HAX Design Library

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

Guideline 10

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 10 > Pattern 10A

Pattern 10A: Disambiguate before acting
Guideline 10 > Pattern 10B

Pattern 10B: Avoid cold starts by eliciting user preferences
Guideline 10 > Pattern 10C

Pattern 10C: Fall back to other strategies

Guideline 11

Guideline 11

Make clear why the system did what it did

Enable the user to access an explanation of why the AI system behaved as it did.
Guideline 11 > Pattern 11A

Pattern 11A: Local explanations
Guideline 11 > Pattern 11A > Example

InterpretML | 11A: Local explanations

card example thumbnail
Guideline 11 > Pattern 11B

Pattern 11B: Global explanations
Guideline 11 > Pattern 11B > Example

InterpretML | 11B: Global explanations

card example thumbnail
Guideline 11 > Pattern 11C

Pattern 11C: Present properties of system outputs
Guideline 11 > Pattern 11C > Example

Google Maps | 11C: Present properties of system outputs

card example thumbnail
Guideline 11 > Pattern 11D

Pattern 11D: Map system input attributes to system outputs
Guideline 11 > Pattern 11E

Pattern 11E: Map user behaviors to system outputs
Guideline 11 > Pattern 11F

Pattern 11F: Example-based explanations
Guideline 11 > Pattern 11G

Pattern 11G: “What if?” explanations
Guideline 11 > Pattern 11G > Example

NerdWallet | 11G: “What if?” explanations

card example thumbnail

Guideline 13

Guideline 13

Learn from user behavior

Personalize the user’s experience by learning from their actions over time.
Guideline 13 > Example

Office Search | G13: Learn from user behavior

card example thumbnail

Guideline 15

Guideline 15

Encourage granular feedback

Enable the user to provide feedback indicating their preferences during regular interaction with the AI system.
Guideline 15 > Pattern 15A

Pattern 15A: Encourage explicit feedback on individual system outputs
Guideline 15 > Pattern 15B

Pattern 15B: Request explicit feedback on selected system outputs
Guideline 15 > Pattern 15B > Example

Google Maps | 15B: Request explicit feedback on selected system outputs

card example thumbnail
Guideline 15 > Pattern 15C

Pattern 15C: Reporting inappropriate content
Guideline 15 > Pattern 15D

Pattern 15D: Use existing public rating or interaction data as feedback for the system

Guideline 17

Guideline 17

Provide global controls

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