Why AI Is Bad at Research (and how to make it actually useful)
Summary
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."
Or choose a question:
More Videos
"A design system team often has to wear multiple hats—diplomat, facilitator, architect, community manager—to keep momentum."
Nina JurcicThe Design System Rollercoaster: From Enabler and Bottleneck to Catalyst for Change
October 3, 2023
"It can be hard for designers to immediately understand or advocate for the real value of design at deeper technical layers."
Stefanie OwensOptimizing for Outcomes: Transformation Design in Systems at Scale
December 4, 2024
"Discernment requires attunement to organizational culture and politics to understand how research will resonate."
Sarah Fathallah Alba VillamilBeyond insights: Rethinking the role of researchers as stewards of organizational wisdom
March 13, 2025
"The future was already here. It’s just not evenly distributed."
Daniel J. RosenbergDesigning with and for Artificial Intelligence
August 11, 2022
"Time is the only resource we cannot replenish. Make sure you don’t spend it doing what’s not meaningful."
Anna Avrekh Dr. John Pagonis Klara Pelcl Sina SchreiberExpert Panel: Leading in and with Research
March 10, 2022
"We need to get better at betting new products will stand on their own sooner rather than later."
Jess GrecoCreating a Basis for Change: Scaling Design Maturity
June 8, 2022
"Non-researchers work 12 hours a day and they don’t want to work 12 and a half hours a day."
Trisha TerharEmpathizing with the Empowered: Non-Researcher Responses to Democratization
March 10, 2022
"Less than a third of respondents feel like they work somewhere with a clear investment in customer-driven decision making."
Marieke McCloskeyUser Science: Product Analytics & User Research
March 11, 2021
"Understanding the lifecycle of AI code is essential because AI is essentially code running in constant evolution."
Aras BilgenWho does the math: A designer’s journey in building an AI-based tutoring app
June 10, 2025
