converge · Decision Making, Communication · 60–120 min · 30-5000 people · low energy

AI-Clustered Consultation (Talk to the City)

People answer an open question in their own words. An AI pipeline extracts the individual arguments, groups similar ones into clusters and sub-clusters, and links each back to the original quotes. The organisers check the clusters against the quotes, share the map back with participants to confirm they recognise their views, and use it to structure a live discussion or decision.

When to use AI-Clustered Consultation (Talk to the City)

Use when you have far more open-ended input than any group could read, and need to see the full range of views without reducing it to a multiple-choice poll.

What it solves

Large consultations collect thousands of comments that nobody reads, so the summary reflects whoever wrote the report.

How to run AI-Clustered Consultation (Talk to the City), step by step

  1. Write one open, neutral question and collect free-text answers or interviews over one to three weeks.
  2. Run the responses through the clustering tool to extract arguments and group them.
  3. A small team checks clusters against the original quotes, fixes labels and splits merged views (60-120 min).
  4. Share the map with participants and ask: is your view here, and is it described fairly? Adjust (async, one week).
  5. In a live session, walk through the main clusters and points of agreement, and choose which disagreements to work on (60-90 min).
  6. Publish the final map with the decisions taken.

Materials needed

  • Survey or interview tool
  • AI clustering tool such as Talk to the City
  • Human review team
  • Shared report page

Facilitator tips

  • Always let readers click from a cluster to the real quotes. That is what makes the map trustworthy.
  • Budget human time for checking; the authors say current models are not good enough for fully automatic processing.
  • Watch for nuanced answers that the AI split into contradictory pieces.

Common pitfalls

  • Skipping the participant check, so people do not recognise themselves in the result.
  • Treating cluster size as a vote count when the sample was not representative.

Variations

  • Use it on transcripts from several parallel table conversations to merge what was said in each.

Running it online or hybrid

Input is collected async through an open-text survey, interview transcripts or meeting notes. The AI pipeline runs between rounds. The live session to review clusters can be online, hybrid or in the room.

What it produces

An opinion map of clusters and sub-clusters with linked original quotes, and a list of areas of agreement and disagreement.

Origin

Talk to the City is an open-source tool by the AI Objectives Institute (introduced by Bruno Marnette and Colleen McKenzie, 2023) for analysing large sets of open-ended public input. — source

Build a session around AI-Clustered Consultation (Talk to the City)

METODIC places AI-Clustered Consultation (Talk to the City) inside a complete, timed session plan — agenda, worksheets, facilitator guide and slides — matched to your group and goal.

Generate a session with AI-Clustered Consultation (Talk to the City) · Try METODIC free