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
"Empathy sticks with you; if I tell you an inspirational story about what a customer has done, you’ll remember it."
Ross SmithBreaking Barriers with Empathy
June 9, 2017
"Shamus Bern will talk about how to drop into a client site and grok what’s going on quickly without sacrificing why they hired you."
Dan WillisTheme 3: Intro
January 8, 2024
"There's always something to learn from a time study, no matter how mature your design ops team is."
Kristin Sundermeyer Tygre MorehartDesign Ops Metrics
September 30, 2021
"Speculation fills in the gaps where past experience fails us, often seen in hesitation or pauses."
Nicole AleongFuture Orientations to Everyday Life: Futures Anthropology as a Methodology
March 26, 2024
"You can see our organization through the homepage of our site — we each owned a rectangle."
Mark InterranteCollaboration Flows in Product Development
June 9, 2017
"Caring personally isn't about memorizing birthdays or throwing big team offsites; it’s about real conversations and learning what’s important to people."
Etienne FangThe Power of Care: From Human-Centered Research to Humanity-Centered Leadership
March 10, 2021
"Our players are hyperconnected and talking on Discord in real time, which spreads information lightning fast."
Erin Hoffman-JohnThis Game is Never Done: Design Leadership Techniques from the Video Game World
November 6, 2017
"If you ever feel like you can't do this job or you're in over your head, it's totally normal."
Dan WillisEnterprise Storytelling Sessions
June 14, 2018
"Making images and text more legible over complex backgrounds is both a tactical design and accessibility challenge."
Elizabeth ChurchillExploring Cadence: You, Your Team, and Your Enterprise
June 8, 2017
