Skip to content
Y
Back
AI Content Pipeline for YouTube Content RepurposeLive

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.

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.

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.

[02]Architecture
creatorjot — architecture.mmd
Click to zoom · drag to pan
[03]Decisions
Score-and-select transcript segmentation over single-pass prompting

WhyFull-transcript prompting collapsed JSON structure, fabricated timestamps, and missed extraction targets on long-form input.

AlternativeA single prompt over the entire transcript

ApproachThe 'Transcript Checkpoints' algorithm partitions transcripts into discrete segments, each scored 1–10 by the model for relevance, automatically selecting the highest-signal angle.

TradeoffAdds a scoring/selection pass and more pipeline complexity than a single call.

OutcomeIn production — structural prompt constraints eliminated JSON collapse and timestamp fabrication.

Distributed pg-boss job pipeline over inline request handling

WhyAI transcript extraction and content generation run long enough that handling them inline would block API responses.

ApproachA pg-boss distributed job pipeline separates the API, transcript workers, and generation workers into independent processes, with progress reported back over Supabase Realtime/SSE.

Tradeoff5 independent services to deploy and operate instead of one.

Outcome97+ Lighthouse score across the multi-service Railway deployment.

[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