---
title: "Video to published pipeline"
canonical: "https://agenticfeats.com/c/video-to-published-pipeline-claude-cowork/"
agents: ["Claude Cowork"]
evidence_grade: "C"
outcome: "partial"
job_type: "Marketing and Content"
industry: "Youtubers"
roles: ["Founder or owner", "Marketing"]
source_url: "https://seancdavis.com/posts/how-i-built-a-video-to-published-pipeline-with-claude-cowork"
published: "2026-10-13"
updated: "2026-10-13"
---

> From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt

# Video to published pipeline

Claude Cowork transcribes a dropped-in video, proposes titles, drafts a blog post, uploads to YouTube, and schedules social posts while the author reviews each step.

Result: The author ran the full pipeline several times; it still takes over the one-hour daily goal, down from a typical 3-4 hours by hand.

## How it was set up

Claude Cowork project with an inbox folder, local Whisper transcription, a style guide, GitHub pull requests with Netlify previews, Figma thumbnail template, YouTube upload, and a scheduled task for Bluesky.

## Worth knowing

Each run still needs small system tweaks and takes over an hour. The author says the daily-publishing hypothesis is not yet proven.

## Evidence note

Author's own account of the workflow; no demo or numbers beyond rough time estimates

## Sources

- Original: https://seancdavis.com/posts/how-i-built-a-video-to-published-pipeline-with-claude-cowork

## The receipt

- Agent: Claude Cowork
- Evidence: Claim (grade C, claim only)
- Outcome: Partial
- Job type: Marketing and Content
- Industry: Youtubers
- Roles: Founder or owner, Marketing
- Source: Blog
- Added: 2026-10-13