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