Card sorting is a foundational research method for understanding how people mentally organize information. You create a set of cards, usually 30 to 100, each representing a content object, then ask participants to work with them to reveal their mental model of how that content should be structured and labeled. Sessions typically involve 6 to 12 participants, individually or in small groups of 3 to 5, and participants should think aloud so you understand the reasoning behind their choices, not just the outcome.
Open card sorting is the most common generative method: participants group the cards however feels natural to them, without predefined categories, then label the groups they've created themselves. This reveals both how people naturally group content and what terminology they'd use for the categories. Modified-Delphi card sorting, devised by Celeste Lyn Paul, takes a different approach: rather than each participant sorting independently, a seed participant creates an initial sort, and each subsequent participant refines that same evolving sort in turn, until the group reaches consensus. Because it produces a single structural model instead of many individual ones to reconcile: it's often more reliable and simpler to analyze, but it takes longer per session, since participants work sequentially rather than in parallel.
Open card sorting shows you many individual mental models you then have to reconcile. Modified-Delphi trades that reconciliation work for a slower, more deliberate path to one shared model.
Open card sorting with multiple individual employees is the stronger choice here. The team doesn't yet know how a broad, unfamiliar employee base naturally thinks about this content: that's precisely the discovery open card sorting is built for. Running it with multiple participants in parallel also fits the tight timeline far better: independent sessions can happen simultaneously, while modified-Delphi's sequential, one-at-a-time refinement process takes meaningfully longer per session.
Choosing open card sorting means giving up the single, ready-to-use consensus model that modified-Delphi would have produced directly. Open sorts from 10 different employees will likely produce 10 different groupings and sets of labels, which the team will then need to reconcile, normalizing similar labels, looking for common patterns, before they have one structural model to act on. That reconciliation work is real, but it's a reasonable trade for discovering the actual diversity of employee mental models across departments, something a single modified-Delphi group session, run with only a handful of people, would be less likely to surface.Modified-Delphi would have been the better choice if the team already had a rough structural hypothesis and needed a small, representative group to refine it into one coherent model efficiently, but that's not the situation described here, where the team is still discovering how employees think in the first place.
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 specializing in card sorting analysis and information architecture.
Names 5 specific outputs to produce, so the response comes back structured rather than a general summary.
Domain, Current IA and Research question tell the AI what your specific situation is, not a generic one.
Structured analysis with actionable recommendations
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 category labels from user research data.
Names 5 specific outputs to produce, so the response comes back structured rather than a general summary.
Domain, Audience, Existing terminology and Brand voice tell the AI what your specific situation is, not a generic one.
Label recommendations with supporting data