What We Solve

We do not ask AI to guess an answer. We preserve domain facts, dependencies, constraints and grounds as inspectable objects. A violation writes nothing and explains why.

Dialect matrix

DialectInputMachine criterionEvidence output
Narrative / White DrumLong-form serialFive gates + foreshadowing state machineEach chapter’s world state is Node-verifiable. Example: a thread marked resolved without payoff is rejected with zero writes.
Judgment grounds chainJudgment textStatutory sentencing rangesZero writes on violation + grounds. Example: a 55% voluntary-surrender reduction exceeds the 40% cap and is rejected immediately.
Spreadsheet dependency chainExcel formulasrelations dependency graph“Which ten manual inputs determine this number?” A broken formula reference does not produce a plausible-looking trace.
CAD reviewDWG / DXF openingsObject-level constraintsAudit list + location anchors. An opening count without source-object anchors is not written.
Textbook checkDOCX illustration rulesFigure-number / citation consistencyHealth report with red flags. A reference to a missing figure cannot be marked passed.
Project stateChat historyIdempotent state transactionsMCP restores in seconds. A stale expected_state_version returns a conflict and writes nothing.

See a rejection run

The point of the law dialect is not to generate a judgment, but to reject an unsupported state change. The local browser demo deliberately pushes a surrender reduction past its ceiling and shows the statutory range and refusal.

Contact

hi@2origin.org · GitHub Issues ↗