Role
Product Designer
Team
Product Manager
Design Manager
AI Engineers
Designers
@2025
What is Orbit?
Orbit is an AI-powered productivity tool for Microsoft product managers, built into Microsoft Teams and powered by Azure AI. Developed as a capstone project in collaboration with Microsoft, Orbit centralizes PMs’ workspaces, provides real-time visibility into team activities, tailors personalized communications, and reduces manual status updates.
My Role
Led Contextual Inquiries
Led Usability Test
Create User Flows, Wireframes, Prototypes
Led Design Iterations
My Impact
Conducted 15+ PM interviews in 6 weeks, synthesizing insights into personas and user journeys.
Designed, iterated, and prototyped the core user flow in Figma within 3 weeks.
Earned strong approval from Microsoft stakeholders for reducing manual reporting and improving alignment.
What did I do?
JAN
APR
Problem Scope
Desk & Generative Research
MAY
JUN
Ideation
Concept Design & Evaluation
JUL
AUG
Design Process
Built & Usability Testing
Don't worry! All content is included as you scroll—but feel free to jump to the section that interests you most.
How do I know I did a good job?
What are Microsoft PMs struggling with?
From our initial desk research, we mapped out general pain points that PMs often face. We now aim to understand which challenges Microsoft PMs encounter most in their day-to-day workflows and tools.
1
Generative Research
We conducted generative research with 6 Microsoft PMs, whose experience ranged from 3 to 15 years, starting with a mind-mapping session followed by contextual inquiries.
Mind Mapping (15min)
We prompted PMs to map out their product roadmap creations flows including tools, and areas where challenges occur. Through this, we:
Helped PMs introspect more deeply on their product roadmap workflows.
Mapped behavioral patterns & workflow insights visually.
Contextual Inquiry (30 - 45min)
We then proceeded with an interviewing focusing on the mind map where we:
Validated pain points in roadmapping & prioritization
Define tool gaps & opportunity areas
Define stakeholder communication challenges.
Discover opportunities for AI integration.
See more details of generative research
2
Persona & Painpoint
Through generative research, we identified PMs’ pain points and synthesized them into clear behavioral patterns, meet Paula—a persona that embodies these challenges and guided our design decisions.
Ideation
How can we help with those pain points?
With the pain points identified, I explored solutions with scalability and scope in mind—considering how to support PMs across different teams and focuses, and what tradeoffs might be required.
1
Concept Exploration
After a round of brainstorming and using the 8x8 ideation method, we generated 30 ideas and grouped them into three key categories through an affinity mapping exercise.
Workload Intelligence
Multi-Agent Automation
Role-Based Communication
2
Concept Down Selection
We then evaluate our concepts using design principle check, and narrow down to our final concept:
User Value
Does it solve a real pain point or help PMs?
Usability
Can it integrate well into PMs' real workflow, or will it add friction?
Opportunity
Does it make smart use of AI, beyond just automation?
Technical Feasibility
Do we have the data, APIs, or capability to build this?
Final Concept
An AI-powered assistant that gathers updates across tools, summarizes key information, and sends tailored nudges to stakeholders—reducing manual check-ins, streamlining communication, and keeping teams aligned.
Onboarding
Main Flow
3
Concept Validation
After presenting our user flows to Microsoft product managers and the design director, we received strong validation for our concepts.
Ananya Patel
11:14 AM
You’ve clearly thought through API rate limits, permissions, and data residency issues, which are often overlooked at this stage…
it actually feels like something we could roll out at Microsoft scale…
Ethan Miller
12:48 PM
It respects how PMs already work. Instead of forcing a new workflow..
It really stands out from other products by being proactive… I can see this being integrated into PMs workflows smoothly…
How the concept came to life?
We brought our concept to life—starting with wireframes, testing with PMs, and evolving into an interactive prototype. After two rounds of feedback and iteration with 12 PMs, we landed on the final design
1
Design Iteration 1 - wireframe
I mapped the flow for one task—following up with stakeholders—focusing on the chat content as a starting point.
2
Cognitive Walkthrough
With our concept and wireframes, we ran semi-structured cognitive walkthroughs with PMs to gather feedback and refine our designs.
Objective
Validate feature usefulness, flow clarity, and content effectiveness.
Methodology
Scenario-based tasks and think-aloud interviews.
Participant
6 PMs from diverse product teams.
Participant Feedback
Unclear UX Writing
‘Alert’ suggests something urgent, but the green item doesn’t feel that important, so the label is misleading.
Information Overload
Seeing so many alerts with so much detail at once feels overwhelming and hard to process.
Navigation Between Alerts
There are alerts, each with follow-ups. After resolving one, it’s unclear how to move to the next in the chat flow.
Unclear Information Source
It feels less trustworthy when I don’t know where the information is coming from.
3
Design Iteration 2 - Mid-fi Prototype
Based on feedback, I iterated on the design, focusing particularly on improving the homepage.
Design Highlight
4
Usability Testing
We then conducted usability testing with our updated prototype and flow with 6 Microsoft PMs. This time the feedback is more granular, more around the
5
Final Prototype
We then conducted usability testing with our updated prototype and flow with 6 Microsoft PMs, we then received following feedback:
Design Highlight
Split to-do and notification by impact
Provide real-time task tracking & updates
Smart scheduling across stakeholder calendars
Provide reassure with 'sent' status
Reflection
What did I learn through out the process?
This was my second time designing a chat-oriented human-AI productivity tool. Since it was an end-to-end experience, I gained many new insights.
1
Power of UX Writing
I used to spend most of my effort mapping user flows into user inputs and system outputs, but I’ve learned that wording matters just as much, especially in conversational design. A single word can change how users perceive and respond.
2
Not to Overcommunicate
It’s easy to assume we should guide users step by step, but what they need, when they need it, how and where it’s presented must be carefully considered. I learned to turn these concerns into interview questions, and user feedback directly shaped my design decisions.
3
Importance Studying User Mental Model
In UX, gap analysis often focuses on what existing products lack, but it’s equally important to understand users’ mental models. With AI-powered tools especially, users develop familiar interaction patterns, and aligning with these reduces cognitive load.
4
Designing with AI
Before designing, I need to define the level of automation we want to provide. In collaborative tools, it’s critical that users feel in control—‘I’m using AI to achieve this,’ not ‘AI is doing it for me.’ Transparency and confirmation inputs help reinforce that sense of ownership.
