Practice voter outreach and canvassing with WeRelate
For the 2024 presidential campaign, our product studio team partnered with Indivisible, a progressive grassroots organization, to create WeRelate. The LLM-powered chatbot helps first-time canvassers practice voter conversations and build confidence.
AI-Powered Volunteer Training Tool
Our team explored how large language models could support voter education through campaign messaging. We evaluated the strengths and risks of LLMs trained on candidates’ policies and talking points. Along the way, we identified a gap in volunteer training and designed a chatbot to deliver dynamic, scenario-based prep for canvassing. I also researched existing AI tools in political messaging and voter outreach during the initial phase.
The problems
How might technology support faster, consistent volunteer training at scale?
How might we better equip volunteers to have more effective conversations with potential voters via phone, text, canvassing or other in-person contact to support progressive candidates and causes?
User flow demonstrating the Conversation Checklist, Chat, and Ask for Help features
User research and insights
To design a solution that met the needs of volunteers, I led comprehensive research sessions in collaboration with a team from Trestle. These sessions involved interviews with field organizers and experienced volunteers to understand their processes for voter outreach, including:
Following voter outreach protocol.
Preparing to speak to voters and have meaningful conversations.
Learning scripts and effectively conveying talking points.
Our research revealed key pain points in the training and preparation process. We chose to focus on first-time and beginner volunteers, who often felt the most unsure about how to engage with voters. Our goal was to help them feel more confident and better equipped to have meaningful, authentic conversations with potential voters.
To deepen my understanding, I participated in canvassing and door-knocking in Corona, Queens, as a first-time volunteer with NYC Votes. This experience provided first-hand insight into the process of speaking to voters including door-knocking, following Get Out the Vote protocols, and using the Minivan mobile app.
Metrics
To support mobilizers and volunteers, increase engagement, and reduce volunteer dropout, our team focused on the following impact metrics:
↑ increase in mobilizer confidence based on pre/post session self-evaluations of conversation skills
↑ increase mobilizers trained — more mobilizers in canvassing or relational voter outreach programs receive roleplaying training
↑ X% more conversations initiated — more mobilizers report wanting to have at least one additional conversation
↑ X% in mobilizer retention — more mobilizers return to volunteer at least once more
Iterative Design and Development
Persona and Prompt Design
The engineering and product teams collaborated to experiment with prompts that configured chatbot personas. This required close teamwork to refine the LLM’s output and ensure alignment with specific voter demographics and personas.
To validate the chatbot’s utility, I led additional research sessions where participants provided input to the chat bot and reviewed its output to share reactions and recommendations. These insights helped refine the chatbot’s design and ensured it met the needs of volunteers.
Scenario Development
Using feedback from testing sessions, the team iteratively refined the chatbot prompts. The final product supported training volunteers in four voter outreach scenarios:
Get Out the Vote
Persuasion
Volunteer Recruitment
Event Recruitment
I also spearheaded the creation and documentation of all user-facing content. This documentation was reviewed weekly, ensuring alignment between the product direction and code development.
User Interface Design and User Acceptance Testing
I was responsible for all aspects of user interaction and interface design for mobile and desktop platforms. Design decisions were informed by team feedback, brainstorming sessions, and usability testing. This iterative design process led to the creation of high-fidelity wireframes delivered to the front-end engineers.
Testing and Launch
Before launch, the team conducted rigorous testing across various scenarios to identify and address bad responses and bugs. Key steps included:
Creating detailed testing scripts to guide the team’s assessments.
Stress-testing the chatbot and helper feature during the User Acceptance Testing phase.
Recording issues and translating them into engineering tickets for resolution.
After addressing all critical bugs and completing a penetration test, the chatbot was launched in partnership with Indivisible.
Outcomes and Reflections
This project demonstrated the potential of leveraging AI to empower volunteers and enhance voter outreach efforts. Through collaborative design, rigorous testing, and user-centered research, we delivered a tool that effectively supports canvassing training and builds confidence in first-time and new volunteers. This experience also reinforced the value of iterative feedback loops in refining digital products for impactful results.
Although a late-stage partnership fell through and limited live usage, we built the product successfully with measurement in mind. setting up analytics to track onboarding, script engagement, and resource usage. We also integrated an NPS survey to capture volunteer confidence. These metrics aligned directly with our goal: boosting readiness for voter outreach.
Though we couldn’t fully validate the product in the field, the project sharpened my skills in prompting LLMs, structuring outputs, and designing user acceptance tests. I tested for accuracy, safety, and misinformation risk, while also learning the value of early partner alignment and strategic contingency planning.
