AI Facilitation Workflows

A library of agent workflow definitions documenting how real platforms orchestrate AI agents to facilitate group processes. Each workflow 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

Workflows are one of three complementary layers:

  1. Patterns (this knowledge base) — abstract facilitation methodologies
  2. Agent Skills — executable instructions following the Agent Skills spec
  3. Workflows (this page) — how real platforms wire agents into complete facilitation systems