In this session, we'll look at what qualitative analysis actually involves, where AI genuinely helps, and where skipping the process costs you. You'll come away with a practical sense of how to use AI as an accelerant and thought partner while maintaining control of the work.
Key Insights
-
•
Qualitative analysis involves moving beyond patterns to generating meaningful explanations and insights.
-
•
AI works best when humans fully understand the research process and guide AI step-by-step.
-
•
Structured data can be heavily automated by AI, reducing manual coding efforts.
-
•
Messy, rich qualitative data requires strong human oversight and involvement to capture unexpected insights.
-
•
Humans bring subjective intuition and surprise to analysis, which AI currently cannot replicate.
-
•
Keeping humans in the loop means supervising major decisions, reviewing AI outputs, and continually refining codes.
-
•
The thematic analysis process benefits from breaking work into discrete steps for AI to perform under human supervision.
-
•
Cognitive offloading risks dulling critical qualitative research skills if AI is overused.
-
•
Adversarial AI agents can be employed to challenge and verify AI-generated findings before human review.
-
•
AI tools can assist in report writing by handling repetitive tasks like tallying but struggle to replicate human narrative tone and excitement.
Notable Quotes
"If you don't understand the process, you're not going to get very far with using AI for analysis."
"AI is a tool. It can be as powerful as the person who is wielding that tool."
"Qualitative analysis isn’t just to call out patterns but to explain why they’re there and make them meaningful for your audience."
"Automate the hell out of structured data, but stay involved in messy, rich data."
"Think of AI as an extra colleague: it does the first pass, you do the second pass."
"Coding is more important than the output; it forces you to be familiar with and think deeply about your data."
"Use AI to remove boring, menial tasks but preserve the manual, difficult hard work for yourself."
"Slowing down on messy data is worth it because you could miss something incredibly important that changes the trajectory of the product."
"Adversarial verification with a second AI agent trying to poke holes in findings mimics how human researchers challenge each other."
"AI doesn’t feel surprise or curiosity, but humans do, and that’s a unique strength in analysis."
Or choose a question:
More Videos
"Starting your accessibility efforts on mobile makes the process simpler and easier to reuse when expanding to other platforms."
Sam ProulxMobile Accessibility and You
June 9, 2022
"Please take advantage of this opportunity to share, ask questions, and learn together even if you are the most introverted person."
Uday Gajendar Louis RosenfeldDay 2 Welcome
June 5, 2024
"It’s easier to sell if the team is talking about the tool — popularity inside counts."
Eric ShumakeAn AMA on UX's Role in Healthcare
April 22, 2026
"The biggest challenge I see is scaling without losing our humanity."
Bud Caddell Kristin Skinner Alana WashingtonDesignOps Community Sensing Session
May 13, 2021
"It’s not the tech, it’s the people — awareness, access, and trust are the real barriers to heat pump adoption."
Sara ConklinExit Interview: 20 Years of Tech, One Very Big Bet, and a Lot of Heat Pumps
April 10, 2026
"Lack of confidence caused by unlabeled or difficult controls often leads assistive tech users to give up on purchases."
Sam ProulxOnline Shopping: Designing an Accessible Experience
March 28, 2023
"We created a family by interacting with each other and sharing our problems with work and trying to solve them together."
Holly ColeUnderstanding Experiences: When you have to do more than work
November 8, 2018
"Arnstein’s ladder reduces participation to delegating decision-making power, ignoring goals like safety, well-being, and satisfaction."
Sarah FathallahA Typology of Participation in Participatory Research
March 28, 2023
"Snow clearing policies choose to clear roads before pavements, deeply ignoring responsibilities that are likely to fall on women."
Mansi GuptaDrawing from Feminist Practice to Make Inclusive Design Operational
September 9, 2022
