Ai Helper
B2C Modular Configurator plugin that allows a user to configure their perfect product by using Ai prompts or image recognition
Team: One product Designer, Two Developers, Four QAs, Two Data BAs
Role: Product Designer
Timeline: 8 weeks
43%
Add to cart rate up
Ai adoption
86%
PDP dropout down
17%
Introduction
Looking to join the race to introduce Ai into our product set and continue to be market leading we looked across our products and identified areas where Ai could help. Taking into account our current limited knowledge in the Ai space and the complex nature of our products we opted for a client facing Ai integration that looked to tackle the overwhelming configuration options available in our customers modular products.
Goal
Develop a straightforward and user-friendly AI interface that allows a user to easily supply a simple text prompt, and in response, the AI will intelligently construct a product that effectively suits their specific needs and requirements. This interface should be designed with accessibility in mind, ensuring a seamless experience for all users.
Target Audience
This Ai plugin will be open to all of our current customer base that have access to the modular configurator and are using it on their PDP’s. Looking across our customers there are two clear personas that cover 87% of user cases:
Qi (chi)
Online gamer
18 years old
Sat in her chair over 12h per day
Like to play and stream games
Confident with technology
Quick to pick up new tools
Social media expert
Samantha
Home office worker
37 years old
Works at her dining table
Sat in her chair over 8h per day
Mum of two
Confident with technology
Enjoys writing and reading
Unanswered Questions
Who are the major players in text prompt Ai?
Can Ai take the product set we have and successfully assemble parts based on compatibility?
How much hand holding do users need when interacting with Ai?
User Research
Who are the major players in text prompt Ai?
Using a simple web search cupeled with blog posts and a conversation with likeminded Ai enthusiasts in a few social groups I started to gather information on Ai trends, market leaders and what the suspected future of Ai tools would become:
What I discovered
Solo travellers struggled with anxiety over traveling alone
Travellers are looking to find connections and make friends
Solo travellers rely on devices for communication with their family while on holiday
Travellers have lots of unanswered questions before their tour
Travellers struggle to manage all aspects of their trip on their own
From these findings I surmised that the application would need to do the following things:
Allow the user to manage their tour from end to end
Connect with fellow travellers that have booked onto the same tour
Allow the user to document and share their tour
Provide full information of the booked tour and a means of asking questions in the lead up to departure
How do travellers currently document their holidays?
In the same survey we also asked these questions:
Do you document your holiday? Yes/No
If yes, do you do this during or after your holiday? During/After
Do you share stories or pictures of your tour with friends or family? Yes/No
If you have been on a trafalgar tour before, what do you like to do on the tour bus between stops?
⏹️ Sight see
⏹️ Read
⏹️ Talk with other passengers
⏹️ Look at my pictures
⏹️ Write about my day
⏹️ Other
If other please specify…
Results
82% of travellers document their tour
15% document during their tour
96% share pictures and stories with friends and family
57% of travelers read on the tour bus
Most travellers had not considered documenting their tour during the holiday and thought it would be great to come away from their holiday with a keepsake that they can share with friends and family.
Application flow
Intro
Log in
Menu
Notifications
Account
Home
Tickets & times
Itinerary
Group chat
Tour diary
Tour info
Book Another
Tour
Wireframes for testing
I tested this low fidelity prototype with a test group of 50 users aged between 50 and 76 that have booked or are planning a holiday in the next 6 months.
The test was moderated and in person using a rented testing lab with Tobi tracking to allow for greater feedback from the users actions with the device.
Findings
Overall success rate 98%
Users were able to navigate the application with ease
Users found the Diary screen overwhelming
Useful comments
‘it would be nice to be able to speak directly with each person’
‘Information about travel would put my mind at ease before traveling’
‘can I place images in with my text to go with what I am typeing?’
Final Product
What I improved
Addition of a search bar on the home page to allow users to find their next trip
Reduction of Trafalgar logo presence to gain more space
Moved the navigation up the page to give it higher priority and used icons to clean up the interface
Simplified the chat interface to allow users to see other tour guests
Re arranged diary to allow for stacking enteries, inline images, entry sharing and editing
The new app boosted Trafalgar's solo traveler engagement by more than 23%, based on new bookings from recommendations and returning solo travelers. A survey showed that the app was the main reason they chose to travel with Trafalgar again.
Learnings
As this project was completed in 2015 and technology has moved on quite a bit, what would I do differently?
I would include an Ai chat bot to receive messages and reply to users wanting to speak with the tour guide and then send a summery of the conversation to the guide a day before the trip as feedback was that tour guides struggle to keep up with the messages when managing multiple tours in a single season.
I would include an Ai text assistant to help users with writing their diary entries.
Now that most people use their phone as their primary camera, I would add a separate gallery page that would allow users to view their images by trip.