VeriComms

🔎 Upgrading an AI-powered tool that helps public health communicators research information and create content with collaborators

See design flats / See prototype

OVERVIEW

Connecting science & communication

Public health communicators are challenged with tackling rising health misinformation on limited time and budgets. To address this, Science to People is building VeriComms, an AI-powered search engine and tool that helps communicators craft trustworthy content from vetted scientific sources.

The Problem

Ineffective layouts prevent communicators from finding important information like sources, and underdeveloped features limit their ability to involve collaborators.

The Solution

Our cross-functional team at Tech Fleet designed a research-informed prototype with improved navigation, making it easier for communicators to find essential elements such as sources. We also added features like commenting and sharing to better support stakeholder collaboration.

MY ROLE

Leading design thinking & collaboration

I guided the UX Design team to ensure our decisions were grounded in usability best practices and research insights. I collaborated closely with researchers, strategists, and writers to improve the product in a rapid timeline of 10 weeks.

Contributions:

Audited the base tool to identify usability issues and opportunity gaps
Designed a streamlined prototype with enhanced navigation and features
Moderated interviews with public health communicators
Facilitated stakeholder workshops, client demos, and team meetings

DISCOVERY

Interviewing public health communicators

VeriComms was originally developed with limited research: 16 surveys and 329 unstructured interactions. Due to confidentiality, we could not conduct usability testing with the base tool.

To guide future improvements, I assisted our research team with interviewing 30 public health communicators to understand their workflows, pain points, and relationship with AI tools. Working with the client, our researchers determined the interview questions through a prioritization exercise. They recorded the interviews on Google Meets, then analyzed the transcriptions through Dovetail to synthesize insights.

Key insights:

Familiar AI chatbot patterns
Communicators expect AI tools to handle varied requests like in ChatGPT and Claude.
AI as a brainstorming assistant
They use AI to help draft campaigns, create outreach content, and visualize data.
Vetted sources
They verify whether AI responses are backed by reliable sources, especially on sensitive topics such as vaccines.
Content collaborators
When creating content, they involve many collaborators to ensure accuracy, sensitivity, and compliance. Participant 23 describes the in-depth process:

“A subject matter expert will provide the content, which is reviewed by their division leader. I create a mockup and submit it to my manager, who does a literacy and design review. After that is approved, it’s sent to the communications director to ensure that it is compliant with our branding. We then send it back to the subject matter expert to review and they give us feedback. Then it will be approved for dissemination to the public.“

AUDIT

Identifying gaps & opportunities

Drawing from Nielsen Norman guidelines, interview insights, and competitor design patterns, I identified usability gaps and opportunities to address communicators’ needs. We compiled our recommendations in a slide deck, and I reviewed them with the client in a workshop. Due to confidentiality, these example slides feature a de-branded version of the base tool.

DESIGN

Prototyping with research

With the design and research teams, I constructed a low-fidelity prototype with two goals:

To gather feedback through concept testing and determine whether the prototype provides the key actions needed by communicators in a typical workflow. Due to confidentiality restrictions, we could not test the base tool.
To visualize a refined version of VeriComms that improves usability and better supports communicators’ workflows.

Feature prioritization

We brainstormed features that build on the opportunities we identified in the audit, interview insights, and competitor products. In collaboration with our strategists, we prioritized the features to incorporate in the prototype based on value and effort.

Prioritized features:

Example prompts that illustrate the tool’s varied capabilities
Sources that are easy and obvious to verify
A text translation feature
Sharing and commenting tools to involve collaborators

Task Flow

Focusing on the product’s core offerings, conducting research and creating content, we mapped a task flow that served as an outline for our prototype. In collaboration with the research team, we ensured each step aligned with the prioritized features.

Initial Prototype

With a solid task flow, we assembled a low-fidelity prototype, looking closely at competitor tools and prevalent design patterns to craft the layouts. We incorporated the prioritized features which correlate with the interview insights and opportunities identified in the audit, such as icons with text labels and a vertical navigation menu.

TESTING & ITERATIONS

Improving feature discoverability

We ran five concept tests in Maze with health communicators, then uploaded the transcripts to Dovetail for qualitative analysis. Participants appreciated the prototype’s ease of use, source visibility, and productivity potential. Participant 5 remarks on how the tool would be suitable for collaborators in different roles, such as government workers and community partners:

“I think people would learn to use [VeriComms] pretty quickly. It’s kind of like ChatGPT; you just jump in.”

Yet, participants overlooked the template and translation features, instead wanting to use the prompt field to complete the tasks. Referring to design patterns in ChatGPT, Google Translate, and Gemini, we addressed these issues by improving discoverability and aligning with participants’ preference.

Users need cues for new features

Problem

None of the participants noticed the Use style template feature.

Solution

A coach mark draws attention to and introduces the feature.

Users need features that align with their mental models

Problem

Participants didn’t notice the translation feature, instead wanting to use the prompt field.

Solution

Users can translate text with a contextual prompt field.

FINAL DESIGNS

An intuitive tool for communicators

The prototype reflects the insights we identified in our discovery research, supporting communicators with verifying AI responses, brainstorming and writing, and collaborating with stakeholders.

Communicators can verify sources via hover citations and a dedicated tab

A contextual prompt field supports intuitive AI-assisted editing, such as translating text

REFLECTIONS

Collaborating to build

In just 10 weeks, our team gained insight into communicators’ workflows, explored AI design patterns, and adjusted to confidentiality restrictions. Our close collaboration enabled us to provide improved user experiences for VeriComms, earning highly positive feedback from the client:

“Your team’s research and UX work directly supported our ability to move forward with fundraising and development. The prototype gave our team a clearer understanding of user needs, leading to more intentional product scoping and feature prioritization for VeriComms. Several of your UX recommendations have been shared with [our developers] and are being incorporated into the current design and build phase.“

Brinleigh Murphy-Reuter
CEO & Founder, Science to People

Given more time, I would integrate our persona—finalized at the end of the phase—into the prototyping process. Incorporating the persona’s perspective would further anchor our design choices in user needs and illustrate the product’s user journey for the client.