AUIs for Google Workspace

Speed up repetitive and tedious interactions, optimize efficiency, and reduce number of clicks in between Google Workspace apps.
2021.03 - 2021.04 | 4 weeks
Adaptive UI
Product Cohesion
Prototype
My roles

User Scenarios
Wireframing
Prototyping
UX/UI

The challenge

Reduce redundant interactions and provide reliable suggestions through applying Adaptive UIs to mobile experiences

The Solution
Suggest Attachments Options
Suggest files and folders to attach based on email content, recipients, and Google Drive's files/folders content.
Autofill Event Names & Guests
Autofill meeting information based on the event title, past event content, and participants.
Prioritize Files & Folders
Better prioritize files and folders based on Google Calendar events information and Google Drive collaborators' activities.
The context
What is AUI?
Adaptive user interfaces (AUIs) employ elements of AI to improve user experience. Application in AUI is to use a little AI to reduce tedious, repetitive, and mundane tasks and personalize user experience, such as navigation, interaction, and attention. Examples includes autofill in Google search and suggestion of destination in Uber.
Explore
Identifying Opportunities
We started by brainstorming 10 ideas from mobile or web apps and identifying opportunities for AUI innovations.
I analyzed design opportunities based on the criteria of value co-creation, data feasibility, and impact of errors:
We wanted to improve the product beyond building stronger recommendation systems.
Looking through our ideas, we found a connection between Box and Calendar, what if they are both Google products and the data can be shared across apps to increase the accuracy of predictions?
We decided to improve Google Workspace ecosystem within the 3 apps due to their overlapping data:
Here we decided to bring in Gmail, the most used google mobile app as part of the package. Gmail is already integrating some AUIs that we could potentially draw inspiration from.
Explore
Data Exchange
We listed out the data that can be collected and labeled through users’ daily activities, and decided to focus on the shared data in the middle.
Not only are these data readily available among all users, but they also provide reliable information to train a global model since people use and generate these data in very similar ways.
The Overlapping Data to Build Reliable AUIs
problem statement
How might we integrate the product ecosystem of Google Workspace apps and improve efficiency for their users through applying adaptive UIs?
Define
Who are Customers?
We considered various scenarios for different audience groups to discover opportunities.
When creating user scenarios, we weighed heavier on creating high density of value. For example, someone who frequently perform the task, or someone who have to use the mobile apps due to urgency, convenience, etc. e.g., working at the airport, or on the subway.
Synthesis: uncovering users' needs
Develop
Iteration / GMAIL
Scenario / GMAIL
Ada needs to share documents in an email to the clients on her phone during her flight. She’s annoyed by the file attachment process. She has to remember the file names and make sure she addresses them correctly. Otherwise, it might confuse the clients who receive the files.
Current User Flow / GMAIL
Initial Solution / GMAIL
As soon as she types out “Please review the attached doc ...”
UI CONSIDERATION
GMAIL: Floating bar or not?
During the process of developing the above Gmail prototype, we considered 3 design patterns as signifiers for AUI inference:
  1. Highlight the attachment icon for inference, and tap to trigger AUI inference;
  2. Highlight the text users input, and tap on the text to trigger AUI inference;
  3. Suggest file/folders above the keyboard, and enable one-tap attachment bar.
We chose the 3rd one because this design pattern provides the clearest signifier.
This design pattern fits with users’ mental model on the functionality. However, it needed more modification at this point in that we want the AUI to provide close-enough inferences, but not one accurate result for users.


Quick & Dirty Testing
Feedback / GMAIL
Smart autofill is not an “individual model”, so autofill for only 6 people in Gmail is out of the possibility.
The fully adaptive UI (only 1 suggestion) does not consider error cases, but taking top 3 selections should work.
DEVELOP
Iteration / GOOGLE CALENDAR
Scenario / GOOGLE CALENDAR
Throughout the day, Ada needs to schedule meetings with multiple teams. She’s pretty frustrated that she has to manually type in the name of meetings and the names/email address of all meeting participants.
Current User Flow / GOOGLE CALENDAR
Initial Solution / GOOGLE CALENDAR
We considered 3 ideas:
  1. Better prioritize lists of contacts
  2. Create a project team feature
  3. Predict event names and guests based on Ada's input, and past events' data.
tHINK ALOUD user testing
Feedback / GOOGLE CALENDAR
"This feature fits with my work styles to follow projects and team members accordingly."
(Idea 2)
"It solves my problem of adding the same group of people repeatedly."
(Idea 3)
We eventually chose idea 3 due to its low interaction cost and high user familiarity.


UI CONSIDERATION
GOOGLE CALENDAR: Auto add or not?
2 AUI options for Google calendar:
  1. one that would suggest the invitees and users have to click to confirm,
  2. one that automatically adds the invitees for users.
The “click to confirm” can be tedious if users invite a large group of people. After evaluating benefits and risks, we decided to pursue option 2.
It was difficult to make the decision, especially when Gmail has so many user scenarios: we believed that it is important for users not to send the invitation to the wrong people, so options 2 seems a little bit aggressive; On the other hand, we also think option 1 would require more clicks if users do not need to go through this step every time they set up events for the same group of people.
Develop
Iteration / GOOGLE DRIVE
Scenario / GOOGLE DRIVE
Ada needs to check file updates before regular meetings, keep track of so many files, and share reports with her teams and clients after the meetings. She’s frustrated that she wastes a lot of her time navigating through folders or looking for files.
Current User Flow / GOOGLE DRIVE
Initial Solution / GOOGLE DRIVE
When Ada opens the app, the system automatically prioritizes files that she potentially wants to open/share...
Quick & Dirty testing
Feedback / GOOGLE DRIVE
We need to consider: how often is an entire folder being shared vs. an individual file being shared?
Sending email in google drive is not a frequent use, so probably not getting enough data to make accurate inferences here.

Final Design
GMAIL
Ada types out keywords relevant to the file, and the system provides a suggested list of files and folders based on the keyword.
GOOGLE CALENDAR
The system suggests 3 meeting names, and automatically generates the participants' names and email addresses for Ada based on the event name and past event participation history.
GOOGLE DRIVE
The system makes inferences on which file Ada will be most likely to open at the moment based on information extracted from Ada’s calendar schedules (e.g., ongoing events, event participants) and Gmail activities (e.g., recently received documents).
value creation
Estimated Impact
We had a hard time defining and calculating the value of our solutions. We decided to go on two routes, one to calculate the market value of this problem space and the individual savings on each transaction. PMs are one of our target users, there’s a much wider market, so the market value is underestimated.
Reflection
What I Learned
Consider diverse scenarios & audience groups
From this project, I learned that a large user base is a challenge but also an opportunity for designers because little tweaks in scenarios can potentially generate more nuanced contextual information that leads to new design opportunities, eg. the scenario change from GDrive file sharing to opening files during meetings.
Error recovery & nuances in AI technology
AI systems are not perfect and make inaccurate predictions frequently. Therefore, I learned to consider error recovery and nuances in designing for AUIs: how do we prevent user disappointment from inaccurate suggestions? how can we bring users one step closer to their goals?