Skip to main content
Meetings is a separate, self-contained service — a detached domain with its own API. It does one job end to end: capture, store, and access meeting data, delivered in real time from the platforms. Run it entirely on its own as a meeting-capture backend — no agents required. A bot joins the call and captures it natively in real time; the transcript is stored and served over the API as it happens — live and historical, speaker-attributed, from Google Meet, Zoom, and Teams. That is the whole product on its own. It also composes with the agent domain — the transcript becomes knowledge agents act on — but that is a composition, not a dependency: meetings stands alone. How the two connect (the transcript.v1 → agent bridge) lives in one place: Modules & seams. Mechanically, the bot is a browser container spawned by the runtime — the same runtime an agent runs in.

​
Platforms

Vexa joins natively, in real time, with no plugins or host configuration — the bot attends like any participant: Drive it programmatically with the Meetings API — send a bot, then stream the speaker-attributed (diarized) transcript.

​
From transcript to knowledge

  1. The bot captures audio; transcription produces a real-time transcript.v1 stream.
  2. The transcript compiles into the person’s workspace as Markdown.
  3. Agents read it like any other file — and act on it:
    • After the meeting — a dispatch writes notes, decisions, and action items as workspace files.
    • During the meeting — a live dispatch surfaces proactive cards (new person, action item, decision); see Meeting copilot.