Why AI Is Bad at Research (and how to make it actually useful)
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."
Or choose a question:
More Videos
"You can’t collaborate without communicating upfront and sharing context."
Husani OakleyTheme Two Intro
June 6, 2023
"Men and boys are part of the problem, therefore they must be part of the solution."
Mansi GuptaDrawing from Feminist Practice to Make Inclusive Design Operational
September 9, 2022
"Accessibility is not just one person’s responsibility; it must be distributed through the whole product team."
Sam ProulxDesigning For Screen Readers: Understanding the Mental Models and Techniques of Real Users
December 10, 2021
"I realized that measuring the value of design is an impossible question without context."
Sarah CoyleDesign and Analytics with Sarah Coyle
July 30, 2020
"Users want answers to urgent benefit questions but also opportunities to explore other programs they might qualify for."
Alan Williams Rose DeebDesigning essential financial services for those in need
February 10, 2022
"Design systems are not a straight jacket, they free you from repetitive work to focus on bigger problems."
Dan DonaldDesign Systems as a Vehicle for Systemic Change
June 1, 2023
"If someone doesn’t have that direct lived experience, it’s not just enough to go to the closest thing you can find."
Samuel MartinCo-Design vs Faux-Design: Navigating the Complexities of Sharing Power in Co-Design
March 27, 2026
"Systems and tools who didn't consider accessibility upfront exclude many people and isolate them from the wider world."
Phil HeskethDesigning Accessible Research Workflows
September 29, 2021
"We as people are our data, which means we have to treat data problems with care and consideration."
David ConradThe Feeling of Data
September 14, 2023
Latest Books All books
Dig deeper with the Rosenbot
What strategies help speed up the procurement and legal review of UX research platforms in organizations like LinkedIn?
How should surveys be structured to balance quantitative metrics with qualitative insights?
What strategies help non-researchers build empathy skills to conduct better user interviews?