Methodology

How a story earns its place.

1. 01

   Discovery

   Sources are checked hourly; items older than seven days do not enter the queue. Freshness is decided by publish timestamps, never by a model's opinion, and items without a trustworthy timestamp are dropped rather than guessed at. Each exact feed item is fingerprinted so it is never evaluated twice; similar coverage from a different publisher can still enter review and is caught later (see deduplication below).

2. 02

   Independent review

   Review workers run every ten minutes. Two AI reviewers built on frontier models from two different AI labs evaluate each candidate separately; neither sees the other's verdict. Each works from the story's headline, metadata, and the material supplied through the source's feed — up to two thousand characters, sometimes only a snippet — scores four editorial dimensions, and casts a single vote: worth a busy reader's time, or not.

3. 03

   The unanimous gate

   A story is published only when both reviewers vote yes. There is no score threshold for publication — the votes decide; the composite score ranks accepted stories afterward. One enthusiastic reviewer is not enough, and disagreement means the story does not run.

4. 04

   An original brief

   Accepted stories get a summary in our own words — a one-line reason the story matters and three to five key points — produced in a separate pass by a dedicated writer model that never votes. Selection is a two-model judgment; the brief's wording is not, and readers should not infer that the reviewers verified every sentence of the summary.

5. 05

   Attribution

   Every story credits its source and links prominently to the original. We never reproduce full articles or substantial passages; occasional excerpts are short, quoted, and attributed. The brief is a reason to click through, not a substitute.