His agent-built pipeline shipped 319 YouTube videos; the median one got 268 views
Since July 2026 a Japanese creator has run a political clip channel with a pipeline the AI built: it watches source channels, fetches new videos, transcribes them locally, picks highlights from voice peaks and wording, fixes subtitle typos and names, makes thumbnails and titles, exports long videos and Shorts, uploads them unlisted, then collects view and retention data to feed the next round. In 3.5 months it shipped 319 videos for about 1.05 million total views and 1,080 subscribers, though the median long video reached only 268 views; he publishes the failures too, including the agent claiming 'fixed' when it was not.
How it works
- Pipeline watches permitted source channels for new uploads
- Fetches and transcribes each video on his PC
- Selects highlight moments from audio peaks and wording
- Builds subtitles and corrects names and typos
- Generates thumbnail and title
- Exports long cut and Shorts version
- Uploads unlisted to YouTube
- Owner reviews and presses publish
- Pipeline gathers views, click-through and retention to inform the next picks
Why it’s worth knowing
The headline number and the honest number are in the same post: a million total views built on a median of 268, with the agent's false 'fixed it' claims listed as a recurring incident.
Where it’s from
Summarized from a public post on note.com. See the original ↗