Clear guidance and feedback during tasks
What this criterion checks
Evaluates whether the application offers adequate guidance and context during key tasks — including data entry, submissions, navigation, and analytics. Assesses whether placeholders, descriptive texts, labels, and tooltips are easy to understand, whether helpful context is provided before the user performs an action, whether these elements are positioned correctly and logically, whether the system provides progress indicators for lengthy tasks, and whether users can complete all key tasks with the information provided along the way.
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 in-context guidance and checks whether the design reduces burdens on users when precision is required, whether guidance is provided to keep users on the right path, whether contextual tips are offered for relevant tasks, and whether wizards or tooltips are used for contextual guidance. It also checks whether reasonable defaults are provided, whether the system helps users understand what input is expected, whether help and documentation are easy to search, and whether help content lists concrete steps to follow.
How reliable it is
This criterion agrees strongly with expert review, so you can rely on its findings and spot-check as you see fit. See Accuracy & confidence for how the confidence tags are set.