Extracting user research insights from transcripts

Let’s be honest... the sheer volume of noise surrounding Artificial Intelligence right now is exhausting and all over the place. Every tool has a “generate” button, and social media (LinkedIn especially) is full of people proclaiming the end of traditional design jobs.

As a product designer, I initially approached this wave with skepticism. I enjoy designing. I like solving complex problems. I was not looking for a machine to do my job for me.

However, almost two years has passed since those early iterations and ignoring AI is no longer an option. Instead of viewing it as a replacement, I have spent my recent time treating AI as a very fast and somewhat literal-minded supporter. The goal is not to let it design the final product. The goal is to clear the path so I have more time for actual critical thinking.

Here is a look at how I have started integrating these tools into my daily workflow:

AI didn’t change what I design. It changed how I design.

Over the past several months, my design process hasn’t just evolved — it’s been fully restructured. My AI tool stack isn’t something I use occasionally; it is an operational layer embedded into my day-to-day and across discovery, ideation, prototyping, validation, and delivery.

This article outlines how I structure projects using AI models — primarily Claude and ChatGPT — alongside specialized tools such as Figma Make and Amplitude.