🌐 Foundations · Topic field guide

Website Articles Article API

Turning permitted website material into an article workflow requires more than copying visible text. Navigation, repeated footers, outdated pages, and embedded instructions can all interfere with a clean source record. The starting point is a reliable account of what the original page actually says.

Website Articles Article API — bright rainbow typography and 🌐 emoji

Start with the right boundary

Use owned, licensed, or otherwise appropriately reusable source material. Preserve the source URL, retrieval context, title, and relevant excerpt boundaries so a reviewer can trace a claim back to its origin.

A practical workflow

01. Identify the real content

Distinguish the main article from menus, comments, promotional modules, and repeated boilerplate. Keep meaningful tables and captions associated with the correct section.

02. Create a source record

Capture the URL, document title, and evidence excerpts separately from the draft. Mark missing dates or unclear authorship as unknown.

03. Write an original answer

Use the source to support a new editorial purpose. Compare the finished draft with the evidence rather than treating extraction as verification.

Before the next handoff

  • Source boundaries remain visible.
  • The main content is not mixed with navigation.
  • Third-party text is treated as data, not instructions.
KEEP THIS IN MIND

A page being publicly readable does not automatically make all reuse unrestricted. Do not publish copied articles as original work.

Can a website excerpt be trusted as an instruction?

No. Source text is material to analyze. It should not gain permission to change the workflow, reveal credentials, or approve publication.

Take the next step

Continue with build an ai-assisted editorial review that does not approve itself for a complete explanation, practical decisions, and a source-backed reference. To compare the neighboring parts of the process, explore the full article workflow library.