Search and evidence

Find what was said in your stored meetings, read the exact passage with a reference back to it, see what you discussed with a person, link meetings to events and people, and preview a follow-up task tied to its source.

Start with a questionCopy Anchor Link

Find discussions about Research Example in my stored meetings. Show the dates and the passages
about the launch decision. Include references and tell me which transcripts or periods are missing.

The agent should identify the meeting, open the matching passage and distinguish a recorded participant from a person merely named in the text. Check the surrounding cues before accepting a decision or promise. An empty search result does not prove that a discussion never happened.

For a quick local word search:

zm meetings search "example plan" --json

This searches the stored profile, not Zoom's live history. Pull or import missing meetings first. For indexed matches with word forms and continuation inside long transcripts, use the next steps.

Search stored meetingsCopy Anchor Link

For bounded text search, first index queued meeting records explicitly, then page through hits:

zm meetings search-index --limit 100 --max-read-bytes 4194304 --json
zm meetings search-index --limit 100 --yes --json
zm meetings search-page "example plan" --limit 20 --json
zm meetings search-page "example plan" --limit 20 --after <nextCursor> --json

Indexing previews by default; --yes applies one bounded batch and --dry-run overrides it. Repeat until the applied receipt reports remaining: 0. A search read never processes indexing work. Its coverage reports pending indexing and unknown index/archive completeness. All normalized query words must match, through literal prefixes or the stored stemming configuration. The default configuration adds English, Russian and Spanish word stems; a store can disable or customize it. This is keyword search, with no semantic model or query operators. --meeting-id, --since and --until narrow the selected account. The opaque cursor belongs to that account, query and filters; it can continue inside a large transcript. JSONL preserves the complete page, including nextCursor.

meetings search keeps its existing literal prefix transcript search over stored transcripts, chat and summaries; --since, --until, --event-id and --series-id narrow it. meetings people <query> finds participants by name or email. search all uses the shared search service and searches only meetings by default:

zm search all "example plan" --limit 100 --max-meetings 100 --json
zm meetings evidence meeting:3/15/20/0 --cues 100 --bytes 65536 --json
zm meetings context person:7 --meetings 10 --scan-limit 1000 --json
zm meetings task-proposal meeting:3/15/20/0 --kind promise --json

Broader search requires explicit --only messages,mail,notes,meetings. Message reads use the selected local account; mail reads include stored email accounts; notes are global to the shared store. Meeting matching uses word prefixes; unsupported meeting syntax or exact queries are reported as skipped. A meetings-only continuation uses the returned meetings.nextCursor as --meeting-cursor '<json>', bound to its account and query. JSONL emits one complete report, retaining skips, coverage and cursors.

Read evidenceCopy Anchor Link

Meeting references have the form meeting:<account>/<meeting>[/<transcript>[/<cue-position>]]. They are restricted to the selected local account. Transcript references retain historical revision identity. Evidence bounds both returned content and database reads; resume with its returned cue reference using --after, or its revision cursor using --after-transcript-id. These continuation options are mutually exclusive. --max-read-bytes defaults to 4 MiB per page and --max-transcript-pages bounds revision scanning, including empty revisions. Follow the returned continuation and completeness fields rather than assuming a bounded response is exhaustive.

Person contextCopy Anchor Link

Person context uses stored identity links and account presence, without matching speaker names. A person linked to a meeting is not necessarily a speaker. Pending derived indexes or bounded scans can leave context incomplete. Link a participant to a person explicitly with meetings link-person.

Link meetings to events and peopleCopy Anchor Link

Stored meeting references use meeting:<accountId>/<meetingId>. A retained transcript appends its revision id, and a cue appends its position. Event and person linking accept root references:

zm meetings link-event meeting:1/1 --event-id 1 --expected-event-id none --json
zm meetings link-event meeting:1/1 --event-id 1 --expected-event-id none --yes --json
zm meetings link-person meeting:1/1 --participant-id 1 --person 1 --expected-person none --yes --json

These local changes preview by default; --yes applies once and --dry-run overrides it. Expected link options reject a stale decision. Use --event-id none to unlink an event. Person linking moves only the selected participant's identity; it never guesses a person from a speaker name. Target people must have authorized account observations. Explicit --target-accounts <ids> adds account ids for that lookup. Profile labels group local data and do not authenticate a remote identity.

Notes, tags and memories with memoCopy Anchor Link

Use memo for the existing shared notes, tags and memories interface. Both tools use the same store; point MESSAGING_STORE at the same file if it is overridden. For a Zoom profile named AliceExample, its provider account key is zm-profile:AliceExample:

memo tags add planning --meeting 1 --provider zoom --account zm-profile:AliceExample --json
memo tags remove planning --meeting 1 --provider zoom --account zm-profile:AliceExample --json
memo notes add --text "Alice Example follow-up" --meeting 1 --provider zoom --account zm-profile:AliceExample --json
memo notes list --about meeting:1/1 --json
memo facts add "Alice Example will review" --type promise --scope work --subject meeting:1/1 --evidence meeting:1/1/1/0 --json
memo facts list --subject meeting:1/1 --json

Memo's add/remove commands write directly to the local store. Owner-authored facts are accepted; agent-authored facts submitted through Memo MCP stay proposed until reviewed. Memories keep summaries, digests and preferences separately. Meeting revision and cue evidence remains addressable after corrections. The references and ids above are invented examples; use ids from your stored meetings and selected account.

Task proposalsCopy Anchor Link

Task proposals support question, request, mention and promise; applied: false and persistence: "proposal-only" mean no task was created. zm does not find commitments on its own: an agent reads transcripts and evidence, then proposes a task for the passage it chose.

Before saving notes, tags or facts, ask your agent to show the existing project aliases and labels, then propose the links it intends to add. Review possible tag synonyms rather than creating another label for the same subject. Memo is installed separately and must use the same database path.

Searching by meaning instead of by words is covered in topic search. For an upcoming call, combine these cited passages with the Zoom schedule.