A list of problems is not a plan. This prompt turns research into IA pain points that each carry a description, the evidence behind them, how often and how badly they bite, a root cause, and a category: findability, navigation, labeling, content gaps, or search. The categories do real work. They tell you which problems are secretly the same problem, and six complaints that all sort into labeling are one naming decision rather than six tickets.
Give it whatever business context you have, because severity is not a property of the problem alone, a rare failure on a signup path can outrank a frequent annoyance somewhere quiet. The root-cause column is where to be most skeptical. Models are fluent at producing plausible causes, and a stated cause is only worth as much as the evidence sitting next to it. "People can't find pricing because the label is unclear" and "because pricing is three levels deep" call for different fixes, and your research either distinguishes them or it does not. Where it does not, the honest output is that you need another round.
Prioritising pain points is where research turns into an IA decision. Categorising them first is what stops you fixing the same problem five times.
Fill in your own details below; the prompt updates as you type. When it's ready, copy it into Claude or whatever AI tool you use.
Casts the AI as: You're a UX researcher synthesizing user pain points from research data.
Names 6 specific outputs to produce, so the response comes back structured rather than a general summary.
Research sources, User type, Current IA and Business context tell the AI what your specific situation is, not a generic one.
Prioritized pain point matrix with recommendations