top of page
Generating simplified, evidence-based health research insights for health content creators
Health content creators were drowning in research and risking misinformation, so they needed a tool that can streamline research time with verified accuracy before posting content.
web design | non-profit | healthtech | AI
Role
UX Design Lead
Responsibilities
UX/UI Design, User Research, Content Design, AI Design, Agile Methodologies
Team
Brinleigh Murphy-Reuter (CEO & Founder)
Pablo M. Flores, PhD (Product Advisor, Founder)
Rajeshwari Subramanian (Growth & Operations, Founder)
Project Management team
Product Strategy team
UX Research team
UX Design team
Mobcoder (outsourced developers)
Duration
5 months
Impact
Achieving a 75% task-completion rate with content creators and an overall 85% stakeholder satisfaction rate, ultimately securing more funding for the company.
OVERVIEW
Background
Science To People already built a version of their AI platform VeriSci to make complex scientific knowledge comprehensible and accessible, but it had problems.
When our team came on, we found the existing version had confusing navigation, duplicated systems, and unclear labelling throughout, with an already engaged outsourced developer team and a 4 month window to design a new MVP experience.
“Meta ... would end its use of fact-checkers and launch a user-based 'community notes' system to flag inaccurate or misleading posts. The move has raised concerns among experts ... that misinformation about science and health could increase on Meta’s platforms.”
“Meta’s fact-checking changes raise concerns about spread of science misinformation,”
Harvard T.H. Chan School of Public Health, 2025
With investor support, Science To People needed designs for a platform with AI fact-checking and content creation tools that they can take back to their funders. I led the design of this phase and worked directly with product and UX teams while aligning with the client and development teams, ultimately reaching a 75% task-completion rate with an 85% stakeholder satisfaction score that helped secure additional funding before its expected pilot in 2026.
Solution
An AI-powered content creation tool to help health and wellness content creators generate engaging, factual content effortlessly by streamlining research, ensuring accuracy, and adapting to their personal tone of voice.
RESEARCH
MVP2 Audit & Content Inventory
Many great features, many more areas to improve on.
We first assessed the usability of the current version of VeriSci (aka MVP2) to understand what users experience with a designer’s perspective. Here's what we learned:
WHAT WE APPRECIATED
Consistent & clean layout, clear differentiation between UI elements, source inclusion for research, and logical navigation on the home page were some of the strengths that we noticed during the audit.
Simultaneously, we conducted a content inventory to understand the depth and breadth of the content in the very limited time we had. With more time, we'd conduct a content audit to assess the quality of the content and how to improve it. Our main takeaway was:
The navigational structure was very confusing due to unclear pathways, duplicated navigational systems, and uncertain labelling and terminology for CTAs.
User Testing & Interviews
How do users work and what do they like?
I explored the needs, preferences, and pain points of 3 different content creators and researchers. I then gathered key findings and results to understand their thoughts and frustrations:
Simplified Workflow to find specific information
Creator tone and voice are crucial to engage with audiences
Reliable sources that are up-to-date is essential, especially with health topics
Comparative Analysis
Companies provide similar products and services, but none cater towards health content creators.
We then examined 9 AI platforms based on their products and services, including those that are not direct competitors, and evaluated them based on a few criteria (i.e. target users & platforms, onboarding, user flow & navigation, unique features, and customization). Out of the 9, we narrowed down to 3 to focus on:
Google NotebookLM:
This layout is intuitive, clear, and visually engaging without traversing between pages or tabs, which are traits that could benefit users to streamline their research efforts in a highly organized manner.
Phind:
This AI search engine provides both text and images in the same query with mermaid diagrams (editable JavaScript-based graphics), which is very helpful for those who are visual learners and want to track their searches.
Eleven Labs:
This AI tool can generate audio files like podcasts from input text and has a “Try me” section on landing page with various user customization. Allowing various controls for personalization with audio or video files would generate better user connection and engagement.
DESIGN DIRECTION
Product Thinking
Addressing constraints with user insights with business goals.
To ensure that we understand and address user needs, we prioritized our impact and efforts and produced product tenets that were critical for the product launch, which infused and balanced the user insights we learned with more business aligned goals.
Saving time:
Streamlining research & content creation processes by pulling recent, relevant information for content generation.
Engaging the audience:
Crafting compelling, platform-ready content with tailored AI-generated content to match tone, style, and audience.
Building trust:
Ensuring accuracy and credibility with content links connected to integrated, vetted, and verified sources from VeriSci.
Easy to digest:
Presenting complex topics in simpler terms by having AI generate and validate claims with multiple sources.
User Persona
Welcome, Dinah Stevens.
To make our research findings more tangible, I created Dinah, a content creator who is passionate about scientific integrity and promotes science communication through educational content, for a holistic view of the target audience that will keep our design decisions aligned with user needs.
Design Ideation
Exploring 2 different options.
By this point, there were 2 different directions we wanted to explore as a team, specifically about how we wanted to present the research and content creation components. After some discussion, our team decided to experiment with both by expanding our roles to explore the two UI layout concepts (aka camps).
Combined UI Camp:
Where the research tool & content creation studio are in the same screen & navigable in the same flow
Separate UI Camp:
Where the research tool & content creation studio are in different screens & flows from the outset
DESIGN
Branding & Design System
Laying the foundation for a cohesive display.
We retained some elements from MVP2's design library and borrowed some components from Shadcn.ui so that both camps can use the same components and features to maintain consistency. I focused on a couple of factors:
-
Cohesive color palette of primarily green & purple – emphasizing feelings of reliability and creativity
-
Legible and clear typography – ensuring clarity and accessibility for users
-
Rounded and softer iconography – reinforcing user comfort and connection
Wireframes & Prototype
Creating the first look of a new VeriSci.
Since I was working on the combined UI concept screens, I made design iterations to focus on:
-
Clean, navigable layouts for effortless transitions between research & content creation panels
-
Intuitive navigation between CTAs and key features on each panel
-
Responsive elements to match the working styles of researchers and creators
We also explored some early onboarding wireframes to give the users and client a more cohesive image of VeriSci, despite our limited time towards the end of the project phase.
TESTING & VALIDATION
Concept Testing & Insights
"Can't we find some way to combine them together?"
We conducted unmoderated, qualitative concept testing via Maze with 8 diverse content creators and tracked heatmaps and post-test interviews with surveys to give us objective data on workflow efficiency and user preferences. Key insights included:
Design insights:
Users need integrated workflows with clearer visual guidance
User interaction insights:
Initial orientation and navigation clarity are essential for usability
Workflow insights:
Integration is critical for evidence-based content creation
User experience insights:
Users find comfort based on their familiarity with the tool
Hand-off Process
Leaving notes for future work.
After gathering insights, we annotated our prototypes on areas that users appreciated as well as areas that users found difficult. We provided specific annotations and recommendations in our hand-off file for future iterations and the client developer team.
Accessibility is key.
Participants preferred having information in one screen rather than navigating through different screens. They also appreciated the visual hierarchy of the screens.
A more realized workflow can help.
Participants felt the interface & content creation workflow could use improvement. They also wondered about the purpose and relevance of the "Edit in Studio" button to content creation.
Possible suggestions:
-
Re-ideate steps to get from research chat to content creation studio
-
Show more clarity on what's being edited
-
E.g. split text into text blocks & include "Edit in Studio" under each block to transport to Studio panel
-
E.g. Provide a pop-up with short functionality description when hovering over the CTA button
-
More visuals, better clarity.
Participants didn't realize that a new answer was generated after refined searching.
Possible suggestion:
-
Include visual feedback (i.e. loading animation) to show that new answer is being populated underneath
Inclusive and reliable.
Participants compared the database-like interface to PubMed and Google Scholar, valuing the inclusion of sources and article types. They also appreciated having citations directly below the answer.
RESULTS
Results
Both UI concepts had great feedback, but one had better results.
The combined UI concept had better usability with more successful task completions, which could be due to many participants having research backgrounds rather than content creation ones.
Despite this, many participants and stakeholders expressed the desire to see elements from both concepts in a single prototype. This would allow the team to create a more seamless experience and improve user engagement to help the client attract and retain more users.
"But I think, if I had to choose ... Oh god this is a hard one, I cannot choose a combination of both?"
- User Test Participant 2
2.32/5
Average difficulty rating*
75%
Participant task-completion success rate**
85%
Stakeholder satisfaction score***
*Ranked by users with scale of 1 to 5 (1 = easiest; 5 = most difficult)
**Data based on results provided by Maze & heatmaps
***Based on endpoint assessment survey from client
REFLECTIONS & NEXT STEPS
Final Thoughts & Takeaways
The results were meaningful, but under specific context.
Success from a specific demographic:
Looking back, I think the combined UI's relative success was partly due to most of our participants having research backgrounds, which implies that they naturally gravitated towards source-driven workflows. This insight means that we may not have stress-tested the design enough against users who'd approach the tool as content creators first.
Next Steps For Future Projects
Mapping the next steps.
More balanced participant pools:
I would push to recruit a balanced mix of research-oriented communicators and active content creators so that the user testing task-completion gap could be addressed more precisely. A 75% rate is a starting point for future iterations to drive better engagement and adoption rates for the platform.
Re-ideate on how to merge both concepts:
For future iterations, I would leverage the combined UI concept's stronger conceptual model as the foundation for further development with targeted improvements (i.e. addressing misclick issue, maintain clear navigation, etc.).
This would enhance both usability and engagement for users, providing valuable insight for the client when they scale up to attract academic institutions and enterprises.
bottom of page