Ollie: Conversational AI
Design a conversational AI assistant for Pittsburgh Regional Transit (PRT)
Client
Pittsburgh Regional Transit (PRT)
Team & Role
Designers: Yuehui Du, Iris Cai, Angela Nam, Aishwarya Rane.
Duration
5 Weeks
Tools
Voice Flow, Figma, Illustrator, After Effects, Premier Pro.
Overview
"Hey Ollie!" to meet your companion on bus.
Ollie is a conversational AI that keeps passengers informed during their ride on the public transportation, ensures their safety, provides accessibility assistance, and adds enjoyment to your ride.
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.
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.
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.
Ollie's Motion Status
We identified essential statuses for conversational feedback, focusing on smooth transitions and infusing shapes with easy-understanding movements and transformations.
Research
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."
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.
"Can't be notified instantly" frustrates all target users
Since the "silent communication" only conduct face-to-face, the asynchronous notification frustrates all target users. Passengers can't receive the updates unless get to the bus stop, and drivers can only know accessibility requests when arriving the stop.
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
How does conversational AI enhance the communication experience?
By analyzing the benefits of conversational AI and aligning them with identified pain points, we have developed a hypothesis on how Ollie can enhance the communication experience.
From communication painpoints to design directions
Before narrowing down to the specific design, we review the painpoints and digest them to three core design directions to guide the design of Ollie's identity and interfaces.
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:
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.
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.
Explore the structure for key features on mobile and kiosk
Design
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.
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
Emerging technology is not the answer, user's needs are.
By focusing on what users actually need and how they’ll use what we design, we make sure tech plays its true role: a real helper that brings practical, meaningful solutions to the table. Along the way, I’ve learned to look past just the flashy side of new tech and really ask, “Is this actually solving our users’ problems?” This user-first mindset doesn’t just lead to designs that are more about the user; it also keeps our work relevant and valuable, adapting to the wide range of human needs out there.
Meet users after getting alignment with the client.
We would like to conduct user testing on the initial version of Ollie. Since this product is for the local communities, besides the direct interview, we can also organize some workshops and group meetings to collect their feedback to optimize our design iteratively.
© Yuehui Du 2024