Rosenverse

Why AI Is Bad at Research (and how to make it actually useful)

Gold
Tuesday, March 10, 2026 • Advancing Research 2026
Share the love for this talk
Why AI Is Bad at Research (and how to make it actually useful)
Speakers: Daniel Korczynski
Link:

Summary

LLMs are everywhere, but when it comes to real research, they often fall short. Generic LLMs weren’t built for continuous research workflows, and product researchers quickly see the problem: the outputs are generic, lack full context, and struggle to connect multiple data sources. Instead of surfacing meaningful insights, they can amplify noise. In this session, Daniel will break down why AI often fails research teams and what’s missing. He’ll show how to make AI actually useful for continuous product research. Accelerating analysis, connecting insights across sources, and keeping researchers at the center, equipped with a powerful tool rather than replaced by one.

Key Insights

  • AI in research struggles with large datasets, often averaging results and missing subtle but important signals.

  • Curating and filtering datasets by removing irrelevant data improves AI research output quality.

  • Scoping research into focused projects or topics helps AI deliver more precise responses.

  • Asking one question at a time significantly enhances the quality of AI-generated answers.

  • Providing detailed contextual information (personas, company background, product details) to AI boosts specificity and nuance in responses.

  • AI hallucinations and trust issues necessitate human-in-the-loop processes to verify output quality and citations.

  • Iterative refinement of AI outputs, similar to app development, is critical for achieving polished research results.

  • Spot checking AI-generated citations can be an effective and efficient way to validate research quality.

  • Context passed as embedded knowledge rather than repeated in prompts yields better AI results.

  • Using multiple specialized AI agents to critique each other’s outputs can mitigate bias and improve research accuracy.

Notable Quotes

"AI has this strange weakness that when working with a large dataset, they often miss crucial, subtle findings."

"The larger the dataset you work with, the more costly it is to run a single operation on AI models."

"Whenever possible, you should be breaking down your work into specific research projects or topics."

"When you ask a question, try to ask one at a time so the model doesn't get lost."

"Context is everything — providing AI with a folder of your company’s knowledge makes responses more detailed and useful."

"Research with AI requires as much iteration and verification as building an app or prototype."

"AI-generated research reports should always be tied to real feedback that you can verify behind every sentence."

"There's no way to deny it: every industry needs to adapt to AI, but nobody really knows how yet."

"Human in the loop means constantly interacting with AI, documenting your thoughts and assuring quality."

"Some engineers build a council of agents that debate and generate responses, which can help with bias and accuracy."

Ask the Rosenbot
Aiyana Bodi
Three Key Climate Initiatives and How You Can Help
2024 • Climate UX Interest Group
Louis Rosenfeld
GenAI for UXers: A Rosenbot Demo and Discussion
2025 • DesignOps Summit 2025
Gold
Kaitlin Tasker
Fast and Fearless Inclusive Research
2023 • Advancing Research 2023
Gold
Rebecca Topps
Planning and conducting remote usability studies for accessibility
2020 • Advancing Research Community
Louis Rosenfeld
Coffee with Lou
2024 • Rosenfeld Community
Sol Mesz
Hands or Brains? How to Hire for Strategy, Strategically
2024 • Enterprise Experience 2020
Gold
Samuel Proulx
Designing for Disability, Innovating for Everyone
2025 • Advancing Research 2025
Gold
Sara Asche Anderson
Not Your Ordinary Re-Brand: Design's Path to Driving Customer Obsession at Best Buy
2024 • Enterprise Experience 2020
Gold
Chris Geison
Theme Two Intro
2023 • Advancing Research 2023
Gold
Etienne Fang
The Power of Care: From Human-Centered Research to Humanity-Centered Leadership
2021 • Advancing Research 2021
Gold
Ryan Rumsey
Business Influence Without Losing Your Soul
2021 • Enterprise Community
Daniel Gloyd
Designing From the Inside Out: How Method Acting Can Inspire Design Research
2026 • Rosenfeld Community
Nalini Kotamraju
Research After UX
2024 • Advancing Research 2024
Gold
Lavy Kumar
Future of Work
2021 • Design at Scale 2021
Gold
Joerg Beringer
Scaling User Research with AI: Continuous Discovery of User Needs in Minutes
2025 • Designing with AI 2025
Gold
Aditi Ruiz
A PM State of Mind: Empathy Mapping Your Product Manager, Pt. 1
2022 • Design in Product 2022
Gold

More Videos

Husani Oakley

"You can’t collaborate without communicating upfront and sharing context."

Husani Oakley

Theme Two Intro

June 6, 2023

Mansi Gupta

"Men and boys are part of the problem, therefore they must be part of the solution."

Mansi Gupta

Drawing from Feminist Practice to Make Inclusive Design Operational

September 9, 2022

Sam Proulx

"Accessibility is not just one person’s responsibility; it must be distributed through the whole product team."

Sam Proulx

Designing For Screen Readers: Understanding the Mental Models and Techniques of Real Users

December 10, 2021

Sarah Coyle

"I realized that measuring the value of design is an impossible question without context."

Sarah Coyle

Design and Analytics with Sarah Coyle

July 30, 2020

Alan Williams

"Users want answers to urgent benefit questions but also opportunities to explore other programs they might qualify for."

Alan Williams Rose Deeb

Designing essential financial services for those in need

February 10, 2022

Dan Donald

"Design systems are not a straight jacket, they free you from repetitive work to focus on bigger problems."

Dan Donald

Design Systems as a Vehicle for Systemic Change

June 1, 2023

Samuel Martin

"If someone doesn’t have that direct lived experience, it’s not just enough to go to the closest thing you can find."

Samuel Martin

Co-Design vs Faux-Design: Navigating the Complexities of Sharing Power in Co-Design

March 27, 2026

Phil Hesketh

"Systems and tools who didn't consider accessibility upfront exclude many people and isolate them from the wider world."

Phil Hesketh

Designing Accessible Research Workflows

September 29, 2021

David Conrad

"We as people are our data, which means we have to treat data problems with care and consideration."

David Conrad

The Feeling of Data

September 14, 2023