Targeting non-technical and budget-conscious Azure users, I designed an AI agent that autonomously optimizes their cloud spending and guides them to make smarter, more cost-effective decisions.
Project
Internship
Timeline
June - September 2025
Role
UX Design Lead, UX Research
Team
Cross-team Designers & Researchers, PM, Engineers
CONTEXT
What is Azure Cost Management?
Located on the Microsoft Azure portal, it's a tool that helps users track, manage, and optimize their spending on cloud services.
It offers insights to help users stay within budget and reduce unnecessary costs.
Having reviewed 7 internal research resources and 2 design sprints for Azure Cost Management, I learned that while anyone can be a user of Azure, those who experience the most problems are:
Students & individual users
Startups & small businesses
Compared to other Azure users, they have…
Pain Points
Goals/Needs
Limited budget - they are mindful of their spending
Save as much money as possible and avoid going over budget
Limited experience in cost management and cloud services
Need more guidance and support
Limited time and resources to learn to manage cost
Prioritize speed, autonomy, and simplicity
A significant number of users are interested in AI-based cost optimization suggestions.
A startup developer
How Might We…
A big challenge I experienced early on in the project was navigating the ambiguity of Agentic AI. Having zero knowledge of this area, I learned the basics by drawing on Microsoft’s internal design work and examining how companies like OpenAI, Amazon, and Google approach similar products.
I initially pressured myself to design something original and unique from the existing patterns. However, through discussions with other designers across the studio, I learned that what truly mattered was designing solutions that addressed real user needs and could be integrated into Azure’s design system for broader use across the platform.
Together, we brainstormed ideas to revamp existing design and combine it with new features.
After 6 iterations, 8 usability testing sessions, and countless design critiques, I've designed a new way Copilot can help users save time while enhance efficiency in the cost optimization process.
*Due to a Non-Disclosure Agreement, the designs and content shown here have been simplified. Please reach out to me if you’d like to learn more about this project!
Cost Simulator
Cloud users are consistently mindful of their spending and service costs. They need clear visibility into pricing whenever purchasing or modifying services.
Cost Simulator helps users visualize potential cost changes before making any decisions on Azure.
Agent doesn’t only answer your questions — it does the task for you
Unlike traditional AI assistants or chatbots, AI agents in Azure Cost Management can directly make changes to users’ cloud services with the user’s approval. This feature is especially helpful for those new to Azure or without deep technical expertise.
Users retain full control over the agent’s actions, with the ability to monitor, intervene, or stop its tasks at any time.
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, thanks to 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
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!
