Open standards for AI-assisted facilitation and deliberative democracy: portable method specs, plus the research and reference behind them — all open source.
Seminars
The OFL seminar series brings together experts in facilitation, deliberative democracy, and AI-assisted dialogue.
Browse all seminars | Recent: Jorim Theuns, Cecile Green, Andy Paice, Alice Siu, Jigsaw, Martin Carcasson
Research
Key papers and research topics supporting OFL development.
| Paper | Description |
|---|---|
| WHoW Framework | Cross-domain moderation analysis (Chen et al. 2024) |
| Fora Corpus | 262 facilitated dialogues from MIT (Schroeder et al. 2024) |
| D-agree Platform | Automated facilitation agent at crowd scale (Ito et al. 2022) |
| Facilitation in the AI Era | Ethnographic study of 22 expert facilitators (Jigsaw 2025) |
| Cueing the Crowd | LLM conversational cues for brainstorming (Rayan et al. 2025) |
| LLM Facilitation Survey | Comprehensive survey on LLM-based facilitation (Korre et al. 2025) |
| Generative Social Choice | LLM-augmented democratic processes (Fish et al. 2025) |
| AI Moderation Chatbots | AI moderation and chatbot facilitation |
| ConvoKit Datasets | Datasets for facilitation research |
More: LLM vs Human Facilitation | Techniques | Mini-Publics | Storytelling
Knowledge Base
Core concepts and definitions shared across OFL projects.
- Glossary - Term definitions
- Conversation Types - Deliberative, generative, transformative
- AI Facilitation Approaches - Fine-tuning vs inference-time
- Teardowns - How many platforms orchestrate AI facilitation agents
Architecture
OFL’s core artifact is the method spec: a portable, forkable definition of a facilitation method that any capable runtime can execute (Harmonica is the reference implementation). Each method spec has two halves:
- A protocol — the method itself, as a forkable spec: its stages, roles, facilitator prompts, and what carries between them. Fork it, adapt it, run it on any capable runtime.
- Evals — how you know it ran well: rubrics scored against the conversation, interoperable with weval’s open eval format.
Nine methods are published in the method-specs registry; browse them under protocols.
The rest of the library is the research and reference these specs draw on — abstract patterns (facilitation methodologies described with the Why-How-Who framework) and teardowns (how many real platforms orchestrate AI facilitation agents today).
A standard owned by facilitators
Good facilitation has to be defined by the people who facilitate. OFL is built so the definition they produce, the evaluations and the knowledge, stays a shared resource they own and govern, closer to a data cooperative than to data a platform extracts. The specs also map to the field rather than walling it off: each one cross-maps to Group Works patterns and IAF competencies.
How the standard is owned and governed →
Evaluation
Every method spec is paired with evals: per-stage, per-method rubrics scored against real conversation turns, so “good facilitation” is inspectable and measurable by the method’s own logic rather than assumed. Interoperable with weval’s open format.
- Evaluation frameworks: how the per-stage evals work, and how the criteria stay honest
- Why-How-Who framework: a research lens for comparing methods across traditions
Support
Donate on Giveth — Help fund research, development, and community building.
Contributing
- Add research summaries
- Propose evaluation criteria
- Submit pull requests with documentation