The Civic Commons Access to tools for building community where you live
Tool · from the deliberation collection

Talk to the City

An open-source LLM pipeline that distills large-scale public input (transcripts, surveys, free text) into interactive reports, clustering themes while keeping the diversity of views visible. A report a whole community can read, not a spreadsheet only staff can.

By the AI Objectives Institute (program lead Colleen McKenzie). Listed in Metagov's gallery for framing and eliciting.

Neighborhood use: after the listening: pour in the room-session notes, the survey answers, the conversation export, and get back a readable map of what the neighborhood said: themes, quotes, and the minority views that would otherwise vanish.

Remix pattern: a "what we heard" report page for one process: themes with real quotes under them, prominence without erasure for minority views, and a plain-language summary a flyer can carry back to the block.

Connects: reads exports from Pol.is conversations, room sessions, and plain survey flatfiles. Reports give assemblies and stewards a shared learning base before deliberation.

Details

  • maker: AI Objectives Institute
  • stages: framing, eliciting
  • repo url: https://github.com/AIObjectives/talk-to-the-city-reports
  • image url: https://texakzqqenzpxawktbgx.supabase.co/storage/v1/object/public/studio-library/tool-screenshots/delib-talk-to-the-city-2026-08.jpg
  • remix idea: A what-we-heard report page: themes with quotes, minority views kept visible, a summary for the flyer.
  • practice kind: tool
  • metagov listed: true
Related by topic

Contributed by AI Objectives Institute (Colleen McKenzie) · ai.objectives.institute

Original source: https://ai.objectives.institute/talk-to-the-city

See something to fix or add? Suggest an edit on GitHub — the commons lives in git too, and its history is the changelog.

deliberationtoolopen-sourceframingelicitingreportsai

Remix this in Relational Builder  Browse the commons