How we verify

Every load-bearing claim carries a source

Not "studies show." An actual primary reference - the original paper, the engineer's own interview, the patent record - with a date. Where we cannot confirm something in a primary source, we do not quietly drop it and we do not assert it. We mark it as unverified, on the page, and say why.

Independent checks challenge the draft

Before publication, a Blueprint is checked independently against its sources. The checker is separate from the writer so it can challenge confident wording, missing caveats, and citations that do not support the claim. A material unresolved objection blocks publication.

Human accountability stays visible

Machines can challenge factual errors; they do not own judgment, taste, or honesty. A Blueprint that passes independent source checks may appear while its final curatorial review is still pending, and the page says so clearly. The human curator owns the direction, reviews the library, and can correct or withdraw anything that does not meet the project's standard.

We tell you when the famous story is wrong

Many beloved biomimicry stories are half-myth. The "constant-temperature" termite mound was corrected by biologists decades ago; "the Gila monster gave us Ozempic" is flatly incorrect. When a story is part legend, you get both halves here - the tidy version and what the researchers actually measured. The honest version is usually the more useful one anyway.

This is the opposite of AI slop. It is slower, it kills some of our best lines, and it is the whole point.