Rosenverse
Why AI Is Bad at Research (and how to make it actually useful)
Conference ticket
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
Sean Dolan
A Practical Look at Creating More Usable Enterprise Customer Journeys
2019 • Enterprise Community
Melissa Tsang
From Insights to Action: Driving Business Values through DesignOps
2024 • DesignOps Summit 2020
Gold
Dane DeSutter
What co-speech gestures reveal about users’ thinking during interviews
2023 • Rosenfeld Community
Sam Proulx
Accessibility: An Opportunity to Innovate
2022 • Civic Design 2022
Gold
Alla Weinberg
People Are Sick of Change: Psychological Safety is the Cure
2023 • DesignOps Community
Rachael Dietkus, LCSW
Everything You Need to Know about the Civic Design 2022 Call for Presentations
2022 • Civic Design Community
Adam Cutler
Discussion
2016 • Enterprise UX 2016
Gold
Bria Alexander
Reflect and Chart Forward
2021 • Civic Design 2021
Gold
Saara Kamppari-Miller
DesignOps for Inclusive Design and Accessibility
2022 • DesignOps Community
Bria Alexander
Opening Remarks Day 1
2024 • Advancing Research 2024
Gold
Robin Beers
How to create actionable insight in the face of politics and silos [Advancing Research Community Workshop Series]
2023 • Advancing Research Community
Sean McKay
Coexisting with non-researchers: Practical strategies for a democratized research future
2025 • Advancing Research 2025
Gold
Uday Gajendar
Day 2 Welcome
2024 • Designing with AI 2024
Gold
Megan Blocker
Day 2 Theme Panel
2025 • Advancing Research 2025
Gold
Craig Villamor
Resilient Enterprise Design
2017 • Enterprise Experience 2017
Gold
Helen Armstrong
Augment the Human. Interrogate the System.
2023 • Enterprise UX 2023
Gold

More Videos

Milan Guenther

"When we showed the Iceland Ministry of Foreign Affairs their portfolio, the Foreign Minister said, we have to pivot our innovation investments to early-stage catalytic innovations."

Milan Guenther Benjamin Kumpf

The $212 billion ‘so what?’: unlocking impact in development cooperation

November 20, 2025

Alnie Figueroa

"Build a program management community of practice so you can formalize partnerships and solve process delivery issues together."

Alnie Figueroa

Teamwork: Strategies for Effective Collaboration with Other Program Management Teams

September 8, 2022

Saara Kamppari-Miller

"Adoption is the only thing that matters in innovation. If you’re not changing behavior, you haven’t innovated."

Saara Kamppari-Miller Nicole Bergstrom Shashi Jain

Key Metrics: Comparing Three Letter Acronym Metrics That Include the Word “Key”

November 13, 2024

Christian Crumlish

"This is a topic near and dear to my heart and I feel really long overdue conversation."

Christian Crumlish

Introduction by our Conference Chair

December 6, 2022

Helen Armstrong

"Working with AI is a lot less like working with another human and more like working with some weird force of nature."

Helen Armstrong

Augment the Human. Interrogate the System.

June 7, 2023

Verónica Urzúa

"The Silicon Valley dream is a problematic ideology that normalizes what the correct research looks like and excludes others."

Verónica Urzúa Jorge Montiel

The B-side of the Research Impact

March 12, 2021

Yoel Sumitro

"Designers adhere to standards not scientific ones, but design rigor tailored to dealing with complexity."

Yoel Sumitro

Actions and Reflections: Bridging the Skills Gap among Researchers

March 9, 2022

Jim Kalbach

"Each first take was the only take, which got pressed on the album."

Jim Kalbach

Jazz Improvisation as a Model for Team Collaboration

June 4, 2019

Bud Caddell

"I see design ops as deeply linked to how internal operations influence what our customers experience."

Bud Caddell Kristin Skinner Alana Washington

DesignOps Community Sensing Session

May 13, 2021