We tested Google’s Gemini 2.5 Flash (used in NotebookLM) on qualitative analysis by running the same prompt multiple times.  It improved on GPT-4o and Claude Sonnet 3.5 at quote accuracy but still struggled with relevance and meaning.

NotebookLM is useful, but it’s still just LLMs deep down. There’s no magic technology that makes it immune to the problems of other AI systems.

Seen last week on social media: a market researcher trying to save their job after reporting a nonsense, LLM-generated analysis of survey data. It’s a common mistake, and there’s not much training available for researchers on how to account for differences between generative AI and traditional research tools.

The reality is that many researchers are now expected to use LLM-based tools in their work, despite their shortcomings. And it can be hard to push back on mandates from above, or competition from peers who don’t understand the risks. Are there ways we can integrate LLMs into research while still being responsible professionals about it?

When we use AI tools in product design, strategy, and user research, we need to keep something important in mind: the AI is not “understanding” our requests, and even with safeguards, it may not catch when it’s making mistakes.

Error-checking AI output takes time, so we need to be wary of claims of “time saved” using AI for product research. A thought-provoking quote by Emily M. bender from the March 31 episode of her Mystery AI Hype Theater 3000 podcast underscores this.

Since it launched, I’ve been testing how well gpt-oss-20b does at qualitative research synthesis. I’ve been able to run dozens of giant, 52K-token prompts on my standard-issue MacBook Pro in just a minute or two apiece, and the results have been surprisingly good overall–albeit, with the same egregious errors that we’ve come to expect in LLM citations.

There’s a widely circulated piece of bad advice when it comes to AI: “If you don’t know how to use AI, just ask the AI!” The problem with this advice is that it assumes the AI “knows” about its own functioning. Spoiler alert: it doesn’t! (But it is good at making up plausible sounding answers!)

Researchers should be in the driver's seat when it comes to AI tools, and that means understanding their tradeoffs just like we do with traditional research methods.  My AI for UX Researchers workshop is not about teaching you to use any one specific AI tool–it's about giving you the skills to evaluate the performance of any AI model or service critically.