AI Content Pipeline for YouTube Content Repurpose

CreatorJot

An AI-powered pipeline that repurposes YouTube content into platform-ready assets using a custom transcript segmentation algorithm and distributed job orchestration.

[01]Overview

Designed and built an end-to-end AI content repurposing system that extracts high-signal angles from YouTube transcripts and generates hooks, summaries, and key moments tailored to each platform.

[02]Challenge

LLMs collapsed JSON structure, fabricated timestamps, and missed extraction targets when processing long-form transcripts — requiring a principled approach to prompt engineering and output validation.

[03]Solution

Designed a custom 'Transcript Checkpoints' algorithm that partitions transcripts into discrete segments, each scored 1–10 by the model for relevance, automatically selecting the highest-signal angle. Paired with a pg-boss distributed job pipeline enforcing forbidden phrases, verbatim evidence usage, and platform-specific formatting constraints.

[04]Impact

→97+ Lighthouse score across multi-service Railway deployment
→5 independent nodes: API, workers, frontend
→Real-time progress tracking via Supabase Realtime/SSE
→Structural prompt constraints eliminating JSON collapse and timestamp fabrication
→Concurrent AI transcript extraction and content generation via distributed job pipeline

Back to work