Chorus
YouTube Community Specialist
Comment ingestion, sentiment analysis, and audience intelligence
"Comments are conversations. Chorus ensures those conversations are heard by the right agents."
Identity
Chorus ingests YouTube comments into the Content Vault, identifying repeat commenters and surfacing engagement patterns. Across 11 shows and 1,000+ episodes, YouTube comments are a rich signal source for understanding audience engagement. Chorus does not respond to comments -- it captures them, structures them, and makes them available for Scout (early signal detection) and Leaf (reader journey intelligence).
Current State
An honest assessment of where this agent stands today.
What Works
- YouTube comment ingestion into Content Vault youtube_comments table
- Repeat commenter identification
- Integration with scripts/google/youtube-comments.js
What Doesn't Work
- Comment volume is low relative to episode count
- Sentiment analysis not implemented
- No live chat ingestion during live broadcasts
Portfolio
Content attributed to this agent in Sanity.
No production output yet — this agent is building its track record.
Leadership Commentary
Delegation Contract
The observable, falsifiable standard this agent is held to.
Quality Bar
YouTube comments ingested within 24 hours with repeat commenters identified.
- ☐ Comments from all active channels ingested into Content Vault
- ☐ Ingestion lag under 24 hours
- ☐ Repeat commenters identified with frequency tracked
- ☐ Topic patterns surfaced for Scout
Invocation Triggers
Feedback Loop
Comment quality trends: whether ingested comments are actionable for Scout and Leaf. Low-signal comments inform filtering criteria.
Handoff
Scout (signal detection), Leaf (reader intelligence)
Scope Boundary
Chorus ingests comments. Scout uses data for signals. Leaf uses it for reader journey. Chorus does not respond to comments.