Skip to main content
Microsoft
HAX Toolkit
HAX Toolkit
HAX Toolkit
Home
Design Library
Learn the tools
Guidelines
Design Library
Design Patterns
Workbook
Playbook
About
Share ideas
More
All Microsoft
Global
Microsoft Security
Azure
Dynamics 365
Microsoft 365
Microsoft Teams
Windows 365
Tech & innovation
Tech & innovation
Microsoft AI
Azure Space
Mixed reality
Microsoft HoloLens
Microsoft Viva
Quantum computing
Sustainability
Industries
Industries
Education
Automotive
Financial services
Government
Healthcare
Manufacturing
Retail
Partners
Partners
Find a partner
Become a partner
Partner Network
Microsoft Marketplace
Marketplace Rewards
Software development companies
Resources
Resources
Blog
Microsoft Advertising
Developer Center
Documentation
Events
Licensing
Microsoft Learn
Microsoft Research
View Sitemap
Search
Search or ask a question
No results
Cancel
0
Cart
0 items in shopping cart
Sign in
HAX Design Library
Interactive collection of the 18 Guidelines for Human-AI Interaction, with design patterns for applying them and examples.
Guideline 1 > Pattern 1A > Example
D365 Marketing | 1A: Introductory blurb
Guideline 1 > Pattern 1A > Example
Outlook | 1A: Introductory blurb and G17: Provide global controls
Guideline 1 > Pattern 1B > Example
Gmail | 1B: Use explanation (G11) patterns
Guideline 1 > Pattern 1D > Example
M365 Chat | 1D: Make clear what the system can do
Guideline 2 > Pattern 2C > Example
Contoso | 2C: Report system performance information
Guideline 2 > Pattern 2D > Example
Copilot in Outlook | 2D: Provide low performance alerts
Guideline 2 > Example
AI Critiques | G2: Make clear how well the system can do what it can do
Guideline 2 > Example
Copilot in Outlook | G2: Make clear how well the system can do what it can do
Guideline 6 > Example
Android | G6: Mitigate social biases
Guideline 7 > Example
Copilot in Outlook | G7: Support efficient invocation
Guideline 8 > Example
Copilot in Outlook | G8: Support efficient dismissal
Guideline 9 > Pattern 9A > Example
Gmail | 9A: Switch classification decisions
Guideline 9 > Pattern 9B > Example
Copilot in Outlook | 9B: Rich and detailed edits
Guideline 9 > Pattern 9B > Example
Nichesss | 9B: Rich and detailed edits
Guideline 9 > Pattern 9E > Example
Outlook | 9E: Batch-editing data
Guideline 9 > Pattern 9E > Example
Gmail | 9E: Batch-editing data
Guideline 11 > Pattern 11B > Example
D365 Marketing | 11B: Global explanations
Guideline 11 > Pattern 11D > Example
Gmail | 11D: Map system input attributes to system outputs
Guideline 11 > Pattern 11G > Example
Copysmith | 11G: “What if explanations”
Guideline 12 > Example
Outlook – G12: Remember recent interactions
Guideline 15 > Pattern 15D > Example
Contoso | 15D: Use existing public rating or interaction data as feedback for the system
Guideline 16 > Pattern 16A > Example
Outlook | 16A: Feedforward: Convey the consequences of user actions before the user takes action
Guideline 16 > Pattern 16B > Example
Gmail | 16B: Feedback: Convey the consequences of user actions after the user takes action
Guideline 16 > Pattern 16D > Example
Gmail | 16D: Convey the consequences of user action in help and documentation
Guideline 18 > Example
Outlook Web | G18: Notify users about changes