Just Now Possible

Powering Government with Community Voices: How ZenCity Built an AI That Listens

Listen Later

Guests

  • Noa Reikhav, Head of Product, Zencity
  • Andrew Therriault, VP of Data Science, Zencity
  • Shota Papiashvili, SVP of R&D, Zencity

    • In this episode

    • How Zencity helps local governments reach, understand, and act on community voices
    • Turning thousands of survey responses, social posts, 311 calls, and news items into usable insight
    • Building a data model with multiple layers—raw data → elements → highlights → insights → briefs
    • Why context is everything when building AI for civic use
    • How the team designed their AI assistant using MCP servers to safely negotiate data access
    • Balancing agentic flexibility with deterministic trust
    • Evaluating accuracy when latency matters: how they think about evals, citations, and model-as-judge systems
    • Using workflows like annual budgeting or crisis communication to deliver AI-generated briefs to the right people at the right time
    • Why government workflows are the ultimate “jobs to be done” framework

      • Takeaways

      • Data architecture defines what AI can do.
      • Guardrails and transparency matter more than flashy outputs.
      • Agentic systems become powerful when grounded in real, multi-tenant data.
      • AI in the public sector can make democracy more responsive—if built responsibly.

        • Chapters:

        00:00 Introduction to the Team
        00:16 What is ZenCity?
        01:26 AI in ZenCity's Platform
        06:00 Survey Methodologies and Use Cases
        09:01 Community Voices and Social Listening
        14:36 Workflows and AI Integration
        22:15 Annual Budget Planning Workflow
        32:44 Data Layers and Sentiment Analysis
        33:53 Post Interaction Surveys and Resident Engagement
        34:20 Data Enrichment and Sentiment Analysis
        35:14 Topic Modeling and Semantic Search
        36:50 AI Content Summarization and User-Driven AI Assistant
        38:53 Highlights, Insights, and the Gold Layer
        41:19 Challenges and Solutions in AI Data Processing
        46:47 AI Assistant and Guardrails
        01:05:27 Future Developments and Orchestration Layer
        01:06:44 Conclusion and Final Thoughts

        ...more
        View all episodesView all episodes
        Download on the App Store
        Just Now PossibleBy Teresa Torres