40 AI patterns are based on our 200+ real-world examples,
organized across five phases of an interaction journey.
Phase 1
Discovering
How do users discover what AI can do in the first interaction?
Open Suggested prompts
Free
Suggested prompts
Jumpstart user engagement with smart and context-aware preset actions.
41 examples inside
Open Autocomplete
PRO Exclusive
Autocomplete
Anticipating & completing actions without disrupting user's workflow.
6 examples inside
NEW
Start with templates
Pre-built starting points that show users what's possible and accelerate first interactions.
Examples inside
Open Branding
PRO Exclusive
Branding
Using visual identity, icons and signature touches to signal AI's presence and capability.
5 examples inside
Open Proactive suggestions
PRO Exclusive
Proactive suggestions
Invisible AI moments that surprise users with exactly what and when they need.
9 examples inside
Open Search & filter
PRO Exclusive
Search & filter
Moving from clicks to natural language searches and applying filters.
17 examples inside
Open Mode selection
PRO Exclusive
Mode selection
Let users pick the right mode or capability for the task when it matters.
10 examples inside
NEW
Guardrails & permissions
Boundaries, controls, and permissions that show what AI can and cannot do.
Examples inside
Disclaimer
A disclosure shown to users that clarifies AI's involvement, limitations, and sets expectations.
Examples inside
NEW
Smart onboarding
Personalized first-run flows that teach users how to get value quickly from AI.
Examples inside
"For my daily work, conference talks and online courses, it’s invaluable."
🇵🇹Christian Kuhnsince Aug 2025
Head of UX center of competence at Optimizer.pt
Phase 2
Instructing
How does the user instruct the AI and provide context?
Open Voice input
Free
Voice input
Enabling users to interact with their voice, have a conversation or take actions.
13 examples inside
Open Multi-modal input
PRO Exclusive
Multi-modal input
Combined visual, handwriting and gesture inputs as part of the user's expressive toolkit.
20 examples inside
Open Structured input
PRO Exclusive
Structured input
Offer lightweight structure (slots, hints) to compose clearer prompts faster.
9 examples inside
Open Prompting assistance
Free
Prompting assistance
Guiding users to express their intent effectively via suggestions, follow-ups, templates etc.
15 examples inside
Open MCP connectors
PRO Exclusive
MCP connectors
Let AI directly interact with other apps and services to perform tasks.
3 examples inside
Open Knowledge bases
PRO Exclusive
Knowledge bases
Use organizational knowledge (databases, docs, wikis) to specialize responses.
5 examples inside
NEW
Autonomy control
Granular controls over how independently an agent can act on the user's behalf.
Examples inside
NEW
Temporary chat
Ephemeral sessions that don't persist to memory or history, for sensitive or throwaway prompts.
Examples inside
NEW
Scheduling
Schedule AI tasks to run at a future time or on a recurring cadence.
Examples inside
NEW
Agent builder
Tooling for users to compose and configure their own agents from primitives.
Examples inside
"I've gotten a ton of value out of aiverse over the last year. Patterns book was solid!"
🇺🇸Dave Brownsince Feb 2025
Head of AI/ML Product Design at Amazon
Phase 3
Observing
How does the AI respond and in what formats?
Open Streaming + Realtime
Free
Streaming + Realtime
Gradual reveal of AI output and immediate low-latency responses together.
45 examples inside
Open Processing steps
PRO Exclusive
Processing steps
Show progress through distinct steps so users understand what's happening.
24 examples inside
Open Parallel processing
PRO Exclusive
Parallel processing
Run multiple processes / agents concurrently to become architects of processes.
12 examples inside
Open Preview
Free
Preview
The "test-drive" of AI to get a glimpse of results before committing to the process.
9 examples inside
Open Variations
PRO Exclusive
Variations
Presenting multiple alternative outputs for the same input.
15 examples inside
Open Structured output
PRO Exclusive
Structured output
Consistently formatting AI responses into predefined schemas instead of free-form text.
25 examples inside
Open Summary
PRO Exclusive
Summary
Condense long content into concise takeaways or executive summaries, for both agent and human consumption.
12 examples inside
Open Multi-modal output
PRO Exclusive
Multi-modal output
Combine text, images, audio, and video where appropriate for richer responses.
Examples inside
NEW
Agent observability
Visibility into what an agent is doing, why, and at which step — logs, traces, and live state.
Examples inside
Open Confidence
PRO Exclusive
Confidence
Showing how sure the AI is to help users gauge reliability, and understand the basis of the output.
2 examples inside
Open Citations & traceability
PRO Exclusive
Citations & traceability
Showing how the AI constructed the answer (sources, references) to build user's trust.
16 examples inside
"Absolutely love the product and I use it at work to share with coworkers!"
🇺🇸Evangelinesince Jun 2025
Staff UX Designer at Palo Alto Networks
Phase 4
Refining
How does the user edit, review, or improve results?
Open Review actions
Free
Review actions
Allowing users to step through AI-suggested changes and refine them before finalizing.
5 examples inside
Open Visual editing
PRO Exclusive
Visual editing
Enable users to refine visually and continuously, without back-and-forth prompts.
15 examples inside
Open Inline editing
PRO Exclusive
Inline editing
Enabling edits on specific parts of textual content, leveraging existing mental models.
19 examples inside
NEW
Pause & Stop agents
Give users immediate control to pause or stop an agent mid-execution.
Examples inside
NEW
Error states & recovery
Clear error states and recovery paths when an AI flow fails or produces invalid output.
Examples inside
NEW
Evaluation / Testing
Surfaces for evaluating, testing, and comparing AI outputs against expectations.
Examples inside
Phase 5
Adapting
How does the system adapt, remember, and improve over time?
Open Memory
PRO Exclusive
Memory
AI system remembers and recalls user context, or history to support continuity and personalization.
2 examples inside
Personalization
Tailor tone, suggestions, and defaults based on user history and choices.
9 examples inside
"I genuinely found it really helpful while designing in a recent project!"
🇬🇧Manasi Agarwalsince May 2025
Senior Product Designer
Updated weekly with new examples
200+ curated AI interactions
From ChatGPT to Figma AI, explore the best AI UX patterns from leading products.
Join 14,000+ design and product folks