ROCKET MORTGAGE
The final high-fidelity designs and internal product screens are protected under NDA. Recruiters and hiring teams can access the full case study with the password available on my resume.
That's not it. Try again.
Client Validation
Redesigned Onboarding Flow for Rocket Assist
of clients felt that tailored responses were helpful for their homebuying journey and stage.
“I like that it [Rocket Assist] realized that the home has a pool so I would need a pool inspection done too…giving relevant info…”
of clients liked that inspector recommendations were from their realtor, felt this was personalized.
“I like the inspector recommendations from my realtor, rather than those who might have paid for advertisement on this app."
of clients said having immediate options for chat transfer reduces frustration.
“I also really like that it [Rocket Assist] gives me the option and the wait time to connect to a human being for stuff that is sensitive…”
Metrics and quotes taken from the project’s usability test conducted with Rocket Mortgage clients
Context
TIMELINE
May 2025 - Aug 2025
INDUSTRY
Fintech
CONTRIBUTION
Product Design, Conversational AI Design
COLLABORATORS
Conversational AI Designers, Product Designers
First-time homebuyers face a flood of tasks in a tight 7–10 day window after their offer is accepted. Generic guidance across the Rocket Mortgage interface makes it unclear what to do next, driving clients to support channels and increasing agent call volume.
Working within the Conversational AI Design team, I collaborated with product managers, researchers and engineers over 3 months to design and validate the experience. Several of the interaction patterns introduced are now being considered for the product roadmap.
Buying a house can be overwhelming
Homebuyers often feel unprepared after their offer is accepted, facing a rush of deadlines within a tight 7–10 day window.
Generic, non-personalized guidance across the Rocket Mortgage web and chat interface makes it difficult to know what to do and why.
This drives 72% of clients to seek help via chat, in turn increasing agent calls and risking client trust in Rocket Mortgage and retention due to a lack of transparency and support.
And overwhelmed clients translate confusion into lost trust...and lost business
Solution #1
A personalized, contextually aware guided home-buying experience within Rocket Assist.
Through API integrations, page scraping, and document analyzation, Rocket Assist will have the contextual awareness to guide clients throughout their loan progress tailoring the experience to their unique needs.
Redesigned Onboarding Flow for Rocket Assist
RM Client Feedback
Personalized recommendations of local inspectors
Solution #2
Experience that goes beyond conversational UI, with visual elements to break the monotony.
Incorporating new UI components like carousels, cards, contact cards, ability to download documents, proactive notifications and dynamic prompt buttons enhances the experience beyond the standard conversational UI.
Easy access to appraisal report with insights
RM Client Feedback
“I like that the inspector cards are easy to navigate and they are simple in design, I can see everything clearly”
“...I like that there is a direct link to the report and that there are highlights of the report. I like that I could download it instantly.”
Personalized recommendations of local inspectors
Solution #3
AI that doesn’t pretend; immediate human intervention when needed for escalation.
Direct transfer to the best assigned Home Loan Team contact, along with callback scheduling options, will alleviate client confusion and streamline their support experience.
Quick human handover
RM Client Feedback
“Overall, I am a big fan of the flow of connecting to a person when required and that the chat history is not deleted.”
“...I also like that it would notify me through the app when the person is available and I don’t have to save random numbers on my phone.”
Conversation context is retained for reference
Key Design Decisions
Aligned early on contextual guidance needs
Narrowed the problem space to moments where first-time buyers needed clarity most, reducing design churn and aligning stakeholders around a shared goal.
Shared work early with cross-functional partners
Built early buy-in across Product, Content, and Engineering reducing downstream work, helping position multiple features for inclusion in roadmap discussions beyond initial scope.
Explored conversational and interaction patterns
Tested different interaction patterns to surface trade-offs between clarity, feasibility, and trust, informing a more balanced final solution.
Validated assumptions with users before finalizing
Confirmed which guidance felt supportive versus overwhelming, directly shaping tone, escalation logic, and information hierarchy.
Business Impact
Reflection
This was my first time working inside a mature, well-established design team and the difference was immediately noticeable. Watching senior designers think through downstream consequences before they became problems reshaped how I approach my own work.
The moment that stuck with me most was presenting to the RMO product lead. I expected design feedback. Instead he broke each feature down to its smallest moving part. APIs, infrastructure constraints and engineering dependencies. It was the first time I understood that a single feature is really ten decisions that all need to align first.
What worked in my favor was not waiting to be pointed in the right direction. Seeking out engineers, designers and domain experts on my own got me into conversations I wasn't expected to be in and those conversations shaped the work more than anything else.
Dana Lee
Director, Conversational Design
Rocket Mortgage
Amanda Matzenbach
Mentor & Conversational Designer
Rocket Mortgage