Labels and content are clear and self-explanatory
What this criterion checks
Evaluates whether labels and content throughout the application are easy to understand without prior context or experience. Assesses navigation menus, main content area text, headings, button labels, lists, menus, and icons for intuitiveness and clarity. Also evaluates whether icons accurately match their corresponding text labels, whether error messages are clear and actionable, and whether all feedback provided by the system can be understood by the average user.
How it's assessed
The agent navigates through the application following realistic user journeys, capturing screenshots at each step. Using AI-powered vision analysis, it evaluates labels and content for self-explanatory clarity and checks whether labels and navigation provide enough information scent, whether technical terms appear without explanation, whether system-oriented terms are used instead of the user's natural language, and whether jargon or overly complex language is used without clarification. It also checks whether different words are used for the same concept, whether error messages use plain language, whether help content is written from the user's perspective, and whether icons include labels that make their meaning clear.
How reliable it is
This criterion is still building up testing data, so confirm its findings as you review. See Accuracy & confidence for how the confidence tags are set.