Teardowns of how real platforms orchestrate AI agents to facilitate group processes. Each captures agent roles, participant interaction models, stage pipelines, and data flow.

Inclusion criteria: Does an AI agent actively conduct, guide, or mediate a conversation or group process? Tools that only collect votes, structure arguments, or analyze data post-hoc are out of scope.

Source: workflows repo

Platforms

PlatformSourceTypeAgentsScale
Anthropic InterviewerresearchedAsync 1-on-1 interviewsInterviewer + Analyst1,000+
Bot MediationresearchedAI dispute mediationAI Bot Mediator2 (bilateral)
ComplexChaosinferredAsync organizational alignmentDialogue Agent + Pattern Synthesizer5-200
CrowdSmartresearchedGenerative Collective IntelligenceCollective Reasoning Agent + Pairwise Engine + Private LM10-10,000
Habermas MachineverifiedIterative consensusStatement Generator + Critique Processor5-1,000
HarmonicaverifiedAsync structured deliberationFacilitator + Cross-Pollinator + Synthesizer3-500
JunoinferredUnscripted AI interviewsInterviewer + Thematic Analyst5-1,000
ListeninferredAI research pipelineRecruiter + Interviewer + Analyst10-1,000
OrchidearesearchedAI workshop facilitationAI Ideator + Proposal Drafter3-500
OutsetresearchedMultimodal AI interviewsAI Moderator + Fraud Detector + Analyst10-5,000
Parlay IdeasresearchedClassroom discussion facilitationParlay Genie + Participation Tracker5-40
RemeshinferredReal-time collective dialogueClustering Engine + Consensus Predictor + Human Moderator20-5,000
Talk to the CityverifiedElicitation + clusteringWhatsApp Bot + Topic Clusterer + Visualizer10-10,000
ThinkscaperesearchedSwarm intelligenceConversational Surrogates + Orchestrator14-400

Source Types

  • verified — documented from open-source code or detailed published methodology
  • researched — documented from academic papers or detailed technical write-ups
  • inferred — reconstructed from public marketing and website descriptions

Workflow Schema

Each YAML file describes:

  • Agents — roles like facilitator, synthesizer, clustering engine, with type (llm, human, hybrid, system)
  • Participants — input mode (text/voice/vote/mixed), interaction style, synchronicity, scale, anonymity
  • Stages — ordered pipeline: input → processing → memory → output
  • Patterns — which OFL facilitation patterns the platform implements (e.g., cross-pollination, Delphi)

See the schema definition for full details.

How This Fits into OFL

Teardowns are reference — a map of how the field actually builds AI facilitation today. They inform the method specs OFL is defining (portable protocols + their evals), alongside the evaluation frameworks and the rest of the knowledge base.