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