Meeting Sync: Transcripts That Become Brain Pages
Every meeting is automatically recorded, transcribed, and imported into your brain with attendee detection, entity propagation, and action item extraction. You never take notes again. The brain remembers what was said, who said it, and what needs to happen next.IMPORTANT: Instructions for the Agent
You are the installer. Follow these steps precisely. Why this is high-value: Meeting transcripts are the richest signal source. A 30-minute meeting mentions 5-10 people, 3-5 companies, and generates 2-3 action items. Each one should propagate to the relevant brain pages. Without this recipe, meetings are black holes. With it, every meeting compounds the brain. The flow:- Circleback records and transcribes the meeting (automatic, no user action)
- The sync script pulls completed meetings from Circleback API
- Each meeting becomes a brain page at
brain/meetings/{YYYY-MM-DD}-{slug}.md - YOU (the agent) propagate entities to people/company pages
Architecture
Opinionated Defaults
Meeting page format:- Skip calendar resources (e.g., “YC-SF Conference Room”)
- Skip group addresses (e.g., “team@company.com”)
- Extract display names, not email addresses
source_id already exists
in the brain, skip it. No duplicates.
Prerequisites
- ModusBrain installed and configured (
modusbrain doctorpasses) - Node.js 18+ (for the sync script)
- Circleback account (https://circleback.ai) with meetings recorded
Setup Flow
Step 1: Get Circleback API Token
Tell the user: “I need your Circleback API token. Here’s where to find it:- Go to https://app.circleback.ai
- Click your profile icon (top right) > Settings
- Go to the API section
- Generate a new API token (or copy existing)
- Paste it to me
Step 2: Set Up the Meeting Sync Script
- List meetings — call Circleback API
list_meetingswith date range (SSE response format, parse streaming events) - Extract meeting data — title, attendees, transcript, duration, date
- Slugify title — “Weekly Team Sync” →
weekly-team-sync - Check for existing — skip if
brain/meetings/{date}-{slug}.mdexists - Format as markdown — frontmatter + key points + action items + transcript
- Filter attendees — remove calendar resources, groups, extract display names
- Infer tags — from title keywords (e.g., “board” → board, “1:1” → 1-on-1)
Step 3: Run First Sync
2026-04-10-weekly-team-sync.md.
Tell the user: “Found and synced N meetings. Here are the most recent: [list 3].”
Step 4: Import to ModusBrain
Step 5: Propagate to Entity Pages
This is YOUR job (the agent). For each meeting:- Read the meeting page — understand who attended and what was discussed
- For each attendee, check brain:
modusbrain search "attendee name"- If page exists: append timeline entry:
- YYYY-MM-DD | Meeting: {title}. Discussed: {key points relevant to this person} [Source: Circleback] - If no page and person is notable: create a brain page
- If page exists: append timeline entry:
- For each company mentioned: update company page timeline
- Action items: if the meeting has action items, ensure they’re tracked
- Cross-reference with calendar: link meeting page to the calendar event
- Sync:
modusbrain sync --no-pull --no-embed
Step 6: Set Up Cron
Sync 3x daily on weekdays:Step 7: Log Setup Completion
Implementation Guide
These are production-tested patterns from syncing 280+ meeting transcripts.SSE Response Parsing
Circleback returns JSONRPC 2.0 over SSE (Server-Sent Events):- Strip
data:prefix - Parse the SSE line as JSON
- Drill into
result.content[0].text - Parse THAT as JSON again (it’s a string containing JSON)
Idempotency (Double-Check)
Auto-Tagging from Meeting Name
Meeting Page Structure
Git Commit After Sync
What the Agent Should Test After Setup
- SSE parsing: Verify
SearchMeetingsreturns parseable data (the double-JSON parsing is the most common failure point). - Idempotency: Sync a meeting, add a note to the file manually, sync again. Verify the meeting is skipped (not re-created or overwritten).
- Attendee filtering: Sync a meeting that includes a conference room in attendees. Verify the room doesn’t appear in the attendee list.
- Auto-tagging: Sync a meeting named “1:1 with Sarah”. Verify tag is
1on1. - Transcript formatting: Verify speaker names and timestamps are formatted correctly (speaker bold, timestamp in parentheses).
- Git commit: Sync 2+ meetings. Verify the git commit message includes the count.
Cost Estimate
Troubleshooting
No meetings found:- Check that Circleback has recorded meetings (open the Circleback dashboard)
- The Circleback bot must join the meeting for recording to work
- Check the date range:
--days 30to widen the search
- Some meetings may not have transcripts (e.g., no audio, bot was removed)
- Check the Circleback dashboard for the specific meeting’s status
- The sync script checks for existing files by source_id
- If duplicates appear, the idempotency check may be failing
- Delete duplicates manually and re-run sync