Contextual AI System
Led the shift from prompt-first AI to contextual assistance—embedding proactive insights and actions in Meetings and Contacts and scaling reusable AI patterns across four experiences.
Role
Staff Product Designer (AI Team)
Team
AI team: 5 engineers, 1 PM, and myself; partnered with Design Systems, Meetings, and Contacts.
Opportunity
AI required too much initiation.
Research from AI Chat showed that many high-value needs were predictable from the context users were already in. Requiring people to open Chat and formulate a prompt turned obvious next steps into extra work.
Strategy
Put intelligence where the context already exists
I mapped the highest-value AI needs to Meetings and Contacts, where Calendly already had the context required to anticipate them. The interaction model was simple: surface what matters proactively, then give users a clear path to go deeper or act.
AI Design System
Creating a scalable interaction language for AI
As AI expanded across Calendly, teams were creating different visual treatments and interaction patterns. I partnered with Design Systems to define a reusable AI state within existing components so new experiences felt recognizable, consistent, and faster to build.
1)
Defining a recognizable AI state
I evolved Calendly's existing blue-purple AI palette with coral, creating a distinct signal for AI-generated content and actions while keeping the experience native to the product.
2)
Extending the existing component system
Rather than creating a separate component model for AI, I worked with Design Systems to extend existing patterns with a standardized AI state. This kept AI recognizable while preserving the structure and behavior users already understood.
3)
Standardizing AI interactions across all components
I applied the same visual language across reusable banners, buttons, prompts, suggestion cards, and Notetaker controls so teams could build new AI experiences from a consistent set of patterns.
Updated Experience
Connecting insights to follow-up actions
The updated experience brought together personalized starting points, contextual recommendations, suggested follow-ups, interactive Calendly objects, and core actions within the assistant.
Upcoming Meeting
Past Meeting
Contact Detail
Impact
Scaling contextual AI across Calendly
The result of this work was a consistent system for AI components, that was implemented across 4 experiences. The contextual AI workflows created a 75% reduction in navigation for our target user’s core workflows.
3
Foundational AI design system
Standardized gradients, banners, buttons, and other components into one system.
4
AI experiences using the system
Scaled a consistent visual and interaction language across four AI experiences.
75%
Less manual navigation for core workflows
Reduced core workflows from 4 clicks to one contextual action.
Meetings and Contacts experiences launched in late August 2026 - metrics are not yet available.