Skip to main content
This recipe helps an agent prepare for the next occurrence of a recurring meeting without loading every transcript.
1

Find the latest meeting

Call list_meetings with a short title query, or run:
anarlog --json meetings list --query "project sync" --limit 10
Resolve the latest relevant meeting ID from the results.
2

Read its structured context

Call get_meeting, or run:
anarlog --json meetings get MEETING_ID
Extract open action items, decisions in notes or summaries, participants, and the meeting’s series ID.
3

Review recurring history

Call get_recurring_meeting_history with the meeting ID, or run:
anarlog --json meetings history MEETING_ID --limit 5 --offset 0
Fetch detail only for earlier meetings that appear relevant.
4

Use transcript evidence sparingly

If a decision is unclear, call get_meeting_transcript with limit: 200, or run:
anarlog --json meetings transcript MEETING_ID --limit 200 --offset 0
Continue from next_offset only when needed.
5

Produce the brief

Keep the output focused on unresolved actions, prior decisions, discussion topics, and useful context for named participants. Distinguish meeting evidence from your own inference.