Skip to content
Log in

User Research Synthesis

Turns a pile of interviews into patterns with evidence, keeping the disconfirming cases rather than smoothing them away.

0

Share this prompt

Free — no card needed

Create a free account

to open User Research Synthesis — and the other 364 prompts across 21 categories.

We store your email address to send these. We never sell it or pass it to advertisers. Withdraw at any time. Privacy Policy.

Already have an account?

CategoryResearchForAnalysts, Designers, FoundersTested onClaudeChatGPTGemini

Running it, start to finish

  1. Write down what you believed before reading the notes.
  2. Look hardest at the disconfirming cases and the unprompted topics.
  3. Act on problems rather than on requests.

What you get back

The output this produces, every time.

  • Separates what people did from what they said they would do, which have very different reliability.
  • Keeps the disconfirming cases, which usually reveal a second segment.
  • Highlights what came up unprompted, which is the strongest signal in a research set.

Getting better results

Where this usually goes wrong, and how to avoid it.

  • State your hypotheses upfront. Section 4 is the return on the research, and it only works if you wrote down what you believed before reading the notes.
  • Do not merge the outliers. The participants who did not fit are frequently a distinct segment, and finding that is worth more than confirming the main pattern.
  • Design against problems, not requests. Section 5 matters because a request is the user's own fix for a problem they may have diagnosed wrongly.

More Research prompts

All Research

Written for The AI University. Every prompt in this library is original work — authored, tested and revised here, not collected from elsewhere. 365 of them, free with an account.