Challenges
Rocket’s onboarding didn’t perform as expected housing market and user needs shifting. Rocket’s rebranding initiative, was to integrate automation ~ Liv (AI chat bot) to build user trust, by providing relevant information to minimize drop off and get clients to the right destination.
After account integration with EHR, clinician can access their pre-populated schedule and make updated as needed.
Defining success
Ultimately reducing the amount of lending agents was the goal, the more contextually specific information Liv could collect upfront while delivering exceptional customer service the better the human in the loop can successfully assist people to get the right support needed.
In monitoring engagement, drop off occurred anytime there was a technical issue with mobile devices, clincians were used to using a desktops during patient visit, etc.
Strategy
Build a 1:1 from mobile app, with successful features and more editing capabilities because
most clinicians don't want to edit on mobile, but will make final edits on desktop due to current workflow with EHR.
In monitoring engagement, drop off occurred anytime there was a technical issue with mobile devices, clincians were used to using a desktops during patient visit, etc.
Pivot
User research and feedback from clinicians, detailed that clinicians wanted an AI solution with human support in the loop, so product pivoted to a solution where an MDS could access, and update generated notes.
Empowering clinicians to maximize AI, but still have support where needed through quick in app messaging
Process
Deploy Fine tuned LLM model trained on medical data to support clinicians workflows in a native mobile app which helps clinicians improve their quality of care with efficiency.
Prioritization
Design pushed to improve the UX based on feedback from Customer Success stakeholders and MDS needs. Allowing priorities and resources to shift towards maximizing NPS, our team achieved this by making onsite visit to various clinics.
Empowering clinicians to maximize AI, but still have support where needed through quick in app messaging
ML improvements
As LLMs improved we were able to fine tune the models to provide context specific recommendations to improve note quality with a few taps, and output summarized note formats.
Empowering clinicians to maximize AI, but still have support where needed through quick in app messaging
Scaling
I communicated insights that clinicians found that the product was trying to constrain them to use it a certain way, once we added personalization features such as templates, and preferences and settings. We were able to let er rip, allowing clinicians to find their own workflow with minimal guardrails!
Empowering clinicians to maximize AI, but still have support where needed through quick in app messaging
Notes
Augmedix was also going through a rebrand during the last quarter of the year, where I supported marketing and branding efforts in how we communicate the value of the product,
and even made space for a design system to keep it all consistent!
If you have questions those processes or this case study, feel free to reach out. ac.design.px@gmail.com
Contact
studio.acas
2025
Rocket's Chat Bot "Liv"
Role
Product Designer
Timeline
OCT 2023 - Now
Results
Deployed to millions of homeowners, increasing conversions by 22 - 27%
