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
"The Shakers patented clever affordances like chair buttons that let you rock without damaging wooden floors."
Daniel GloydWarming the User Experience: Lessons from America's first and most radical human-centered designers
May 9, 2024
"Data is power; find your eigen metric, the one or two things that prove your hypothesis."
Aletheia DelivreNew Shapes and Emerging Identities for Design Ops
September 11, 2025
"Women are more likely to die in car crashes because crash test dummies are not designed with women in mind."
Dr. Jamika D. Burge Mansi GuptaAdvancing the Inclusion of Womxn in Research Practices
September 15, 2022
"Everything’s changing really quickly—if you don’t revise your plan in a few months, you’re building for a world that’s already outdated."
Peter Van DijckDesigning AI-first products on top of a rapidly evolving technology
June 10, 2025
"Cluster analysis is very useful if you want to avoid a one-size-fits-all approach to product or service design."
Ricardo MartinsUnlocking the power of advanced quantitative methods
March 12, 2025
"We turned all of these files in boxes into an Excel file, and then into a shared Google Doc accessible to multiple people."
Emily Danielson“I mean, I can lift a shovel”: Design Skills in Disaster Response
June 9, 2022
"We are on our third and final day of Advancing Research 2023."
Bria AlexanderOpening Remarks
March 29, 2023
"Sometimes the loudest voices dominate, but asynchronous collaboration helps give quieter voices a chance to speak."
Jerome “Axle” BrownHow to Use Self-Directed Learning to Ensure Your Research Insights are Heard and Acted Upon
March 11, 2021
"Principles at this level act like a company mission that product teams can translate into their own more specific design principles."
Sarah WilliamsA Framework for CX Transformation
June 11, 2021
Latest Books All books
Dig deeper with the Rosenbot
How does systems thinking help identify leverage points for improving rural maternal health?
How did the concept and language of 'jobs' emerge alongside industrialization and corporate labor structures?
How can measuring team behaviors instead of just results improve trust and performance in design ops?