Cross-meeting memory

MeetCrew remembers meetings as structured records, not raw recordings — and it identifies people by platform identity, never by their voice.

What gets remembered

After a meeting ends, MeetCrew extracts structured records from the transcript: decisions, open questions, action items, notable statements, and the topics, people, and projects they involve, each carrying owners and dates. Memory is per deployment. Each teammate remembers only the meetings it attended, and one teammate’s memory is readable by another only when you explicitly configure that sharing.

Isolated and searchable

Every tenant’s memory is isolated from every other tenant’s — the separation is structural, not a filter you have to trust. Within a tenant, your teammates query memory through a search interface — structured search, natural-language search, and on-demand entity summaries — so a teammate can recall what was decided about an account or who owns an outstanding item.

No voiceprints

MeetCrew stores no voice-derived data of any kind. To recognize the same person across meetings, it uses the identity the meeting platform supplies for that person’s account — their Microsoft Entra account on Teams, their Zoom account on Zoom — never a display name and never a voice template. On Teams, people in your own organization are recognized across meetings. On Zoom, MeetCrew can tell only who is in the meeting host’s Zoom account, so it recognizes those people as your organization’s only in a meeting it created through your Zoom connection, or one where you confirmed, when sending the teammate in, that the host signs in to a Zoom account your organization administers; in any other Zoom meeting everyone, your own staff included, is treated as a guest. A guest — someone signed in to another organization’s Teams, or anyone in a Zoom meeting who isn’t signed in to the host’s Zoom account — is recognized across meetings only when the teammate’s Link external guests across meetings setting is on; otherwise they are recognized within a single meeting only. A change to that setting applies from the next meeting the teammate joins, and turning it off does not erase what the teammate already remembers. Speakers without platform identity are treated as anonymous, first-class participants. Where a statement is attributed to a named person, the name comes from the identity the meeting platform supplies, never from voice.

Retention and deletion

Transcripts and structured memory are kept for 24 months. In v1 the period is fixed, and your console shows it read-only. When it ends, the meeting’s transcript and the memory extracted from it are deleted. A data-subject deletion request removes the person from the structured memory and the search index, and keeps the raw transcript as a non-queryable record until its retention period ends. A “don’t remember” command deletes the meeting’s transcript when the meeting ends and stops any memory being extracted from it.