Talk to the City is an open-source AI tool that distills insights from large-scale public input. It helps large groups of people coordinate by understanding each other better, faster, and in more depth.
We use Large Language Models (LLMs) to analyze broad themes from large datasets of free-text responses, summarize specific claims, and link those claims back to exact quotes. We create an interactive report from the results, combining all scales of analysis.
I drove the platform's comprehensive redesign, including information architecture, design systems, visual identity, and interaction patterns.I collaborated with engineers to refine the LLM pipeline that extracts and clusters arguments from participant responses.Through user research with civic organizations and government partners, I iteratively improved the interface to make complex deliberation data accessible to non-technical users.
The tool has been deployed at national scale with Taiwan's Ministry of Digital Affairs and has processed input from over 10,000 participants across 100+ organizations. Beyond the core platform, I researched and prototyped experimental tools for collective coordination, including Discourse Mapper, Crux Dialogue, and Agent Parliament.
Taiwanese AI Assemblies Report | Talktothe.city by AI Objectives Institute
Reports with new cruxes tab:
WIRED, A Privacy Hero’s Final Wish: An Institute to Redirect AI’s Future
Protocol Labs, Scaling Deliberations Beyond Outcomes