Ollie
Design a conversational AI assistant for Pittsburgh Regional Transit (PRT)
Project Type
Studio project collaborated with Pittsburgh Regional Transit (PRT)
Team
Yuehui Du (Designer)
Iris Cai (Designer)
Angela Nam (Designer)
Aishwarya Rane (Designer)
Contribution
Value Creation
UI/UX Design
User Research
Motion Design
Prototyping
Timeline
5 Weeks
Sep. - Nov. 2022
Tools
Vioce Flow
Figma
Illustrator
After Effects
Premier Pro
Overview
Context
PRT is Pittsburgh's the prominent local public transit system.
PRT provides 60 million rides a year, and the majority of people that inside and outside the Pittsburgh would use it as daily transit service.
Who are the users?
We pinpointed three primary user groups for the conversational AI: daily commuter, passengers needing accessibility support, and bus drivers, who look for efficient communication and accurate updating information.
Daily Commuter
who relies on apps to sync bus schedules with routine, aiming to optimize transit and gain recognition.
Bus Driver
who aims to complete ride on time, communicate real-time updates, and assist passengers efficiently.
Disable Passenger
who seeks smooth access and support to enjoy safe, independent ride without feeling like a burden.
Challenge
Passengers rely on multiple platforms but are still unable to communicate with driver and system in real-time to address their needs.
Passengers have multiple resources to check real-time bus information like Transit, Google Map, PRT Ready2Ride, digital bus stop, this overwhelmed experience does not provide accurate information and makes the communication inefficient.
Solution
Real-time communicate on mobile
We prioritize the mobile experience, recognizing it as the most accessible device during transportation rides. Ollie consistently provides pertinent information whenever needed.
Integrate Ollie on the bus stop kiosk
We identified a chance to repurpose the interactive screen already installed at the bus stop. The multiple touchpoint broadens access to Ollie's assistance, facilitating a more convenient transit experience for all users.
Research
Interview
What do we want to investigate from the user interview?
Goal 01
Understand typical ride process (pre-, during, post-) for target users.
Goal 02
Identify main painpoints in communication between users and the system.
Goal 03
Prioritize target users' needs in different scenarios.
Daily Commuter A
"Bus drivers arrive and depart on their own time. Don’t count on the set schedule...It’s hard to know when is correct to get to the bus stop."
Daily Commuter B
"Late night buses are really terrible. The app says they are coming but didn’t show up at all. It’s ruined my night..."
Disable Passenger C
"While usually the driver will prepare the ramp, I'm still worried what if the bus is full or the driver doesn't see me in advance and waste time for other passengers."
Synthesis
Frequent "silent" communication between passengers and the driver
Throughout the journey, passengers signal their need for the driver's real-time service indirectly—by waving a hand, pulling the string, or standing by the exit. The driver responds through actions. This communication relies entirely on unspoken rules.
Service reliability is the primary concern for both passengers and the PRT
Through affinity mapping, 60% interview feedback mentioned service reliability, including timing, misinformation, and safety. PRT set the annual KPI including "on-time performance". The passengers and the PRT have a common sense on the importance of reliability.
Findings
Three major communication painpoints between users and the system
01
Immediate requests increase uncertainty.
Passengers check bus schedule immediately before departure, which leave no room for emergency preparedness.
02
Lack of real-time updates from the driver on-site.
The system hardly get on-site information without driver’s report, neither do passengers.
03
Accessibility support requests can't reach in advance.
Driver can only be noticed the ramp request when actually seeing the disable passenger,
Prioritize target users in different scenarios
The mobile and kiosk platforms are adapted for various user types. By prioritizing target users, the design can more effectively address their specific needs.
Ideation
Hypothesis of AI
How does conversational AI enhance the communication experience?
For build a consistent visual system for PRT, we learned from the brand identity and create Ollie's visual system to align with its core value.
Define Identity
From the PRT brand identity to Ollie's visual system
For build a consistent visual system for PRT, we learned from the brand identity and create Ollie's visual system to align with its core value.
Define Ollie's personailty
Defining Ollie's identity by considering the traits and tone that best align with the project's objectives and the client's core values. We concluded that characteristics would suit best:
Storyboard
Explore scenarios about the conversation between users and Ollie
For build a consistent visual system for PRT, we learned from the brand identity and create Ollie's visual system to align with its core value.
Define Kiosk
Determine the digital bus stop as the secondary touchpoint
During the field research, we found PRT initially aimed to install interactive screens, but budget constraints have led to the use of posters with QR codes instead. We see this as a strategic opportunity to implement PRT's vision.
Interface Structure
Explore the structure for key features on mobile and kiosk
Design
Visualize Ollie
Visualize Ollie by rapid iterations
Focusing on embodying public transportation attributes and PRT's mission in a singular visual form. This iterative process involved considerable refinement until we settled on Ollie's definitive visual representation.
Ollie's Motion Status
We identified essential statuses for conversational feedback, focusing on smooth transitions and infusing shapes with easy-understanding movements and transformations.
Final Design
Painpoint 01
Immediate requests increase uncertainty
Solution 01
Pre-schedule &
real-time update notification
Painpoint 02
Lack of real-time updates from diver on-site
Solution 02
Driver provides quick updates via verbal communication
Painpoint 03
Accessibility support requests can't reach in advance
Solution 03
Hands-free request services and notify the driver ahead
Kiosk Feature 01
Personalized ride recommendation
Kiosk Feature 02
Cross-platform information synchronization
Kiosk Feature 03
Real-time notification broadcasting
Scenario 01. Daily commuter schedules a ride
Scenario 02. Driver updates bus status to passengers at the next stop
Scenario 03. Disable passenger requests support to the incoming driver
Scenario 04. Passenger asks for a ride from kiosk and export to the mobile
Scenario 05. Kiosk broadcasts bus updates to the passengers waiting in line
Reflection
What I've learned?
Emerging technologies are not the answer, user's needs are.
Focusing on embodying public transportation attributes and PRT's mission in a singular visual form. This iterative process involved considerable refinement until we settled on Ollie's definitive visual representation.
Next steps
Emerging technologies are not the answer, user's needs are.
Focusing on embodying public transportation attributes and PRT's mission in a singular visual form. This iterative process involved considerable refinement until we settled on Ollie's definitive visual representation.
Interaction through Mobile
We prioritize the mobile experience, recognizing it as the most accessible device during transportation rides. The interface boasts interactive and conversational elements, enabling passengers to seamlessly interact with Ollie for assistance. Features include shortcuts for primary functions, typing for searches, and natural language interaction for queries. Ollie consistently provides pertinent information and recommendations whenever needed.
Interaction through Kiosk
During our contextual inquiry, we identified a chance to repurpose the interactive screen already installed at the bus stop. We developed an interactive kiosk featuring Ollie's capabilities, enhancing the user experience beyond the mobile interface. This broadens access to Ollie's assistance, facilitating a more convenient transit experience for all users.
Concept Video with Key Scenarios
Challenge
Why leveraging conversational AI to an every-day experience of riding a bus?
Goal
How might we…
create an intuitive, inclusive, and reliable conversational AI that enhances the public transportation experience
Understand Client
Why Pittsburgh Regional Transit (PRT)?
As the most used local public transportation in Pittsburgh, designing for PRT includes an opportunity space that conversational AI can step in to ease the process and shape a richer user experience. The potential opportunities are listed below:
Prominent Public Transportation
PRT is the most used local public transportation in Pittsburgh, providing 60 million rides a year, and the majority of people that inside and outside the city would use its daily service.
Variety of Users & Multifaceted Requirements
PRT serves a wide array of passengers, each with unique needs, seeking various forms of support from the service. It's essential to provide detailed information that caters to every aspect of the journey.
Complex & Comprehensive Information
There are diverse types of users using PRT and request multiple support from the service. The comprehensive information related to every step during the ride is needed.
Understanding the Brand
We started by deep understanding the brand identity and visual system of PRT. We looked into client's brand identity and core values to align with their vision and goal to serve for the public: providing safe, reliable, and accessible public transportation throughout the community.
Auditing Existing PRT App
Ready2Ride, the mobile app developed by PRT, is designed to bring website information directly to users' smartphones, offering key features such as ticket purchasing, bus schedule checking, and accessibility support. However, the app is still under development and faces challenges with fragmented information, leading many passengers to opt for alternative solutions like the Transit app for their transportation tracking needs.
Secondary Touchpoint Opportunity
During our field research, we identified the bus stop as a significant secondary touchpoint for users. Although PRT initially aimed to install interactive screens, budget constraints have led to the use of posters with QR codes instead. We see this as a strategic opportunity to implement our client's vision.
User Research
Understand and Learn from the Everyday Users
Findings: Identify User's Painpoints from User Research
Through meticulous user research, we delved deeply into the experiences of our users, uncovering their core challenges and needs. By employing a variety of methods, including shadowing observation, interviews, and stakeholder synthesis, we gained valuable insights into the daily interactions passengers have with our services. Some pain points as key digests from interview are shown below:
Bus drivers arrive and depart on their own time. Don’t count on the set schedule...It’s hard to know when is correct to get to the bus stop.
Inefficient Communication
Why is it so difficult to find a place to buy a bus pass? I even don’t know when it was expired and it turned really chaotic when I got on bus to renew it.
Complicated Fare Purchase Process
Late night buses are really terrible. The app says they are coming but didn’t show up at all. It’s ruined my night...
Unreliable Service Reporting
Stakeholder Map
We created a stakeholder map to pinpoint the essential participants within the PRT service ecosystem. This visualization helped us understand the interactions and impacts among these groups, enabling us to assess how the AI assistant could offer advantages to each stakeholder, which we then clearly delineated.
Interview Synthesis
We analyzed user interviews to identify key challenges in current PRT experience. From these insights, we crafted hypotheses on how conversational AI could enhance user experiences, such as improving communication, simplifying fare purchases, ensuring service reliability, and boosting accessibility. These hypotheses will shape our design approach for Ollie.
Modeling: Current User Flow
To validate potential opportunities, we charted the comprehensive journey for both passengers and drivers, identifying prospective users of our digital service. Marked segments within these maps signify areas where a conversational AI agent could intervene to enhance the user experience.
Modeling: Target Users & User Journey
Following our stakeholder mapping and interview synthesis, we pinpointed three primary user groups for the conversational AI: general passengers, passengers needing accessibility support, and bus drivers. We crafted detailed personas for these groups and conducted a thorough analysis of their experiences to unearth potential design opportunities.
By employing user journey maps, we meticulously charted the experiences of these key users, identifying crucial pain points and areas ripe for improvement. This method allowed us to capture their emotional journey and explore how conversational AI could significantly enhance their overall experience.
Ideation
Prioritizing Target Users
Before detailed design, we identified key user groups to focus our limited resources effectively. This strategic allocation allows us to deeply understand and address the specific needs of these prioritized users, enhancing the overall design impact.
Proposing Design Directions from User Painpoints
Before detailed design, we identified key user groups to focus our limited resources effectively. This strategic allocation allows us to deeply understand and address the specific needs of these prioritized users, enhancing the overall design impact.
Storyboard Scenarios
To illustrate the diverse experiences of our users, we crafted storyboards that encapsulate the journeys of a daily commuter, a passenger with disabilities, and a bus driver, allowing us to examine the flow and gain insights into how each distinct experience could unfold, and enhancing our understanding and design approach for each group.
Define the Identity of Conversational AI
We explored defining Ollie's identity by considering the traits and tone that best align with the project's objectives and the client's core values. We concluded that the following characteristics would suit Ollie best:
Visualizing Ollie
After establishing Ollie's traits and personality, we iterated on its design, focusing on embodying public transportation attributes and PRT's mission in a singular visual form. This iterative process involved considerable refinement until we settled on Ollie's definitive visual representation.
Explore
Developing Visual System
Before detailed design, we identified key user groups to focus our limited resources effectively. This strategic allocation allows us to deeply understand and address the specific needs of these prioritized users, enhancing the overall design impact.
Prototyping Mobile Interaction
Structure
Before detailed design, we identified key user groups to focus our limited resources effectively. This strategic allocation allows us to deeply understand and address the specific needs of these prioritized users, enhancing the overall design impact.
Scenario 1. Schedule Tomorrow's Trip
Before detailed design, we identified key user groups to focus our limited resources effectively. This strategic allocation allows us to deeply understand and address the specific needs of these prioritized users, enhancing the overall design impact.
Scenario 2. Renew Bus Pass
Before detailed design, we identified key user groups to focus our limited resources effectively. This strategic allocation allows us to deeply understand and address the specific needs of these prioritized users, enhancing the overall design impact.
Scenario 3. Driver Updates to the Passengers
Before detailed design, we identified key user groups to focus our limited resources effectively. This strategic allocation allows us to deeply understand and address the specific needs of these prioritized users, enhancing the overall design impact.
Scenario 4. Request Accessibility Supports
Before detailed design, we identified key user groups to focus our limited resources effectively. This strategic allocation allows us to deeply understand and address the specific needs of these prioritized users, enhancing the overall design impact.
Prototyping Mobile Interaction
Structure
Before detailed design, we identified key user groups to focus our limited resources effectively. This strategic allocation allows us to deeply understand and address the specific needs of these prioritized users, enhancing the overall design impact.
Scenario 5. The Tourist Plans Trip and Cross-platform Experience
Before detailed design, we identified key user groups to focus our limited resources effectively. This strategic allocation allows us to deeply understand and address the specific needs of these prioritized users, enhancing the overall design impact.
Scenario 6. Notification to Waiting Passengers
Before detailed design, we identified key user groups to focus our limited resources effectively. This strategic allocation allows us to deeply understand and address the specific needs of these prioritized users, enhancing the overall design impact.
Value Proposition
Structure
Before detailed design, we identified key user groups to focus our limited resources effectively. This strategic allocation allows us to deeply understand and address the specific needs of these prioritized users, enhancing the overall design impact.
© Yuehui Du 2024