How this site works

Every guide is drafted by an AI pipeline and reviewed by a human once a week. Nothing publishes without a merge.

Each Monday a writer agent picks topics from a backlog, researches them on the web and drafts a guide to a fixed template. Automated checks test word count, structure, source links and compliance language. A separate critic agent scores the draft against a rubric and can send it back for one revision. The result opens as a pull request, and a human approves, edits or rejects it. Every outcome is logged below.

Drafts reviewed

0

Accepted

n/a

Average human edit

n/a

Critic agrees with human

n/a

Cost per accepted guide

n/a