Timeline
June - September 2025
Role
UX Design Lead, Design Strategy
Collaboration
Azure Growth Experience team: Designers, Researchers, PM, Engineers
Nav
Problem
Small businesses and student users on Azure have trouble managing their spending and optimizing costs, due to their limitation in budget technical experience.
Solution
I designed an AI agent that autonomously analyzes user's spending habit, provides suggestions to reduce costs, and executes the optimization process on behalf of them.
Impact
70-75%
of the cost optimization process was automated
87%
user satisfaction rate on the final prototype
SOLUTION PREVIEW
A glance of an AI-assisted optimization process
Cost Simulator
When giving suggestions to reduce costs, the AI agent helps users visualize potential cost changes and any relevant technical changes to their cloud services, so they can make a decision whether to move forward.
How Might We…
IDEATION
Think outside the (chat)box
"Push the boundaries and go beyond the existing patterns. Just be creative."
Working on AI features for a legacy system like Microsoft Azure, I was still encouraged to explore visionary, futuristic concepts. Therefore, I explored how AI could be integrated naturally across the site and proactively support users exactly where they need it, instead of making them turn to the chatbot for help.
DESIGN DECISION #1
Personalized cost optimization suggestions
The AI agent keeps track of user's spending habit and proactively provide ways to optimize costs.
The suggestion cards are displayed on the dashboard to explain what's wrong with the current spending habit, how to improve it, and guide users to the next steps.
Previous Iteration
❌ Cost impact isn't mentioned
❌ Generic title can be overlooked by users
❌ Two CTAs can overwhelm users
❌ The semantic red looks like a warning
Final Iteration
✅ Highlight cost impact
✅ Allow user to ignore/skip the suggestion
✅ One CTA to encourage user to estimate costs before making decisions
Integrating suggestion cards into the dashboard
DESIGN DECISION #2
Cost Simulator to make more informed decisions
After giving optimization suggestions, the AI agent helps users visualize potential cost changes, so they can make a decision whether to move forward.
As cloud users are mindful of their spending, this feature provides them with clear visibility into pricing whenever purchasing or modifying services.
Final iteration
Previous iteration
DESIGN DECISION #3
Human-in-the-loop AI interaction
The core priority of the process was to help users build trust with AI and feel more comfortable using AI features by maintaining transparency and human control.
Users have the ability to…
IMPACT & USER FEEDBACK
Users make better decisions and get the tasks done more quickly
I tested the prototype with 8 users from diverse backgrounds—including students and tech professionals—with varying levels of cloud experience (beginner to intermediate) and from different regions across America, Europe, and Asia. The outcome was promising.
87%
Participants said the user flow was easy to comprehend, and the visual design and content were intuitive
70-75%
of the user process was automated by Copilot Agent, which gave users ease of mind
At the same time, I also received some valuable constructive feedback that could help me and the team improve the design further:
The transition between tabs and subpages under Cost Overview could be confusing
Some features/ buttons were vague or not noticeable
Some text content is lengthy
REFLECTION
What I learned as a Designer
Responsible AI
Being assigned to work on an AI-first project, I always reminded myself the most important goal was to remain user-centric and make sure my AI-powered design could solve user problems.
Think outside the box
As a designer, I’m often encouraged to follow the design systems, but in this project, I was given the creative freedom to explore new design elements. This experience taught me to take bold steps beyond the patterns I had limited myself to, create something new, and demonstrate its usability to the team.
Two-way collaboration
As a young designer, I’ve always seen collaboration as a way to learn from others and get feedback on my work. But this project showed me that my ideas could also contribute to others’ projects and inspire them. My design turned out to be more influential than I expected!
THE PEOPLE <3
Summer in the Pacific Northwest
Although this was my second internship with Microsoft, the experience didn't remain the same. I worked on a different product space, had a new manager and some new team members, and even got to connect with some of them in an in-person summer party! I learned a lot from this half-new-half-familiar internship experience.
