HAX Design Library

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

Guideline 9

Guideline 9

Support efficient correction

Make it easy to edit, refine, or recover when the AI system is wrong.
Guideline 9 > Pattern 9A

Pattern 9A: Switch classification decisions
Guideline 9 > Pattern 9A > Example

Gmail | 9A: Switch classification decisions

card example thumbnail
Guideline 9 > Pattern 9B

Pattern 9B: Rich and detailed edits
Guideline 9 > Pattern 9C

Pattern 9C: Undo automated actions
Guideline 9 > Pattern 9C > Example

Bing Search | 9C: Undo automated actions

card example thumbnail
Guideline 9 > Pattern 9D

Pattern 9D: Do G9 through G15
Guideline 9 > Pattern 9D > Example

Instagram | 9D: Do G9 through G15

card example thumbnail
Guideline 9 > Pattern 9E

Pattern 9E: Batch-editing data
Guideline 9 > Pattern 9E > Example

Outlook | 9E: Batch-editing data

card example thumbnail
Guideline 9 > Pattern 9E > Example

Gmail | 9E: Batch-editing data

card example thumbnail

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 11B

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

Instagram | 11B: Global explanations

card example thumbnail
Guideline 11 > Pattern 11C

Pattern 11C: Present properties of system outputs
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 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 15A > Example

Instagram | 15A: Encourage explicit feedback on individual system outputs

card example thumbnail
Guideline 15 > Pattern 15A > Example

Google Search | 15A: Encourage explicit feedback on individual system outputs

card example thumbnail
Guideline 15 > Pattern 15B

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

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

Twitter | 15C: Reporting inappropriate content

card example thumbnail
Guideline 15 > Pattern 15C > Example

Instagram | 15C: Reporting inappropriate content

card example thumbnail
Guideline 15 > Pattern 15D

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

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

card example thumbnail
Guideline 15 > Pattern 15D > Example

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

card example thumbnail