Notes on AI-facilitated structured conversation: product updates, case-study deep-dives, and what we're learning from running sessions in the field.
Sessions now chain into full methodologies, cross-pollinate between participants, and improve between runs. Here's what changed and why — with gov/acc as the public sensemaking case study.
We built automated quality scoring for Harmonica's AI facilitator, then discovered the scoring itself was wrong in three distinct ways. The fixes took longer than the original prompt improvements — and mattered more.
Anthropic just shipped an AI feature called Dreams. Organizations are missing the same rhythm — and paying six figures every few years for it.
