This project tests one idea. Can AI agents understand and act on digital systems better when their knowledge is a graph? Here that graph is called a Canonical Representation. The other choice is text written for people. A smaller test on format alone found no gain it could measure. In July 2026 we wrote the test plan first, then gave an AI model the same facts as a document and as a graph. It scored the same both times: 8 of 8 tasks, both to recall facts and to take an action. The question this project tracks now is wider and harder to fake. Can an AI interface run for months with a Canonical Representation as its only source of knowledge? That means no second store of knowledge beside it.
Linked from: The Graph Web (investigates), The problem (motivates), Where it could lead (depends on), Format test (July 2026) (tests), Plain page test (September 2026) (tests), Review of the idea (October 2026) (tests).
«The idea it tests» on the page with every Node · The same content as JSON