Why fact extraction and published claims stay separate in ProfileScribe
Abstracts
Abstracts
One design choice behind ProfileScribe: the crawler agent that reads approved sources never writes directly to a public profile. It normalizes what it finds into timestamped facts first, and those facts sit in a review queue before anything becomes a claim someone can read.
That separation exists because professional profiles are often wrong in small, compounding ways — a stale title, a project that quietly changed scope, a link that no longer points where it used to. Keeping extraction and publishing as distinct steps makes it possible to check evidence before it becomes a statement about someone's work.
It is a narrow piece of the system, but it is the piece that decides whether the rest of the profile can be trusted.