Integrating Election Data into Generative AI Tools
Download our manual of best practices for disseminating election information and voting guidance through AI platforms.
Generative AI tools create content based on information they have been trained on in the past, but elections and voting data evolves over time. Because these tools are not built to process data in real time, they may present users with out-of-date or entirely fabricated information that could confuse or disenfranchise them.
The Democracy Works Elections API, which provides reliable voting guidance for all levels of US elections, is a powerful tool that mitigates such harms. We believe that to operate responsibly, generative AI tools should disseminate live, authoritative data on elections and voting to their users using the API. The data that powers the Elections API covers thousands of elections each year and is compiled and continuously updated by a team of expert election researchers at Democracy Works. The API has the breadth and depth of data required to accurately respond to the election-related questions users are likely to ask generative AI tools, including queries about election dates, registration, and voting methods.
This 40-page guide outlines best practices for how generative AI tools should respond to election-related questions and prompts. We focus on their ideal outputs and interactions with the user, not the techniques needed to achieve this behavior. We also provide specific recommendations for how developers can best leverage the Elections API to strengthen their own generative AI tools and help build a more responsible information environment.