All writing

Field notes,

Finding articles that an automated publishing system skipped.

At SGNews, repairing the publishing process included making skipped articles visible so they could be processed again.

Written by
Patrick Gibbs
Published
Reading time
2 min read

SGNews is a news site that publishes through an AI editorial pipeline I built. AI rewrites each source story as a short briefing, and the pipeline publishes it. I also worked on how it collected source stories and handled failures.

The project record counted 47,277 articles published between 7 May and 12 September 2026, including 2,445 in the final measured week. Those are historical figures from the site’s public data.

The articles left behind

Thirteen articles had been skipped by earlier processing runs. Some source pages carried too little text for a full briefing, so I had the AI write a shorter summary for thin pages instead of skipping them. After that repair, a recorded run processed the thirteen articles in 89 seconds with no errors.

That timing describes one run. The more useful lesson was that the waiting articles could be identified and recovered, instead of disappearing into an apparently successful process.

Show what failed

A source can stop working for several reasons: its page structure changes, it returns no article text, or access is blocked. Those failures need different fixes.

I worked on identifying those conditions and keeping the processing queue moving through the waiting articles. For a business relying on automatic publishing, knowing what was skipped is part of knowing whether the system is working.

Related work
SGNews

Say hello.

Tell me what you'd like to build or improve.

Quick navigation

Find a page.

Use the arrow keys to choose a result, Enter to open it, or Escape to close.