6 reviews, and what each one hands back.
Each page shows the input we ran, the answer that came back, what gets better, and what the tool cannot do. Where a real run is on file, the answer is the unedited output.
critique_experience
Find the problems in a design before a user or an engineer does, ranked by how badly each one hurts.
Findings marked critical, warning or note, each with the evidence behind it (observed or inferred) and the smallest fix, then a ship-or-not summary.
See a real run for critique_experiencegenerate_state_matrix
List every state a feature can be in, including the ones nobody drew.
States grouped by dimension (data, permission, billing, outside services and more), plus a list of likely gaps tagged as stated or inferred.
What it does for generate_state_matrixmap_journey
Map the stages around a goal and name the entries, exits and interruptions the flow forgot.
Ordered stages for the objective, the ways people arrive that the flow ignores, the ways they leave, and how interruptions are handled.
What it does for map_journeyaudit_copy
Review buttons, errors, empty states, confirmations and notifications, and rewrite the ones that fail.
Each string that has a real problem, the reason it fails, and a replacement. Strings that already work come back untouched.
See a real run for audit_copyfind_assumptions
Pull the unchecked beliefs out of a brief and turn each into a question you could answer this week.
Assumptions ranked by risk, each paired with a research question.
What it does for find_assumptionscheck_terminology
Find one concept that goes by several names across your UI, docs and API.
Concept clusters showing which source uses which term, with the drifting ones flagged.
What it does for check_terminology