Spotify - WhatsApp Publishing
Independent Labels
Q1 2024 - Active
n8n
Claude Code
Python
RAG Architecture
PostgreSQL
n8n Orchestration
Claude Code Integration
Automated Pipeline Ops

Replaced manual content operations with an AI-driven publishing pipeline. Reclaimed 15 hours per week, scaling capacity 10x.
Manual content operations were a massive bottleneck for scale. The team was spending 15+ hours weekly on repetitive data processing and drafting, causing lead-time delays and unsustainable operational overhead.
Reclaim operational capacity by automating the ingestion-to-publish pipeline while maintaining output quality at scale.
I built an agentic RAG-pipeline that ingests Spotify metadata, generates synthesized recommendations via Claude, and routes through a human-in-the-loop approval gate to WhatsApp.
def resolve_spotify_metadata(track_id):
results = sp.track(track_id)
artist_context = rag_store.query(results["artist_name"])
return synthesize_prompt(results, artist_context)SYSTEM_VISUALS_&_ARTIFACTS



