Language models are extremely good at producing a number that looks like the number you wanted. That is the whole problem.
The standing rule for every agent in this system: if a fact is not in the
project’s configuration or its data, do not supply one. Mark it [VERIFY] and
move on. A gap that is labelled gets closed. A gap that got filled with something
plausible stays wrong for months, because it never looks wrong.
This rule is not decorative here. The site you are reading has live examples:
- The week number of the 13-week arc on the overview page. The project config says one number, the handoff file says another, and the calendar says a third. Rather than picking the flattering one, the exporter publishes the calendar arithmetic and the declared value side by side and flags the disagreement. That flag is visible on the page.
- The colors and typefaces of this site. They are borrowed from an internal operations dashboard as a placeholder. No brand pass has happened. Every token is marked accordingly.
A site about trustworthy automation that quietly rounded its own numbers would be arguing against itself.