Concepts
Core concepts
Nine ideas. Each page states the idea in plain language, then precisely, then shows it in real code from a real experiment, then says what an engineering agent should do differently because of it, and then how it is most often got wrong.
The concepts
Core concepts
The nine ideas the methodology is assembled from, each with its evidence and its common failure mode.
Explicit domain state
A named state instead of a combination of flags that a reader has to decode.
Legal transitions
Which changes the model permits, declared once, enforced everywhere.
Capabilities
What an actor may do next, derived from the rules rather than maintained beside them.
Obligations, effects and uncertainty
What is still owed, what leaves the system, and what is honestly not known yet.
Boundaries and authority
Where a constrained value becomes an open one, and what three of the experiments measured there.
Structural locality
A feature's parts stay together; the authority that decides its rules stays singular.
Navigation and context
Deterministic routing to the right semantic area, and honest diagnostics when that fails.
Heterogeneous verification
Several mechanisms that fail differently, because no single one covers the failure set.
Evidence and traceability
What was measured, how, and what must never be concluded from it.
How to read the confidence labels
Some of these concepts are mechanisms — they work by construction, and the evidence is that the mechanism does what it says. Others are claims about outcomes, and those carry an evidence state: supported, provisional, contradicted or open. The two are never merged. A contract Ordo requires can be adopted while the benefit it predicts remains unproven, and where that is the case, this site says so on the page.