HAX Design Library

Interactive collection of the 18 Guidelines for Human-AI Interaction, with design patterns for applying them and examples.
Guideline 2

Make clear how well the system can do what it can do

Help the user understand how often the AI system may make mistakes.
Guideline 9

Support efficient correction

Make it easy to edit, refine, or recover when the AI system is wrong.
Guideline 10

Scope services when in doubt

Engage in disambiguation or gracefully degrade the AI system’s services when uncertain about a user’s goals.
Guideline 17

Provide global controls

Allow the user to globally customize what the AI system monitors and how it behaves.