37 AI patterns are based on our 200+ real-world examples,
organized across five phases of an interaction journey.
Onboarding
Entry touchpoints
Entryways that show users how to begin; search, suggested prompts, open input, icons, proactive nudges, or autocomplete.
6 patterns
Open Proactive suggestions
Free
Proactive suggestions
Invisible AI moments that surprise users with exactly what and when they need.
Open Suggested prompts
Exclusive
Suggested prompts
Jumpstart user engagement with smart and context-aware preset actions.
Open Searching & filtering
Exclusive
Searching & filtering
Moving from clicks to natural language searches and applying filters.
Open Autocomplete
Exclusive
Autocomplete
Anticipating & completing actions without disrupting user's workflow.
Setting expectations
Disclaimer
A disclosure shown to users that clarifies AI’s involvement, limitations, and sets expectations.
Input
Expressive Input
Ways for users to express intent; voice, images, handwriting, gestures, or structured prompts.
5 patterns
Open Voice input
Free
Voice input
Enabling users to interact with their voice, have a conversation or take actions.
Open Handwriting input
Exclusive
Handwriting input
Allowing users to write and receive information in natural handwriting.
Open Visual input
Exclusive
Visual input
Let users attach images, screenshots, or other visuals as part of the input.
Open Gesture input
Exclusive
Gesture input
Using physical gestures (swipes, pinches, circles) as expressive input signals for AI systems.
Open Structured input
Exclusive
Structured input
Offer lightweight structure (slots, hints) to compose clearer prompts faster.
Expanding context
Additional signals that enrich the request; prompt help, model choice, connectors, or knowledge sources.
4 patterns
Open Prompt assistance
Exclusive
Prompt assistance
Guiding users to express their intent effectively via suggestions, follow-ups, templates etc.
Expanding context
Model selection
Let users pick the right model or mode for the task when it matters.
Expanding context
MCP connectors
Connect to tools and data sources so AI can act with relevant information.
Expanding context
Knowledge bases & Integration
Use organizational knowledge (databases, docs, wikis) to specialize responses.
Output
Types of outputs
Different ways responses are delivered; previews, video, images, audio, summaries, or structured formats.
8 patterns
Open Preview output
Exclusive
Preview output
The "test-drive" of AI to get a glimpse of results before committing to the process.
Types of outputs
Video output
Generate or assemble video for dynamic explanations and demos.
Types of outputs
Image output
Return images or generated visuals as the primary output form.
Types of outputs
Audio output
Speak results aloud for accessibility and hands-free use.
Types of outputs
Multi-modal output
Combine text, images, audio, and video where appropriate for richer responses.
Types of outputs
Summary
Condense long content into concise takeaways or executive summaries.
Open Structured output
Exclusive
Structured output
Consistently formatting AI responses into predefined schemas instead of free-form text.
Processing
How the system handles generation; real-time, streaming, parallel work, or stepwise updates.
4 patterns
Open Parallel processing
Exclusive
Parallel processing
Run mutliple processes / agents concurrently to become architects of processes.
Open Streaming
Exclusive
Streaming
Gradual reveal of AI output, showing the progress instead of waiting blindly.
Processing
Processing steps
Show progress through distinct steps so users understand what’s happening.
Explainability
Help users understand answers and recover gracefully when things go wrong.
2 patterns
Open Confidence indicators
Exclusive
Confidence indicators
Showing how sure the AI is to help users gauge reliability, and understand the basis of the output.
Open Citations
Exclusive
Citations
Showing how the AI constructed the answer (sources, references) to build user's trust.
Refinement
Correction & Iteration
Tools for revising outputs — continue, retry, act inline, edit visually, or review results.
5 patterns
Open Inline actions
Exclusive
Inline actions
Enabling edits on specific parts of textual content, leveraging existing mental models.
Open Visual editing
Exclusive
Visual editing
Enable users to refine visually and continuously, without back-and-forth prompts.
Correction & Iteration
Reply
Continue the conversation to refine results with follow-up instructions.
Correction & Iteration
Regenerate
Request a fresh attempt with the same or tweaked prompt.
Open Review
Exclusive
Review
Allowing users to step through AI-suggested changes and refine them before finalizing.
Learning
Managing memory
The system recalls, persists, or forgets context to support continuity and control.
1 pattern
Open Managing memory
Exclusive
Managing memory
AI system remembers and recalls user context, or history to support continuity and personalization.
Collecting feedback
Collect feedback to improve outputs and personalize future interactions.
1 pattern
Collecting feedback
Collecting feedback
Capturing quick sentiment on results to steer quality.
Personalization
Adjust behavior, tone, and defaults to fit the individual user.
1 pattern
Personalization
Personalization
Tailor tone, suggestions, and defaults based on user history and choices.
Insights in your inbox, monthly
Stay ahead of the curve
for designers and product teams in the new AI paradigm.
