Bringing AI Guidance to Cloud Workflows
As part of improving Azure’s quota management experience, I led the integration of an AI-powered solution (Copilot) into cloud workflows, enabling users to self-troubleshoot issues and providing clearer guidance and visibility into the cloud system.
This project builds directly on the UX strategy work outlined in the previous case study.
Timeline
2024 - 2025
Role
Product Designer
Team
Research, Engineer, PM, Copilot
Responsibilities
User Research, Prototype
Challenge
Quota issues are consistently happening: Users had no clarity on why, or how to fix them
Data and research revealed that cloud users often struggle to understand why their workflows fail, especially when the root cause relates to quota or capacity.
Many lack visibility into what went wrong, what alternatives exist, or how to proactively prevent issues.
These gaps led to repeated delays, rework, and growing dependence on support, ultimately driving up operational costs and lowering customer trust.
Opportunity
Designing Contextual AI guidance at the point of failure
Building on prior research and workshops, I uncovered a strategic opportunity to embed Copilot at failure points in the cloud workflow, moments when users were blocked, confused, and uncertain what to do next.
What users needed was real-time, in-context guidance right when and where issues happened.
Why I Integrated Copilot?
They needed help that was:
- Immediate — not delayed by support tickets
- Actionable — not just error messages, but next steps
- Contextual — surfaced right when and where the issue occurred
By embedding Copilot into failure moments, we could:
- Shows real-time explanations for failures
- Recommends relevant actions like retrying or submitting a ticket
- Makes users feel guided—not stuck
Design Process
Integrating Copilot into Critical User Journeys
To provide timely, in-context guidance, I embedded Copilot at moments of highest friction where quota issues disrupted workflows the most. This made support immediate, seamless, and confidence-boosting.
01
Identify Friction Points
Grounded in the customer journey and Jobs-To-Be-Done framework, I mapped where quota-related issues blocked progress.
Outcome: Key moments identified where Copilot could add the most value.
02
Design Solutions
Designed end-to-end flows with clear guidance, actionable fixes, and context-specific support, embedded directly in the existing UI.
Outcome: Interactive prototypes
03
Align & Prepare for Delivery
I facilitated a workshop with PMs, engineers, and the Copilot UX team to review design, align feasibility, and validate technical constraints.
Outcome: Finalized entry points, priorities, and feasibility across teams.
Final Solutions
Quota issues still happen but now users know why, and how to fix them
With Copilot embedded into failure points, users now get clear explanations, actionable next steps, and visibility into the quota system.
Empower Confident Deployment Through AI Guidance
By integrating Copilot into the pre-deployment workflow, users gain visibility into real-time capacity, avoid failure-prone configurations, and make faster, more informed decisions all without leaving the platform.
Design solution / Copilot
