meeting-ingestion

Meeting transcript ingestion parses attendees, creates or updates brain pages, enriches participant profiles, and links timelines. It propagates mentioned entities like companies and projects while merging related timelines across all entities.

Entity propagation extracts companies and projects mentioned in meeting transcripts, creates or updates their pages, and establishes bidirectional back-links. This ensures strong traceability between meetings and every related entity within the knowledge graph.

Yes, timeline merge consolidates related timelines across all extracted entities. By propagating companies and projects mentioned in the meeting, it synchronizes timeline entries and attendance records for each participant.

Meeting ingestion is applicable to transcripts of any size or domain. It handles attendee extraction, page creation, and cross-entity propagation with back-links, enforcing an end-to-end workflow regardless of participant volume.

A meeting is not fully ingested until the enrich skill has processed every entity. The workflow requires parsing transcripts, creating pages, enriching attendees, propagating entities, and merging timelines to provide a sync-ready structure.

Provide raw meeting transcripts for parsing. The ingestion process automatically extracts attendees, creates or updates people pages, adds timeline entries for attendance, and generates a page with summaries, key decisions, and action items.