Leveraging AI to improve virtual brainstorming session in Microsoft Whiteboard feature
Overview
We were sponsored by Microsoft to explore ways to enhance remote brainstorming sessions for UX designers, addressing the challenges of reduced collaboration and engagement in our growing remote work landscape.
The result is Whiteboard AI, an integration for the digital whiteboarding tool Microsoft Whiteboard that introduces a set of AI-powered features that support creative agency, adapt to diverse workflows, and reimagine the remote brainstorming experience.
In June 2023, we presented these concepts via video prototype to stakeholders at Microsoft Whiteboard, including their Director of Product Design and Lead Researcher.
Timeline: 6 months (Jan - Jun 2023)
Collaborators: Rabab Rabbani
Apoorva Kulkarni
Zoey Gray
Gauri Nayak
Role: Product Designer
Responsible for research planning, study moderation, data analysis, paper prototyping, prototyping in Figma, video prototyping in Jitter.
Whiteboard AI in 60 seconds
Understanding the Problem
Remote work can feel lonely and uninspired.
For many of us in the post-COVID world, remote work has become a lasting reality. While it has its benefits, it can also pose challenges in terms of building strong connections with colleagues and capturing the same level of enthusiasm and participation as in-person collaboration. So in January 2023, Microsoft approached us with the challenge of improving brainstorming sessions in Microsoft Whiteboard to make them as generative, collaborative, and inspiring as in real life.
Remote brainstorming shouldn't be brain-numbing!
No creative blocks.
No siloed workflows.
No limits on exploration.
Extensive research, including Wizard of Oz studies, focus groups, participatory design sessions, and usability testing, has guided us in reimagining a smarter brainstorming experience, from the broader canvas all the way down to the smallest unit of a sticky note.
Initial Prompt
Whiteboard on Microsoft Teams helps users collaborative with their teams. This was the UI when we took over the project.
After initial literature reviews, research into Microsoft Whiteboard’s user base, analysis of the market trends, and knowing that Microsoft had just invested $10 billion dollars into Open AI, we decided to scope down:
How might we leverage AI to improve a remote brainstorming session, so it will be as generative, collaborative, and inspiring as in real life?
Research Method
What are we trying to find?
We watched UX designers brainstorm both with and without AI.
To stimulate brainstorming with AI on the whiteboard, we took an unconventional approach by integrating the Wizard of Oz method early in our research. We created a makeshift prompt box on the canvas, allowing participants to input queries to an AI. Our team then quickly inputted these queries into ChatGPT (for text output) and Dall-E (for image output) behind the scenes before returning the responses to the participants.
Followed by this session we conducted a focus group session where we asked our participants what it was like working with AI.
Findings
What did we find out?
In conversations with UX designers, we unearthed some interesting tensions and ethical challenges related to AI and mostly understood how users would like AI to help them:
2. While ideating individually, participants looked at their teammates’ stickies to get more ideas and understand the general direction of the team.
01
1. During idea share-outs, team members got inspiration from hearing each other’s ideas.
Inspiration from others’ ideas
2. Some participants also used the output from AI assistant as further inputs to build on existing ideas from a new perspective..
02
1. Participants used the AI assistant to conduct secondary research to get a quick overview of information related to the prompt they were working on.
AI as a great side-kick
2. Synthesis was time-consuming due to the large number of stickies generated, the time taken for identifying and grouping similar ideas and analyzing the themes.
03
1. Participants struggled to collectively synthesize all the ideas that the team had put on whiteboard in a short time.
Synthesis is time-consuming
2. For some participants, this was also a barrier to using the AI tool, because they were uncertain about when they should use it or what they should be expecting from it.
04
1. Participants found it challenging to accommodate the AI tool in their personal ideation process while keeping their own workflow uninterrupted.
Need for flexibility
Design Outcome
What we built.
Through extensive testing, we designed a feature set to inspire, enhance collaboration, and facilitate easier synthesis.
Feature 1
Next-Gen Notes
Re-designed sticky notes with auto generated, real-time keyword tags. Quickly identifying big themes across the whiteboard.
Feature 2
Generating Notes
Fixating on an idea and hitting a dead end? Whiteboard AI lets you build on your and your team’s existing ideas.
Feature 3
Merge and Cluster
A good brainstorming session is chaotic, in a good way but sorting through a sea of sticky notes is often the more laborious part of synthesis.
Whiteboard AI organizes your ideas, all while keeping you in-charge.
Feature 4
Inspire me
Blank canvas on a whiteboard is scary. How does one take that first step?
Whiteboard AI inspires you, where you are the hero of your brainstorming session, and AI the sidekick.
Feature 5
Mind Map
Synthesize all the crazy, great ideas your team puts on the whiteboard, in real time.
Making those brilliant connections between ideas. Nudging you to explore the uncharted. Showing you the big picture. Saving time.
But, there is more to solve for
Addressing ethical concerns surrounding AI remains an ongoing challenge, and finding the right balance between AI assistance and human creativity is a delicate task. Here's few that we started questioning:
01
Co-creating with AI raises concerns related to authenticity, originality, loss of creative control, and over-reliance on tech among others.
Creative Agency
02
AI can sometimes share false information with absolute confidence. How do we establish trust and protect users?
Trust in AI
03
Data Privacy & Intellectual Property
Concerns raised by our participants: “What if AI now steals all my best ideas and suggests them to others?” “Who gets the ownership of these ideas - the AI or us?”