Passengers navigating busy transit environments often struggle to access timely and reliable information. Stressful conditions and fragmented communication channels create confusion, reduce confidence, and make it difficult for travelers — particularly those with situational or physical limitations — to get the assistance they need.While current systems offer basic notifications, they lack the adaptability, clarity, and real-time responsiveness required to support diverse passenger needs. This gap presented an opportunity to reimagine conversational AI as a more dynamic, accessible, and context-aware travel assistant.
¹ About Us, https://www.rideprt.org/inside-Pittsburgh-Regional-Transit/about-us/
² Deto, Ryan. “Pittsburgh Regional Transit Says Worker Shortages, Other Issues Contributing to Service Cuts.” TribLIVE.com, 29 Oct. 2022
Research
Defining the Problem Space
To build an effective conversational AI for transit, I needed to understand both the emotional and practical challenges passengers face. My research approach combined two methods to capture a complete picture of user needs: Existing System Audit and User Interviews.
Existing System Audit
To understand how current systems are functioning, I systematically evaluated existing transit information platforms, travel apps, and digital touch points. This audit assessed information architecture, interaction patterns, and accessibility features to identify critical gaps in how real-time updates, error states, and multi-modal information delivery are currently handled.
💡 Key Findings
Current platforms overwhelm users with excessive information or fail to provide contextual, timely assistance when passengers need it most. No existing solution offers conversational interaction or adapts communication style to user stress levels.
User Interviews
In order to understand passenger experiences and pain points, I conducted interviews with frequent transit users across different demographics and travel patterns. These conversations revealed emotional states, information-seeking behaviors, and coping mechanisms during moments of high stress and uncertainty throughout their journeys.
💡 Key Findings
Passengers prioritize speed and clarity over detailed information, with stress levels significantly impacting their ability to process complex interactions. Flexible communication modes are essential for different contexts and accessibility needs.
Research revealed a critical gap: while existing systems convey information, they often overlook the emotional and contextual needs of passengers in stressful travel situations. What passengers truly need is adaptive, human-like support that responds to their context and offers reassurance. These insights highlighted a key opportunity to reimagine transit assistance as a more conversational and empathetic experience — leading to the question:
💭 Design Question
How might we design a conversational AI system that streamlines real-time support and improves passenger confidence without adding cognitive burden during travel?
Solution
Making Insight into Action
Building on the research findings and design principles, we developed Ollie as a comprehensive conversational AI assistant that adapts to each user's needs while providing timely, contextual support throughout their journey.
The overall mobile interface includes interactive and conversational components for the passengers to get assistance from Ollie by collaborating with Ollie through conversation, which can be verbal and non-verbal.
Timely
Reminders
Help users to keep track of
activities in their daily routine
Personalized
Recommendations
Optimized recommendations
based on personal preferences
Keep Passengers
Informed
Providing passengers live information for better traveling experience
Flexibility with
Options
Providing list of alternative
options to reach to destinations
Ensures Safety
& Security
Live updates for safe and pleasant
bus ride experience
When redefining Pittsburgh Regional Transit's brand identity, our team tried to envision client's brand identity more in crisp, modern, and intellectual direction. During this process, we kept some brand colors and typography style in similar language while withdrawing some design elements that seemed to unbalance the overall scheme of the brand.
Since we were redesigning the Pittsburgh Regional Transit experience through a voice assistant, it was crucial for our team to also establish non-verbal ways of communication through motion design. While developing the storyboard, we placed particular emphasis on implementing a feature that would allow users to mute Ollie’s voice when needed. We felt this was essential, especially since users would often interact with Ollie in public spaces.
When developing the motion design, our team explored how these motion states could embody Ollie’s personality and enhance the overall user experience. Each state—such as idle, listening, responding, or muted—was carefully applied to communicate subtle emotional cues without relying on voice. Through these animations, Ollie maintained a sense of presence and approachability, allowing users to engage comfortably even in silent or public settings.
Inactivate status pattern at interactive screen
Active status pattern at interactive screen
