An AI content intelligence pipeline that watches 51 YouTube channels so I don't have to. Daily-driven. The video at the top of this site is one of its outputs.
Every day, a scheduled job polls the YouTube Data API for new uploads across a curated set of strategy/AI/engineering channels. New videos are transcribed (Whisper, GPU-accelerated), classified, and run through two Claude models in sequence — one for a fast TLDW summary, one for a deeper analytical writeup. Output is committed to a git repo so every artifact is versioned, diffable, and immediately queryable by other Claude sessions.
For every video, three markdown files land in a per-channel directory:
transcript.md — frontmatter-tagged full transcript with video ID, channel ID, published date, YouTube URL.summary.md — TLDW one-paragraph, watch/skip recommendation, key insights (3–5 bullets), action items.detailed.md — multi-section deep analysis: core thesis, key points, tools mentioned, problems highlighted, notable quotes, creator perspective.The directory layout is deliberately filesystem-native (channels/{channel-slug}/{date}_{video-id}/) so any Claude Code session can grep, glob, or summarize across the corpus without hitting a database.
Most "AI summarizer" tools are one-shot consumer apps. TLDW is a production pipeline: it has retry/backoff, state persistence, dual-model cost routing (Haiku for cheap summarization, Sonnet for analysis), and a cross-channel search skill that lets me ask "what did the strategy channels say about agent legibility this month?" without re-reading 50 videos.
This is the same operational discipline that managed 100+ Windows Mobile builds — branch isolation, idempotent steps, observable failures — applied to LLM workflows.
nate-transcript-digest for cross-channel synthesis